From 937f5d5ec642501d2dd3c91918685de30a932b34 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Thu, 9 Sep 2021 18:01:28 -0700 Subject: Input: ads7846 - remove custom filter handling functions from pdata The functions in the platform data struct to initialize, cleanup and apply custom filters are not in use by any mainline board. Remove support for them to pave the road for more cleanups to come. The enum was moved as it has no users outside of the driver code itself. Signed-off-by: Daniel Mack Reviewed-by: Marco Felsch Link: https://lore.kernel.org/r/20210907200726.2034962-3-daniel@zonque.org Signed-off-by: Dmitry Torokhov --- include/linux/spi/ads7846.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/ads7846.h b/include/linux/spi/ads7846.h index 1a5eaef3b7f2..d424c1aadf38 100644 --- a/include/linux/spi/ads7846.h +++ b/include/linux/spi/ads7846.h @@ -1,17 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* linux/spi/ads7846.h */ -/* Touchscreen characteristics vary between boards and models. The - * platform_data for the device's "struct device" holds this information. - * - * It's OK if the min/max values are zero. - */ -enum ads7846_filter { - ADS7846_FILTER_OK, - ADS7846_FILTER_REPEAT, - ADS7846_FILTER_IGNORE, -}; - struct ads7846_platform_data { u16 model; /* 7843, 7845, 7846, 7873. */ u16 vref_delay_usecs; /* 0 for external vref; etc */ @@ -51,10 +40,6 @@ struct ads7846_platform_data { int gpio_pendown_debounce; /* platform specific debounce time for * the gpio_pendown */ int (*get_pendown_state)(void); - int (*filter_init) (const struct ads7846_platform_data *pdata, - void **filter_data); - int (*filter) (void *filter_data, int data_idx, int *val); - void (*filter_cleanup)(void *filter_data); void (*wait_for_sync)(void); bool wakeup; unsigned long irq_flags; -- cgit v1.2.3 From 537d3af1bee8ad1415fda9b622d1ea6d1ae76dfa Mon Sep 17 00:00:00 2001 From: Arnaud Pouliquen Date: Mon, 12 Jul 2021 14:39:12 +0200 Subject: rpmsg: Fix rpmsg_create_ept return when RPMSG config is not defined According to the description of the rpmsg_create_ept in rpmsg_core.c the function should return NULL on error. Fixes: 2c8a57088045 ("rpmsg: Provide function stubs for API") Signed-off-by: Arnaud Pouliquen Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210712123912.10672-1-arnaud.pouliquen@foss.st.com Signed-off-by: Bjorn Andersson --- include/linux/rpmsg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index d97dcd049f18..a8dcf8a9ae88 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -231,7 +231,7 @@ static inline struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_device *rpdev /* This shouldn't be possible */ WARN_ON(1); - return ERR_PTR(-ENXIO); + return NULL; } static inline int rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len) -- cgit v1.2.3 From f4c87dbbef2638f6da6e29b5e998e3b1dcdb08ee Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 9 Aug 2021 13:25:13 +0200 Subject: kcsan: Save instruction pointer for scoped accesses Save the instruction pointer for scoped accesses, so that it becomes possible for the reporting code to construct more accurate stack traces that will show the start of the scope. Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 9fd0ad80fef6..5f5965246877 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -100,9 +100,12 @@ void kcsan_set_access_mask(unsigned long mask); /* Scoped access information. */ struct kcsan_scoped_access { struct list_head list; + /* Access information. */ const volatile void *ptr; size_t size; int type; + /* Location where scoped access was set up. */ + unsigned long ip; }; /* * Automatically call kcsan_end_scoped_access() when kcsan_scoped_access goes -- cgit v1.2.3 From a2aec2c86ef0cad0fd6be718cfeb5cf5eefbfca9 Mon Sep 17 00:00:00 2001 From: "GONG, Ruiqi" Date: Mon, 30 Aug 2021 16:33:56 +0800 Subject: mtd: Remove obsolete macros only used by the old nand_ecclayout struct All uses of MTD_MAX_{OOBFREE,ECCPOS}_ENTRIES_LARGE have been removed as commit ef5eeea6e911 ("mtd: nand: brcm: switch to mtd_ooblayout_ops") and commit aab616e31d1c ("mtd: kill the nand_ecclayout struct") replaced struct nand_ecclayout by the new mtd_ooblayout_ops interface. Remove these two macros therefore. Reported-by: Yi Yang Signed-off-by: GONG, Ruiqi Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210830083356.31702-1-gongruiqi1@huawei.com --- include/linux/mtd/mtd.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 88227044fc86..f5e7dfc2e4e9 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -72,8 +72,6 @@ struct mtd_oob_ops { uint8_t *oobbuf; }; -#define MTD_MAX_OOBFREE_ENTRIES_LARGE 32 -#define MTD_MAX_ECCPOS_ENTRIES_LARGE 640 /** * struct mtd_oob_region - oob region definition * @offset: region offset -- cgit v1.2.3 From 06dc660e6eb8817c4c379d2ca290ae0b3f77c69f Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 14 Sep 2021 01:27:08 +1000 Subject: PCI: Rename pcibios_add_device() to pcibios_device_add() The general convention for pcibios_* hooks is that they're named after the corresponding pci_* function they provide a hook for. The exception is pcibios_add_device() which provides a hook for pci_device_add(). Rename pcibios_add_device() to pcibios_device_add() so it matches pci_device_add(). Also, remove the export of the microblaze version. The only caller must be compiled as a built-in so there's no reason for the export. Link: https://lore.kernel.org/r/20210913152709.48013-1-oohall@gmail.com Signed-off-by: Oliver O'Halloran Signed-off-by: Bjorn Helgaas Acked-by: Niklas Schnelle # s390 --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..7e0ce3a4d5a1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2126,7 +2126,7 @@ void pcibios_disable_device(struct pci_dev *dev); void pcibios_set_master(struct pci_dev *dev); int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state); -int pcibios_add_device(struct pci_dev *dev); +int pcibios_device_add(struct pci_dev *dev); void pcibios_release_device(struct pci_dev *dev); #ifdef CONFIG_PCI void pcibios_penalize_isa_irq(int irq, int active); -- cgit v1.2.3 From d1c6e08e7503649e4a4f3f9e700e2c05300b6379 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:11:37 -0700 Subject: libnvdimm/labels: Add uuid helpers In preparation for CXL labels that move the uuid to a different offset in the label, add nsl_{ref,get,validate}_uuid(). These helpers use the proper uuid_t type. That type definition predated the libnvdimm subsystem, so now is as a good a time as any to convert all the uuid handling in the subsystem to uuid_t to match the helpers. Note that the uuid fields in the label data and superblocks is not replaced per Andy's expectation that uuid_t is a kernel internal type not to appear in external ABI interfaces. So, in those case {import,export}_uuid() is used to go between the 2 types. Also note that this rework uncovered some unnecessary copies for label comparisons, those are cleaned up with nsl_uuid_equal(). As for the whitespace changes, all new code is clang-format compliant. Reported-by: Andy Shevchenko Reviewed-by: Andy Shevchenko Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116429748.2460985.15659993454313919977.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/nd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nd.h b/include/linux/nd.h index ee9ad76afbba..8a8c63edb1b2 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -88,7 +88,7 @@ struct nd_namespace_pmem { struct nd_namespace_io nsio; unsigned long lbasize; char *alt_name; - u8 *uuid; + uuid_t *uuid; int id; }; @@ -105,7 +105,7 @@ struct nd_namespace_pmem { struct nd_namespace_blk { struct nd_namespace_common common; char *alt_name; - u8 *uuid; + uuid_t *uuid; int id; unsigned long lbasize; resource_size_t size; -- cgit v1.2.3 From 23c64d7618a7e76e46db99444d184ef75498fb71 Mon Sep 17 00:00:00 2001 From: Piyush Mehta Date: Wed, 22 Sep 2021 19:23:17 +0530 Subject: firmware: zynqmp: Add MMIO read and write support for PS_MODE pin Add Xilinx ZynqMP firmware MMIO APIs support to set and get PS_MODE pins value and status. These APIs create an interface path between mode pin controller driver and low-level API to access GPIO pins. Signed-off-by: Piyush Mehta Acked-by: Michal Simek Acked-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- include/linux/firmware/xlnx-zynqmp.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 56b426fe020c..3917f89b2b3c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -72,6 +72,8 @@ enum pm_api_id { PM_SET_REQUIREMENT = 15, PM_RESET_ASSERT = 17, PM_RESET_GET_STATUS = 18, + PM_MMIO_WRITE = 19, + PM_MMIO_READ = 20, PM_PM_INIT_FINALIZE = 21, PM_FPGA_LOAD = 22, PM_FPGA_GET_STATUS = 23, @@ -390,6 +392,8 @@ int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); +unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode); +int zynqmp_pm_bootmode_write(u32 ps_mode); int zynqmp_pm_init_finalize(void); int zynqmp_pm_set_suspend_mode(u32 mode); int zynqmp_pm_request_node(const u32 node, const u32 capabilities, @@ -520,6 +524,16 @@ static inline int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, return -ENODEV; } +static inline unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_bootmode_write(u32 ps_mode) +{ + return -ENODEV; +} + static inline int zynqmp_pm_init_finalize(void) { return -ENODEV; -- cgit v1.2.3 From d50497c4a05e73e76874fd0d4942036375a7ec0f Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 15 Sep 2021 18:46:27 -0700 Subject: platform/chrome: cros_ec_proto: Fix check_features ret val The kerneldoc for cros_ec_check_features() states that it returns 1 or 0 depedending on whether a feature is supported or not, but it instead returns a negative error number in one case, and a non-1 bitmask in other cases. Since all call-sites only check for a 1 or 0 return value, update the function to return boolean values. Signed-off-by: Prashant Malani Reviewed-by: Guenter Roeck Signed-off-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20210916014632.2662612-1-pmalani@chromium.org --- include/linux/platform_data/cros_ec_proto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 02599687770c..55844ece0b32 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -227,7 +227,7 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); -int cros_ec_check_features(struct cros_ec_dev *ec, int feature); +bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); -- cgit v1.2.3 From e765f13ed126fe7e41d1a6e3c60d754cd6c2af93 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Sep 2021 19:34:30 +0200 Subject: nvdimm/pmem: move dax_attribute_group from dax to pmem dax_attribute_group is only used by the pmem driver, and can avoid the completely pointless lookup by the disk name if moved there. This leaves just a single caller of dax_get_by_host, so move dax_get_by_host into the same ifdef block as that caller. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20210922173431.2454024-3-hch@lst.de Signed-off-by: Dan Williams --- include/linux/dax.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 2619d94c308d..8623caa67388 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -38,8 +38,6 @@ struct dax_operations { int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); }; -extern struct attribute_group dax_attribute_group; - #if IS_ENABLED(CONFIG_DAX) struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags); -- cgit v1.2.3 From 7b4d7894c65bd1e83b2f021d7944a46bdd64836a Mon Sep 17 00:00:00 2001 From: Deepak Kumar Singh Date: Tue, 31 Aug 2021 20:00:27 +0530 Subject: soc: qcom: aoss: Expose send for generic usecase Not all upcoming usecases will have an interface to allow the aoss driver to hook onto. Expose the send api and create a get function to enable drivers to send their own messages to aoss. Signed-off-by: Chris Lew Signed-off-by: Deepak Kumar Singh Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/1630420228-31075-2-git-send-email-deesin@codeaurora.org --- include/linux/soc/qcom/qcom_aoss.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/linux/soc/qcom/qcom_aoss.h (limited to 'include/linux') diff --git a/include/linux/soc/qcom/qcom_aoss.h b/include/linux/soc/qcom/qcom_aoss.h new file mode 100644 index 000000000000..3c2a82e606f8 --- /dev/null +++ b/include/linux/soc/qcom/qcom_aoss.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + */ + +#ifndef __QCOM_AOSS_H__ +#define __QCOM_AOSS_H__ + +#include +#include + +struct qmp; + +#if IS_ENABLED(CONFIG_QCOM_AOSS_QMP) + +int qmp_send(struct qmp *qmp, const void *data, size_t len); +struct qmp *qmp_get(struct device *dev); +void qmp_put(struct qmp *qmp); + +#else + +static inline int qmp_send(struct qmp *qmp, const void *data, size_t len) +{ + return -ENODEV; +} + +static inline struct qmp *qmp_get(struct device *dev) +{ + return ERR_PTR(-ENODEV); +} + +static inline void qmp_put(struct qmp *qmp) +{ +} + +#endif + +#endif -- cgit v1.2.3 From af9d82626c8f8547910e3e22c76ced3f5d5f5286 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 24 Aug 2021 14:20:51 +0200 Subject: PCI/ACPI: Remove OSC_PCI_SUPPORT_MASKS and OSC_PCI_CONTROL_MASKS These masks are only used internally in the PCI Host Bridge _OSC negotiation code, which already makes sure nothing outside of these masks is set. Remove the masks and simplify the code. Suggested-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20210824122054.29481-2-joro@8bytes.org Signed-off-by: Joerg Roedel Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 974d497a897d..eb59fd3052c0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -577,7 +577,6 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_MSI_SUPPORT 0x00000010 #define OSC_PCI_EDR_SUPPORT 0x00000080 #define OSC_PCI_HPX_TYPE_3_SUPPORT 0x00000100 -#define OSC_PCI_SUPPORT_MASKS 0x0000019f /* PCI Host Bridge _OSC: Capabilities DWORD 3: Control Field */ #define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL 0x00000001 @@ -587,7 +586,6 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_EXPRESS_CAPABILITY_CONTROL 0x00000010 #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 -#define OSC_PCI_CONTROL_MASKS 0x000000bf #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 -- cgit v1.2.3 From 7101c83950e629b83f9d827f288063e52074a6ea Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 29 Sep 2021 19:23:50 -0700 Subject: platform/chrome: cros_usbpd_notify: Move ec_command() cros_ec_command() can be used by other modules too. So, move it to a common location and export it. This patch does not introduce any functional changes. Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20210930022403.3358070-3-pmalani@chromium.org --- include/linux/platform_data/cros_ec_proto.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 55844ece0b32..20b17c43caeb 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -231,6 +231,9 @@ bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); +int cros_ec_command(struct cros_ec_device *ec_dev, int command, uint8_t *outdata, int outsize, + uint8_t *indata, int insize); + /** * cros_ec_get_time_ns() - Return time in ns. * -- cgit v1.2.3 From 5d122256f4e5900f7f8de5d8787af570314f6701 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 29 Sep 2021 19:23:52 -0700 Subject: platform/chrome: cros_ec_proto: Make data pointers void Convert the input and output data pointers for cros_ec_command() to void pointers so that the callers don't have to cast their custom structs to uint8_t *. Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20210930022403.3358070-4-pmalani@chromium.org --- include/linux/platform_data/cros_ec_proto.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 20b17c43caeb..f833473c5f44 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -231,8 +231,8 @@ bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); -int cros_ec_command(struct cros_ec_device *ec_dev, int command, uint8_t *outdata, int outsize, - uint8_t *indata, int insize); +int cros_ec_command(struct cros_ec_device *ec_dev, int command, void *outdata, int outsize, + void *indata, int insize); /** * cros_ec_get_time_ns() - Return time in ns. -- cgit v1.2.3 From 4f1406396ed4d97518b8112327bdaf14fc9d4090 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 29 Sep 2021 19:23:54 -0700 Subject: platform/chrome: cros_ec_proto: Add version for ec_command Add a version parameter to cros_ec_command() for callers that may want to specify which version of the host command they would like to use. Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20210930022403.3358070-5-pmalani@chromium.org --- include/linux/platform_data/cros_ec_proto.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index f833473c5f44..9d370816a419 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -231,8 +231,8 @@ bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); -int cros_ec_command(struct cros_ec_device *ec_dev, int command, void *outdata, int outsize, - void *indata, int insize); +int cros_ec_command(struct cros_ec_device *ec_dev, unsigned int version, int command, void *outdata, + int outsize, void *indata, int insize); /** * cros_ec_get_time_ns() - Return time in ns. -- cgit v1.2.3 From dae9a6cab8009e526570e7477ce858dcdfeb256e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 30 Sep 2021 17:06:21 -0400 Subject: NFSD: Have legacy NFSD WRITE decoders use xdr_stream_subsegment() Refactor. Now that the NFSv2 and NFSv3 XDR decoders have been converted to use xdr_streams, the WRITE decoder functions can use xdr_stream_subsegment() to extract the WRITE payload into its own xdr_buf, just as the NFSv4 WRITE XDR decoder currently does. That makes it possible to pass the first kvec, pages array + length, page_base, and total payload length via a single function parameter. The payload's page_base is not yet assigned or used, but will be in subsequent patches. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 064c96157d1f..6263410c948a 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -532,8 +532,7 @@ int svc_encode_result_payload(struct svc_rqst *rqstp, unsigned int offset, unsigned int length); unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, - struct page **pages, - struct kvec *first, size_t total); + struct xdr_buf *payload); char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, struct kvec *first, void *p, size_t total); -- cgit v1.2.3 From ca05cbae2a0468e5d78e9b4605936a8bf5da328b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 10 Jul 2021 18:07:14 -0400 Subject: NFS: Fix up nfs_ctx_key_to_expire() If the cached credential exists but doesn't have any expiration callback then exit early. Fix up atomicity issues when replacing the credential with a new one since the existing code could lead to refcount leaks. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b9a8b925db43..9b75448ce0df 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -81,7 +81,7 @@ struct nfs_open_context { fl_owner_t flock_owner; struct dentry *dentry; const struct cred *cred; - struct rpc_cred *ll_cred; /* low-level cred - use to check for expiry */ + struct rpc_cred __rcu *ll_cred; /* low-level cred - use to check for expiry */ struct nfs4_state *state; fmode_t mode; -- cgit v1.2.3 From b9f8713f42af11ae6d7f63075334ba5298436be6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 12 Jul 2021 12:24:15 -0400 Subject: SUNRPC: Remove unnecessary memory barriers The only check for RPC_TASK_RUNNING is the one in rpc_make_runnable(), which happens under the same spin lock held when we call rpc_clear_running(). Ditto, the last check for RPC_TASK_QUEUED in rpc_execute() is performed under the same lock as the one held when we call rpc_clear_queued(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index a237b8dbf608..db964bb63912 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -150,25 +150,13 @@ struct rpc_task_setup { #define RPC_TASK_MSG_PIN_WAIT 5 #define RPC_TASK_SIGNALLED 6 -#define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) -#define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_test_and_set_running(t) \ test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) -#define rpc_clear_running(t) \ - do { \ - smp_mb__before_atomic(); \ - clear_bit(RPC_TASK_RUNNING, &(t)->tk_runstate); \ - smp_mb__after_atomic(); \ - } while (0) +#define rpc_clear_running(t) clear_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define RPC_IS_QUEUED(t) test_bit(RPC_TASK_QUEUED, &(t)->tk_runstate) #define rpc_set_queued(t) set_bit(RPC_TASK_QUEUED, &(t)->tk_runstate) -#define rpc_clear_queued(t) \ - do { \ - smp_mb__before_atomic(); \ - clear_bit(RPC_TASK_QUEUED, &(t)->tk_runstate); \ - smp_mb__after_atomic(); \ - } while (0) +#define rpc_clear_queued(t) clear_bit(RPC_TASK_QUEUED, &(t)->tk_runstate) #define RPC_IS_ACTIVATED(t) test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate) -- cgit v1.2.3 From ff81dfb5d721fff87bd516c558847f6effb70031 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 28 Sep 2021 14:33:44 -0400 Subject: NFS: Further optimisations for 'ls -l' If a user is doing 'ls -l', we have a heuristic in GETATTR that tells the readdir code to try to use READDIRPLUS in order to refresh the inode attributes. In certain cirumstances, we also try to invalidate the remaining directory entries in order to ensure this refresh. If there are multiple readers of the directory, we probably should avoid invalidating the page cache, since the heuristic breaks down in that situation anyway. Signed-off-by: Trond Myklebust Tested-by: Benjamin Coddington Reviewed-by: Benjamin Coddington --- include/linux/nfs_fs.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 9b75448ce0df..ca547cc5458c 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -103,6 +103,7 @@ struct nfs_open_dir_context { __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; __u64 dup_cookie; + pgoff_t page_index; signed char duped; }; @@ -181,9 +182,6 @@ struct nfs_inode { struct rw_semaphore rmdir_sem; struct mutex commit_mutex; - /* track last access to cached pages */ - unsigned long page_index; - #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ @@ -272,6 +270,7 @@ struct nfs4_copy_state { #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ +#define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ -- cgit v1.2.3 From 3734b9f2cee01d9dde2fbbda742ba6dd6ba10a29 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 27 Sep 2021 01:40:24 +0300 Subject: opp: Change type of dev_pm_opp_attach_genpd(names) argument Elements of the 'names' array are not changed by the code, constify them for consistency. Signed-off-by: Dmitry Osipenko Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 84150a22fd7c..7f1f066fc377 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -156,9 +156,9 @@ int devm_pm_opp_set_clkname(struct device *dev, const char *name); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); int devm_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); -struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); +struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs); void dev_pm_opp_detach_genpd(struct opp_table *opp_table); -int devm_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); +int devm_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs); struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, struct opp_table *dst_table, struct dev_pm_opp *src_opp); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); @@ -376,7 +376,7 @@ static inline int devm_pm_opp_set_clkname(struct device *dev, const char *name) return -EOPNOTSUPP; } -static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs) +static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs) { return ERR_PTR(-EOPNOTSUPP); } @@ -384,7 +384,7 @@ static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, cons static inline void dev_pm_opp_detach_genpd(struct opp_table *opp_table) {} static inline int devm_pm_opp_attach_genpd(struct device *dev, - const char **names, + const char * const *names, struct device ***virt_devs) { return -EOPNOTSUPP; -- cgit v1.2.3 From e69709f6861aaba80b4eaab6825e8c522a2afb5c Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 20 Sep 2021 20:22:46 +0300 Subject: opp: Add more resource-managed variants of dev_pm_opp_of_add_table() Add resource-managed variants of dev_pm_opp_of_add_table_indexed() and dev_pm_opp_of_add_table_noclk(), allowing drivers to remove boilerplate code. Signed-off-by: Dmitry Osipenko [ Viresh: Added underscore to devm_of_add_table_indexed() ] Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 7f1f066fc377..879c138c7b8e 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -439,7 +439,9 @@ static inline int dev_pm_opp_sync_regulators(struct device *dev) #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) int dev_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_add_table_indexed(struct device *dev, int index); +int devm_pm_opp_of_add_table_indexed(struct device *dev, int index); int dev_pm_opp_of_add_table_noclk(struct device *dev, int index); +int devm_pm_opp_of_add_table_noclk(struct device *dev, int index); void dev_pm_opp_of_remove_table(struct device *dev); int devm_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask); @@ -465,11 +467,21 @@ static inline int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) return -EOPNOTSUPP; } +static inline int devm_pm_opp_of_add_table_indexed(struct device *dev, int index) +{ + return -EOPNOTSUPP; +} + static inline int dev_pm_opp_of_add_table_noclk(struct device *dev, int index) { return -EOPNOTSUPP; } +static inline int devm_pm_opp_of_add_table_noclk(struct device *dev, int index) +{ + return -EOPNOTSUPP; +} + static inline void dev_pm_opp_of_remove_table(struct device *dev) { } -- cgit v1.2.3 From e68ce0faf29c7c268666e11e95bf27dca97d28b0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 2 Sep 2021 14:47:48 +0200 Subject: mfd: hi6421-spmi-pmic: Cleanup drvdata to only include regmap There are lots of fields in struct hi6421_spmi_pmic that aren't used. As a matter of fact, only regmap is needed. So, drop the struct as a whole, and set regmap as the drvdata. Signed-off-by: Mauro Carvalho Chehab Acked-by: Mark Brown Acked-by: Greg Kroah-Hartman Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/1828cb783b1ebca0b98bf0b3077d8701adb228f7.1630586862.git.mchehab+huawei@kernel.org --- include/linux/mfd/hi6421-spmi-pmic.h | 25 ------------------------- 1 file changed, 25 deletions(-) delete mode 100644 include/linux/mfd/hi6421-spmi-pmic.h (limited to 'include/linux') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h deleted file mode 100644 index e5b8dbf828b6..000000000000 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ /dev/null @@ -1,25 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Header file for device driver Hi6421 PMIC - * - * Copyright (c) 2013 Linaro Ltd. - * Copyright (C) 2011 Hisilicon. - * Copyright (c) 2020-2021 Huawei Technologies Co., Ltd - * - * Guodong Xu - */ - -#ifndef __HISI_PMIC_H -#define __HISI_PMIC_H - -#include -#include - -struct hi6421_spmi_pmic { - struct resource *res; - struct device *dev; - void __iomem *regs; - struct regmap *regmap; -}; - -#endif /* __HISI_PMIC_H */ -- cgit v1.2.3 From 5baaac3184ab896d74993825858f1b1a46c460ce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 15 Jun 2021 15:10:03 +0200 Subject: dma-buf: add dma_resv_for_each_fence v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A simpler version of the iterator to be used when the dma_resv object is locked. v2: fix index check here as well v3: minor coding improvement, some documentation cleanup Signed-off-by: Christian König Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20211006123609.2026-1-christian.koenig@amd.com --- include/linux/dma-resv.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 764138ad8583..491359cea54c 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -179,6 +179,8 @@ struct dma_resv_iter { struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor); struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor); +struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor); +struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor); /** * dma_resv_iter_begin - initialize a dma_resv_iter object @@ -244,6 +246,24 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) for (fence = dma_resv_iter_first_unlocked(cursor); \ fence; fence = dma_resv_iter_next_unlocked(cursor)) +/** + * dma_resv_for_each_fence - fence iterator + * @cursor: a struct dma_resv_iter pointer + * @obj: a dma_resv object pointer + * @all_fences: true if all fences should be returned + * @fence: the current fence + * + * Iterate over the fences in a struct dma_resv object while holding the + * &dma_resv.lock. @all_fences controls if the shared fences are returned as + * well. The cursor initialisation is part of the iterator and the fence stays + * valid as long as the lock is held and so no extra reference to the fence is + * taken. + */ +#define dma_resv_for_each_fence(cursor, obj, all_fences, fence) \ + for (dma_resv_iter_begin(cursor, obj, all_fences), \ + fence = dma_resv_iter_first(cursor); fence; \ + fence = dma_resv_iter_next(cursor)) + #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) -- cgit v1.2.3 From 0392dd51f9c78d46109a408f27dc820300dcd8bd Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 4 Oct 2021 10:10:10 -0400 Subject: SUNRPC: Per-rpc_clnt task PIDs The current range of RPC task PIDs is 0..65535. That's not adequate for distinguishing tasks across multiple rpc_clnts running high throughput workloads. To help relieve this situation and to reduce the bottleneck of having a single atomic for assigning all RPC task PIDs, assign task PIDs per rpc_clnt. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index a4661646adc9..267b7aeaf1a6 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -40,6 +40,7 @@ struct rpc_clnt { unsigned int cl_clid; /* client id */ struct list_head cl_clients; /* Global list of clients */ struct list_head cl_tasks; /* List of tasks */ + atomic_t cl_pid; /* task PID counter */ spinlock_t cl_lock; /* spinlock */ struct rpc_xprt __rcu * cl_xprt; /* transport */ const struct rpc_procinfo *cl_procinfo; /* procedure info */ -- cgit v1.2.3 From 5e51cc0005c6ed1b793c228632f36269615f7c31 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Fri, 8 Oct 2021 10:50:07 +0100 Subject: dma-resv: Fix dma_resv_get_fences and dma_resv_copy_fences after conversion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cache the count of shared fences in the iterator to avoid dereferencing the dma_resv_object outside the RCU protection. Otherwise iterator and its users can observe an incosistent state which makes it impossible to use safely. Such as: <6> [187.517041] [IGT] gem_sync: executing <7> [187.536343] i915 0000:00:02.0: [drm:i915_gem_context_create_ioctl [i915]] HW context 1 created <7> [187.536793] i915 0000:00:02.0: [drm:i915_gem_context_create_ioctl [i915]] HW context 1 created <6> [187.551235] [IGT] gem_sync: starting subtest basic-many-each <1> [188.935462] BUG: kernel NULL pointer dereference, address: 0000000000000010 <1> [188.935485] #PF: supervisor write access in kernel mode <1> [188.935495] #PF: error_code(0x0002) - not-present page <6> [188.935504] PGD 0 P4D 0 <4> [188.935512] Oops: 0002 [#1] PREEMPT SMP NOPTI <4> [188.935521] CPU: 2 PID: 1467 Comm: gem_sync Not tainted 5.15.0-rc4-CI-Patchwork_21264+ #1 <4> [188.935535] Hardware name: /NUC6CAYB, BIOS AYAPLCEL.86A.0049.2018.0508.1356 05/08/2018 <4> [188.935546] RIP: 0010:dma_resv_get_fences+0x116/0x2d0 <4> [188.935560] Code: 10 85 c0 7f c9 be 03 00 00 00 e8 15 8b df ff eb bd e8 8e c6 ff ff eb b6 41 8b 04 24 49 8b 55 00 48 89 e7 8d 48 01 41 89 0c 24 <4c> 89 34 c2 e8 41 f2 ff ff 49 89 c6 48 85 c0 75 8c 48 8b 44 24 10 <4> [188.935583] RSP: 0018:ffffc900011dbcc8 EFLAGS: 00010202 <4> [188.935593] RAX: 0000000000000000 RBX: 00000000ffffffff RCX: 0000000000000001 <4> [188.935603] RDX: 0000000000000010 RSI: ffffffff822e343c RDI: ffffc900011dbcc8 <4> [188.935613] RBP: ffffc900011dbd48 R08: ffff88812d255bb8 R09: 00000000fffffffe <4> [188.935623] R10: 0000000000000001 R11: 0000000000000000 R12: ffffc900011dbd44 <4> [188.935633] R13: ffffc900011dbd50 R14: ffff888113d29cc0 R15: 0000000000000000 <4> [188.935643] FS: 00007f68d17e9700(0000) GS:ffff888277900000(0000) knlGS:0000000000000000 <4> [188.935655] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4> [188.935665] CR2: 0000000000000010 CR3: 000000012d0a4000 CR4: 00000000003506e0 <4> [188.935676] Call Trace: <4> [188.935685] i915_gem_object_wait+0x1ff/0x410 [i915] <4> [188.935988] i915_gem_wait_ioctl+0xf2/0x2a0 [i915] <4> [188.936272] ? i915_gem_object_wait+0x410/0x410 [i915] <4> [188.936533] drm_ioctl_kernel+0xae/0x140 <4> [188.936546] drm_ioctl+0x201/0x3d0 <4> [188.936555] ? i915_gem_object_wait+0x410/0x410 [i915] <4> [188.936820] ? __fget_files+0xc2/0x1c0 <4> [188.936830] ? __fget_files+0xda/0x1c0 <4> [188.936839] __x64_sys_ioctl+0x6d/0xa0 <4> [188.936848] do_syscall_64+0x3a/0xb0 <4> [188.936859] entry_SYSCALL_64_after_hwframe+0x44/0xae If the shared object has changed during the RCU unlocked period callers will correctly handle the restart on the next iteration. Signed-off-by: Tvrtko Ursulin Fixes: 96601e8a4755 ("dma-buf: use new iterator in dma_resv_copy_fences") Fixes: d3c80698c9f5 ("dma-buf: use new iterator in dma_resv_get_fences v3") Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/4274 Cc: Christian König Cc: Daniel Vetter Cc: Sumit Semwal Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20211008095007.972693-1-tvrtko.ursulin@linux.intel.com Reviewed-by: Christian König Signed-off-by: Christian König --- include/linux/dma-resv.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 491359cea54c..45f1d4812a37 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -170,9 +170,12 @@ struct dma_resv_iter { /** @index: index into the shared fences */ unsigned int index; - /** @fences: the shared fences */ + /** @fences: the shared fences; private, *MUST* not dereference */ struct dma_resv_list *fences; + /** @shared_count: number of shared fences */ + unsigned int shared_count; + /** @is_restarted: true if this is the first returned fence */ bool is_restarted; }; -- cgit v1.2.3 From bf2928c7a284e31f9f91a004b5dca09c522157c0 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 10 Sep 2021 08:22:06 +0200 Subject: PCI/VPD: Add pci_read/write_vpd_any() In certain cases we need a variant of pci_read_vpd()/pci_write_vpd() that does not check against dev->vpd.len. Such cases are: - Reading VPD if dev->vpd.len isn't set yet (in pci_vpd_size()) - Devices that map non-VPD information to arbitrary places in VPD address space (example: Chelsio T3 EEPROM write-protect flag) Therefore add pci_read_vpd_any() and pci_write_vpd_any() that check against PCI_VPD_MAX_SIZE only. Link: https://lore.kernel.org/r/93ecce28-a158-f02a-d134-8afcaced8efe@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas Acked-by: Jakub Kicinski --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..9649bd9e468d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1350,6 +1350,8 @@ void pci_unlock_rescan_remove(void); /* Vital Product Data routines */ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf); ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf); +ssize_t pci_read_vpd_any(struct pci_dev *dev, loff_t pos, size_t count, void *buf); +ssize_t pci_write_vpd_any(struct pci_dev *dev, loff_t pos, size_t count, const void *buf); /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx); -- cgit v1.2.3 From 0ae93b99beb283438aa571a6add4eab0c077d576 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 7 Oct 2021 16:17:24 -0400 Subject: SUNRPC: Simplify the SVC dispatch code path Micro-optimization: The last user of the generic SVC dispatch code path has been removed, so svc_process_common() can be simplified. This declutters the hot path so that the by-far most common case (a dispatch function exists) is made the /only/ path. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 6263410c948a..4205a6ef4770 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -443,10 +443,7 @@ struct svc_version { /* Need xprt with congestion control */ bool vs_need_cong_ctrl; - /* Override dispatch function (e.g. when caching replies). - * A return value of 0 means drop the request. - * vs_dispatch == NULL means use default dispatcher. - */ + /* Dispatch function */ int (*vs_dispatch)(struct svc_rqst *, __be32 *); }; -- cgit v1.2.3 From 8e9028b3790ddb02c407e1a4da0ab7cf82790e7e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 12 Oct 2021 15:42:59 -0500 Subject: PCI: Return NULL for to_pci_driver(NULL) to_pci_driver() takes a pointer to a struct device_driver and uses container_of() to find the struct pci_driver that contains it. If given a NULL pointer to a struct device_driver, return a NULL pci_driver pointer instead of applying container_of() to NULL. This simplifies callers that would otherwise have to check for a NULL pointer first. Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..a2d62165a7f7 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -900,7 +900,10 @@ struct pci_driver { struct pci_dynids dynids; }; -#define to_pci_driver(drv) container_of(drv, struct pci_driver, driver) +static inline struct pci_driver *to_pci_driver(struct device_driver *drv) +{ + return drv ? container_of(drv, struct pci_driver, driver) : NULL; +} /** * PCI_DEVICE - macro used to describe a specific PCI device -- cgit v1.2.3 From b3ec8cdf457e5e63d396fe1346cc788cf7c1b578 Mon Sep 17 00:00:00 2001 From: Claudio Suarez Date: Thu, 30 Sep 2021 17:10:26 +0200 Subject: fbdev: Garbage collect fbdev scrolling acceleration, part 1 (from TODO list) Scroll acceleration is disabled in fbcon by hard-wiring p->scrollmode = SCROLL_REDRAW. Remove the obsolete code in fbcon.c and fbdev/core/ Signed-off-by: Claudio Suarez Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/YVXTYqszZix9TxjJ@gineta.localdomain --- include/linux/fb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 5950f8f5dc74..6f3db99ab990 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -262,7 +262,7 @@ struct fb_ops { /* Draws a rectangle */ void (*fb_fillrect) (struct fb_info *info, const struct fb_fillrect *rect); - /* Copy data from area to another */ + /* Copy data from area to another. Obsolete. */ void (*fb_copyarea) (struct fb_info *info, const struct fb_copyarea *region); /* Draws a image to the display */ void (*fb_imageblit) (struct fb_info *info, const struct fb_image *image); -- cgit v1.2.3 From 16c663642c7ec03cd4cee5fec520bb69e97babe4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 12 Oct 2021 11:57:22 -0400 Subject: SUNRPC: Replace the "__be32 *p" parameter to .pc_decode The passed-in value of the "__be32 *p" parameter is now unused in every server-side XDR decoder, and can be removed. Note also that there is a line in each decoder that sets up a local pointer to a struct xdr_stream. Passing that pointer from the dispatcher instead saves one line per decoder function. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/lockd/xdr.h | 19 ++++++++++--------- include/linux/lockd/xdr4.h | 19 +++++++++---------- include/linux/sunrpc/svc.h | 3 ++- 3 files changed, 21 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index a98309c0121c..170ad6f5596a 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -96,18 +96,19 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); + int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); -int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); -int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); -int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_res(struct svc_rqst *, __be32 *); -int nlmsvc_decode_res(struct svc_rqst *, __be32 *); int nlmsvc_encode_void(struct svc_rqst *, __be32 *); -int nlmsvc_decode_void(struct svc_rqst *, __be32 *); -int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); -int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); -int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); #endif /* LOCKD_XDR_H */ diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 5ae766f26e04..68e14e0f2b1f 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -22,21 +22,20 @@ #define nlm4_fbig cpu_to_be32(NLM_FBIG) #define nlm4_failed cpu_to_be32(NLM_FAILED) +int nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); - -int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); -int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); -int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); -int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_res(struct svc_rqst *, __be32 *); -int nlm4svc_decode_res(struct svc_rqst *, __be32 *); int nlm4svc_encode_void(struct svc_rqst *, __be32 *); -int nlm4svc_decode_void(struct svc_rqst *, __be32 *); -int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); -int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); -int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); extern const struct rpc_version nlm_version4; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 4205a6ef4770..da3c5bc43d85 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -454,7 +454,8 @@ struct svc_procedure { /* process the request: */ __be32 (*pc_func)(struct svc_rqst *); /* XDR decode args: */ - int (*pc_decode)(struct svc_rqst *, __be32 *data); + int (*pc_decode)(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* XDR encode result: */ int (*pc_encode)(struct svc_rqst *, __be32 *data); /* XDR free result: */ -- cgit v1.2.3 From c44b31c263798ec34614dd394c31ef1a2e7e716e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 12 Oct 2021 11:57:28 -0400 Subject: SUNRPC: Change return value type of .pc_decode Returning an undecorated integer is an age-old trope, but it's not clear (even to previous experts in this code) that the only valid return values are 1 and 0. These functions do not return a negative errno, rpc_stat value, or a positive length. Document there are only two valid return values by having .pc_decode return only true or false. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/lockd/xdr.h | 18 +++++++++--------- include/linux/lockd/xdr4.h | 18 +++++++++--------- include/linux/sunrpc/svc.h | 2 +- 3 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 170ad6f5596a..e1362244f909 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -96,15 +96,15 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); int nlmsvc_encode_res(struct svc_rqst *, __be32 *); diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 68e14e0f2b1f..376b8f6a3763 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -22,15 +22,15 @@ #define nlm4_fbig cpu_to_be32(NLM_FBIG) #define nlm4_failed cpu_to_be32(NLM_FAILED) -int nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); int nlm4svc_encode_res(struct svc_rqst *, __be32 *); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index da3c5bc43d85..d6109fa7a57b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -454,7 +454,7 @@ struct svc_procedure { /* process the request: */ __be32 (*pc_func)(struct svc_rqst *); /* XDR decode args: */ - int (*pc_decode)(struct svc_rqst *rqstp, + bool (*pc_decode)(struct svc_rqst *rqstp, struct xdr_stream *xdr); /* XDR encode result: */ int (*pc_encode)(struct svc_rqst *, __be32 *data); -- cgit v1.2.3 From fda494411485aff91768842c532f90fb8eb54943 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 13 Oct 2021 10:41:06 -0400 Subject: SUNRPC: Replace the "__be32 *p" parameter to .pc_encode The passed-in value of the "__be32 *p" parameter is now unused in every server-side XDR encoder, and can be removed. Note also that there is a line in each encoder that sets up a local pointer to a struct xdr_stream. Passing that pointer from the dispatcher instead saves one line per encoder function. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/lockd/xdr.h | 8 ++++---- include/linux/lockd/xdr4.h | 8 ++++---- include/linux/sunrpc/svc.h | 3 ++- 3 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index e1362244f909..d8bd26a5525e 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -106,9 +106,9 @@ bool nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); -int nlmsvc_encode_res(struct svc_rqst *, __be32 *); -int nlmsvc_encode_void(struct svc_rqst *, __be32 *); -int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); +int nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); #endif /* LOCKD_XDR_H */ diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 376b8f6a3763..50677be3557d 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -32,10 +32,10 @@ bool nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); -int nlm4svc_encode_res(struct svc_rqst *, __be32 *); -int nlm4svc_encode_void(struct svc_rqst *, __be32 *); -int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); +int nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); extern const struct rpc_version nlm_version4; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index d6109fa7a57b..85694cd0db66 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -457,7 +457,8 @@ struct svc_procedure { bool (*pc_decode)(struct svc_rqst *rqstp, struct xdr_stream *xdr); /* XDR encode result: */ - int (*pc_encode)(struct svc_rqst *, __be32 *data); + int (*pc_encode)(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* XDR free result: */ void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ -- cgit v1.2.3 From 130e2054d4a652a2bd79fb1557ddcd19c053cb37 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 13 Oct 2021 10:41:13 -0400 Subject: SUNRPC: Change return value type of .pc_encode Returning an undecorated integer is an age-old trope, but it's not clear (even to previous experts in this code) that the only valid return values are 1 and 0. These functions do not return a negative errno, rpc_stat value, or a positive length. Document there are only two valid return values by having .pc_encode return only true or false. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/lockd/xdr.h | 8 ++++---- include/linux/lockd/xdr4.h | 8 ++++---- include/linux/sunrpc/svc.h | 2 +- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index d8bd26a5525e..398f70093cd3 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -106,9 +106,9 @@ bool nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); #endif /* LOCKD_XDR_H */ diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 50677be3557d..9a6b55da8fd6 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -32,10 +32,10 @@ bool nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); extern const struct rpc_version nlm_version4; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 85694cd0db66..0ae28ae6caf2 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -457,7 +457,7 @@ struct svc_procedure { bool (*pc_decode)(struct svc_rqst *rqstp, struct xdr_stream *xdr); /* XDR encode result: */ - int (*pc_encode)(struct svc_rqst *rqstp, + bool (*pc_encode)(struct svc_rqst *rqstp, struct xdr_stream *xdr); /* XDR free result: */ void (*pc_release)(struct svc_rqst *); -- cgit v1.2.3 From 06de2cd788bfa3b51137e9bd471d68029ab68103 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 12 Oct 2021 17:39:27 +0200 Subject: gpio: max730x: Make __max730x_remove() return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An spi or i2c remove callback is only called for devices that probed successfully. In this case this implies that __max730x_probe() set a non-NULL driver data. So the check ts == NULL is never true. With this check dropped, __max730x_remove() returns zero unconditionally. Make it return void instead which makes it easier to see in the callers that there is no error to handle. Also the return value of i2c and spi remove callbacks is ignored anyway. Signed-off-by: Uwe Kleine-König Signed-off-by: Bartosz Golaszewski --- include/linux/spi/max7301.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/max7301.h b/include/linux/spi/max7301.h index 21449067aedb..e392c53758bc 100644 --- a/include/linux/spi/max7301.h +++ b/include/linux/spi/max7301.h @@ -31,6 +31,6 @@ struct max7301_platform_data { u32 input_pullup_active; }; -extern int __max730x_remove(struct device *dev); +extern void __max730x_remove(struct device *dev); extern int __max730x_probe(struct max7301 *ts); #endif -- cgit v1.2.3 From e9bdcdbf6936dd1fbf419e00222dc9038b7812c2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 11 Oct 2021 15:32:44 +0200 Subject: pid: add pidfd_get_task() helper The number of system calls making use of pidfds is constantly increasing. Some of those new system calls duplicate the code to turn a pidfd into task_struct it refers to. Give them a simple helper for this. Link: https://lore.kernel.org/r/20211004125050.1153693-2-christian.brauner@ubuntu.com Link: https://lore.kernel.org/r/20211011133245.1703103-2-brauner@kernel.org Cc: Vlastimil Babka Cc: Suren Baghdasaryan Cc: Matthew Bobrowski Cc: Alexander Duyck Cc: David Hildenbrand Cc: Jan Kara Cc: Minchan Kim Reviewed-by: Matthew Bobrowski Acked-by: David Hildenbrand Signed-off-by: Christian Brauner --- include/linux/pid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index af308e15f174..343abf22092e 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -78,6 +78,7 @@ struct file; extern struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); +struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_create(struct pid *pid, unsigned int flags); static inline struct pid *get_pid(struct pid *pid) -- cgit v1.2.3 From 9f37ab0412eba537377c38b1dde1a04fbd7b5264 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 14 Oct 2021 14:18:59 +0000 Subject: PCI/switchtec: Add check of event support Not all events are supported by every gen/variant of the Switchtec firmware. To solve this, since Gen4, a new bit in each event header is introduced to indicate if an event is supported by the firmware. Link: https://lore.kernel.org/r/20211014141859.11444-6-kelvin.cao@microchip.com Signed-off-by: Logan Gunthorpe Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- include/linux/switchtec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index 082f1d51957a..be24056ac00f 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -19,6 +19,7 @@ #define SWITCHTEC_EVENT_EN_CLI BIT(2) #define SWITCHTEC_EVENT_EN_IRQ BIT(3) #define SWITCHTEC_EVENT_FATAL BIT(4) +#define SWITCHTEC_EVENT_NOT_SUPP BIT(31) #define SWITCHTEC_DMA_MRPC_EN BIT(0) -- cgit v1.2.3 From 9955548919c47a6987b40d90a30fd56bbc043e7b Mon Sep 17 00:00:00 2001 From: Arnaud Pouliquen Date: Fri, 1 Oct 2021 12:12:30 +0200 Subject: remoteproc: Remove vdev_to_rvdev and vdev_to_rproc from remoteproc API These both functions are only used by the remoteproc_virtio. There is no reason to expose them in the API. Move the functions in remoteproc_virtio.c Signed-off-by: Arnaud Pouliquen Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20211001101234.4247-4-arnaud.pouliquen@foss.st.com --- include/linux/remoteproc.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 83c09ac36b13..e0600e1e5c17 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -684,18 +684,6 @@ int rproc_coredump_add_custom_segment(struct rproc *rproc, void *priv); int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine); -static inline struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) -{ - return container_of(vdev->dev.parent, struct rproc_vdev, dev); -} - -static inline struct rproc *vdev_to_rproc(struct virtio_device *vdev) -{ - struct rproc_vdev *rvdev = vdev_to_rvdev(vdev); - - return rvdev->rproc; -} - void rproc_add_subdev(struct rproc *rproc, struct rproc_subdev *subdev); void rproc_remove_subdev(struct rproc *rproc, struct rproc_subdev *subdev); -- cgit v1.2.3 From 789c1093f02c436b320d78a739f9610c8271cb73 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 11 Oct 2021 21:21:14 +0800 Subject: rtc: class: don't call cdev_device_del() when cdev_device_add() failed I got a null-ptr-deref report when doing fault injection test: general protection fault, probably for non-canonical address 0xdffffc0000000022: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000110-0x0000000000000117] RIP: 0010:device_del+0x132/0xdc0 Call Trace: cdev_device_del+0x1a/0x80 devm_rtc_unregister_device+0x37/0x80 release_nodes+0xc3/0x3b0 If cdev_device_add() fails, 'dev->p' is not set, it causes null-ptr-deref when calling cdev_device_del(). Registering character device is optional, we don't return error code here, so introduce a new flag 'RTC_NO_CDEV' to indicate if it has character device, cdev_device_del() is called when this bit is not set. Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211011132114.3663509-1-yangyingliang@huawei.com --- include/linux/rtc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index bd611e26291d..354e0843ab17 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -80,6 +80,7 @@ struct rtc_timer { /* flags */ #define RTC_DEV_BUSY 0 +#define RTC_NO_CDEV 1 struct rtc_device { struct device dev; -- cgit v1.2.3 From c3f69c7f629ff53c75f335754ea41426b8e095de Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 12 Oct 2021 16:35:14 -0700 Subject: scsi: ata: Switch to attribute groups struct device supports attribute groups directly but does not support struct device_attribute directly. Hence switch to attribute groups. Link: https://lore.kernel.org/r/20211012233558.4066756-3-bvanassche@acm.org Acked-by: Damien Le Moal Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/linux/libata.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index c0c64f03e107..bd1b782d1bbf 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1388,7 +1388,7 @@ extern int ata_link_nr_enabled(struct ata_link *link); */ extern const struct ata_port_operations ata_base_port_ops; extern const struct ata_port_operations sata_port_ops; -extern struct device_attribute *ata_common_sdev_attrs[]; +extern const struct attribute_group *ata_common_sdev_groups[]; /* * All sht initializers (BASE, PIO, BMDMA, NCQ) must be instantiated @@ -1418,14 +1418,14 @@ extern struct device_attribute *ata_common_sdev_attrs[]; #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ - .sdev_attrs = ata_common_sdev_attrs + .sdev_groups = ata_common_sdev_groups #ifdef CONFIG_SATA_HOST -extern struct device_attribute *ata_ncq_sdev_attrs[]; +extern const struct attribute_group *ata_ncq_sdev_groups[]; #define ATA_NCQ_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ - .sdev_attrs = ata_ncq_sdev_attrs, \ + .sdev_groups = ata_ncq_sdev_groups, \ .change_queue_depth = ata_scsi_change_queue_depth #endif -- cgit v1.2.3 From b5f9c644eb1baafcd349ad134e2110773f8d0a38 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 4 Oct 2021 14:59:35 +0200 Subject: PCI: Remove struct pci_dev->driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no remaining uses of the struct pci_dev->driver pointer, so remove it. Link: https://lore.kernel.org/r/20211004125935.2300113-12-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index a2d62165a7f7..03bfdb25a55c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -342,7 +342,6 @@ struct pci_dev { u16 pcie_flags_reg; /* Cached PCIe Capabilities Register */ unsigned long *dma_alias_mask;/* Mask of enabled devfn aliases */ - struct pci_driver *driver; /* Driver bound to this device */ u64 dma_mask; /* Mask of the bits of bus address this device implements. Normally this is 0xffffffff. You only need to change -- cgit v1.2.3 From 0d20e9fb1262b1f9ac895b287db892bc75b05b84 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:31 +0200 Subject: rtc: add BSM parameter BSM or Backup Switch Mode is a common feature on RTCs, allowing to select how the RTC will decide when to switch from its primary power supply to the backup power supply. It is necessary to be able to set it from userspace as there are uses cases where it has to be done dynamically. Supported values are: RTC_BSM_DISABLED: disabled RTC_BSM_DIRECT: switching will happen as soon as Vbackup > Vdd RTC_BSM_LEVEL: switching will happen around a threshold, usually with an hysteresis RTC_BSM_STANDBY: switching will not happen until Vdd > Vbackup, this is useful to ensure the RTC doesn't draw any power until the device is first powered on. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-6-alexandre.belloni@bootlin.com --- include/linux/rtc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 354e0843ab17..47fd1c2d3a57 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -66,6 +66,8 @@ struct rtc_class_ops { int (*alarm_irq_enable)(struct device *, unsigned int enabled); int (*read_offset)(struct device *, long *offset); int (*set_offset)(struct device *, long offset); + int (*param_get)(struct device *, struct rtc_param *param); + int (*param_set)(struct device *, struct rtc_param *param); }; struct rtc_device; -- cgit v1.2.3 From 88dee3b0efe4b769fb22ce2e963aabae403e6801 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Mon, 18 Oct 2021 20:41:09 +0800 Subject: PCI: Remove unused pci_pool wrappers The pci_pool users have been converted to dma_pool. Remove the unused pci_pool wrappers. Link: https://lore.kernel.org/r/20211018124110.214-1-caihuoqing@baidu.com Signed-off-by: Cai Huoqing Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..2ae9dd7f975f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1498,19 +1498,8 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, #define PCI_IRQ_ALL_TYPES \ (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) -/* kmem_cache style wrapper around pci_alloc_consistent() */ - #include -#define pci_pool dma_pool -#define pci_pool_create(name, pdev, size, align, allocation) \ - dma_pool_create(name, &pdev->dev, size, align, allocation) -#define pci_pool_destroy(pool) dma_pool_destroy(pool) -#define pci_pool_alloc(pool, flags, handle) dma_pool_alloc(pool, flags, handle) -#define pci_pool_zalloc(pool, flags, handle) \ - dma_pool_zalloc(pool, flags, handle) -#define pci_pool_free(pool, vaddr, addr) dma_pool_free(pool, vaddr, addr) - struct msix_entry { u32 vector; /* Kernel uses to write allocated vector */ u16 entry; /* Driver uses to specify entry, OS writes */ -- cgit v1.2.3 From f783484381ad088490a497abb4faab47511774c5 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:35 +0200 Subject: mfd: ti_am335x_tscadc: Use driver data So far every sub-cell parameter in this driver was hardcoded: cell name, cell compatible, specific clock name and desired clock frequency. As we are about to introduce support for ADC1/magnetic reader, we need a bit of flexibility. Let's add a driver data structure which will contain these information. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-18-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index ffc091b77633..bb3b56ade3fb 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -162,11 +162,20 @@ #define TSCADC_CELLS 2 +struct ti_tscadc_data { + char *adc_feature_name; + char *adc_feature_compatible; + char *secondary_feature_name; + char *secondary_feature_compatible; + unsigned int target_clk_rate; +}; + struct ti_tscadc_dev { struct device *dev; struct regmap *regmap; void __iomem *tscadc_base; phys_addr_t tscadc_phys_base; + const struct ti_tscadc_data *data; int irq; int used_cells; /* 1-2 */ int tsc_wires; -- cgit v1.2.3 From 7c605802f33176d872ffb6a3830ba4d88d9f21f6 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:37 +0200 Subject: mfd: ti_am335x_tscadc: Drop useless variables from the driver structure Keeping the count of tsc_cells and adc_cells is completely redundant, we can derive this information from other variables. Plus, these variables are not used anywhere else now. Let's get rid of them. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-20-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index bb3b56ade3fb..23442059d271 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -177,10 +177,7 @@ struct ti_tscadc_dev { phys_addr_t tscadc_phys_base; const struct ti_tscadc_data *data; int irq; - int used_cells; /* 1-2 */ int tsc_wires; - int tsc_cell; /* -1 if not used */ - int adc_cell; /* -1 if not used */ struct mfd_cell cells[TSCADC_CELLS]; u32 reg_se_cache; bool adc_waiting; -- cgit v1.2.3 From b813f32030e2b70adf68f73e99853f91526aa3a1 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:40 +0200 Subject: mfd: ti_am335x_tscadc: Gather the ctrl register logic in one place Instead of deriving in the probe and in the resume path the value of the ctrl register, let's do it only once in the probe, save the value of this register (all but the subsystem enable bit) in the driver's structure and use it from the resume callback. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-23-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 23442059d271..c9c6f0b29181 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -177,8 +177,8 @@ struct ti_tscadc_dev { phys_addr_t tscadc_phys_base; const struct ti_tscadc_data *data; int irq; - int tsc_wires; struct mfd_cell cells[TSCADC_CELLS]; + u32 ctrl; u32 reg_se_cache; bool adc_waiting; bool adc_in_use; -- cgit v1.2.3 From 36782dab984a8b4ef8f4ec8c2270c56468cbbbeb Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:41 +0200 Subject: mfd: ti_am335x_tscadc: Replace the header license text with SPDX tag Drop the text license and replace it with an equivalent SPDX license tag identifier. Signed-off-by: Miquel Raynal Acked-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-24-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index c9c6f0b29181..2b8a5f58a3b6 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -1,21 +1,13 @@ -#ifndef __LINUX_TI_AM335X_TSCADC_MFD_H -#define __LINUX_TI_AM335X_TSCADC_MFD_H - +/* SPDX-License-Identifier: GPL-2.0-only */ /* * TI Touch Screen / ADC MFD driver * * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/ - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ +#ifndef __LINUX_TI_AM335X_TSCADC_MFD_H +#define __LINUX_TI_AM335X_TSCADC_MFD_H + #include #define REG_RAWIRQSTATUS 0x024 -- cgit v1.2.3 From 3831abe135566813341cc36b1493d75f6ac460c3 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:42 +0200 Subject: mfd: ti_am335x_tscadc: Fix header spacing Harmonize the spacing within macro definitions. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-25-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 2b8a5f58a3b6..893c474c1f8c 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -41,7 +41,7 @@ /* Step Enable */ #define STEPENB_MASK (0x1FFFF << 0) #define STEPENB(val) ((val) << 0) -#define ENB(val) (1 << (val)) +#define ENB(val) (1 << (val)) #define STPENB_STEPENB STEPENB(0x1FFFF) #define STPENB_STEPENB_TC STEPENB(0x1FFF) @@ -122,15 +122,15 @@ #define CNTRLREG_TSCENB BIT(7) /* FIFO READ Register */ -#define FIFOREAD_DATA_MASK (0xfff << 0) -#define FIFOREAD_CHNLID_MASK (0xf << 16) +#define FIFOREAD_DATA_MASK (0xfff << 0) +#define FIFOREAD_CHNLID_MASK (0xf << 16) /* DMA ENABLE/CLEAR Register */ #define DMA_FIFO0 BIT(0) #define DMA_FIFO1 BIT(1) /* Sequencer Status */ -#define SEQ_STATUS BIT(5) +#define SEQ_STATUS BIT(5) #define CHARGE_STEP 0x11 #define ADC_CLK 3000000 @@ -150,7 +150,7 @@ * * max processing time: 266431 * 308ns = 83ms(approx) */ -#define IDLE_TIMEOUT 83 /* milliseconds */ +#define IDLE_TIMEOUT 83 /* milliseconds */ #define TSCADC_CELLS 2 -- cgit v1.2.3 From 48959fcdca8b335afa4485e71114008c81291bf9 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:43 +0200 Subject: mfd: ti_am335x_tscadc: Use the new HZ_PER_MHZ macro Before adding another frequency with even more zeroes, use the HZ_PER_MHZ macro to clarify the number. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-26-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 893c474c1f8c..a85643677bef 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -9,6 +9,7 @@ #define __LINUX_TI_AM335X_TSCADC_MFD_H #include +#include #define REG_RAWIRQSTATUS 0x024 #define REG_IRQSTATUS 0x028 @@ -133,7 +134,7 @@ #define SEQ_STATUS BIT(5) #define CHARGE_STEP 0x11 -#define ADC_CLK 3000000 +#define ADC_CLK (3 * HZ_PER_MHZ) #define TOTAL_STEPS 16 #define TOTAL_CHANNELS 8 #define FIFO1_THRESHOLD 19 -- cgit v1.2.3 From 65de5532a317b22f7fb93001cd0ed494145d3f4e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:44 +0200 Subject: mfd: ti_am335x_tscadc: Drop unused definitions from the header The STEP ENABLE definitions are highly unclear and not used so drop them. Suggested-by: Jonathan Cameron Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-27-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index a85643677bef..1cd8cd34f2b7 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -39,13 +39,6 @@ /* IRQ wakeup enable */ #define IRQWKUP_ENB BIT(0) -/* Step Enable */ -#define STEPENB_MASK (0x1FFFF << 0) -#define STEPENB(val) ((val) << 0) -#define ENB(val) (1 << (val)) -#define STPENB_STEPENB STEPENB(0x1FFFF) -#define STPENB_STEPENB_TC STEPENB(0x1FFF) - /* IRQ enable */ #define IRQENB_HW_PEN BIT(0) #define IRQENB_EOS BIT(1) -- cgit v1.2.3 From b7cb7bf11817129c623fa921a1d6cd86b3cb727b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:45 +0200 Subject: mfd: ti_am335x_tscadc: Use BIT(), GENMASK() and FIELD_PREP() when relevant Clean the ti_am335x_tscadc.h header by: * converting masks to GENMASK() * converting regular shifts to BIT() * using FIELD_PREP() when relevant Sometimes reorder the lines to be able to use the relevant bitmask. Mind the s/%d/%ld/ change in a log due to the type change following the use of FIELD_PREP() in the header. Suggested-by: Jonathan Cameron Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-28-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 61 ++++++++++++++++++------------------ 1 file changed, 31 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 1cd8cd34f2b7..ae694fa2d711 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -8,6 +8,7 @@ #ifndef __LINUX_TI_AM335X_TSCADC_MFD_H #define __LINUX_TI_AM335X_TSCADC_MFD_H +#include #include #include @@ -51,12 +52,12 @@ #define IRQENB_PENUP BIT(9) /* Step Configuration */ -#define STEPCONFIG_MODE_MASK (3 << 0) -#define STEPCONFIG_MODE(val) ((val) << 0) +#define STEPCONFIG_MODE_MASK GENMASK(1, 0) +#define STEPCONFIG_MODE(val) FIELD_PREP(STEPCONFIG_MODE_MASK, (val)) #define STEPCONFIG_MODE_SWCNT STEPCONFIG_MODE(1) #define STEPCONFIG_MODE_HWSYNC STEPCONFIG_MODE(2) -#define STEPCONFIG_AVG_MASK (7 << 2) -#define STEPCONFIG_AVG(val) ((val) << 2) +#define STEPCONFIG_AVG_MASK GENMASK(4, 2) +#define STEPCONFIG_AVG(val) FIELD_PREP(STEPCONFIG_AVG_MASK, (val)) #define STEPCONFIG_AVG_16 STEPCONFIG_AVG(4) #define STEPCONFIG_XPP BIT(5) #define STEPCONFIG_XNN BIT(6) @@ -64,43 +65,43 @@ #define STEPCONFIG_YNN BIT(8) #define STEPCONFIG_XNP BIT(9) #define STEPCONFIG_YPN BIT(10) -#define STEPCONFIG_RFP(val) ((val) << 12) -#define STEPCONFIG_RFP_VREFP (0x3 << 12) -#define STEPCONFIG_INM_MASK (0xF << 15) -#define STEPCONFIG_INM(val) ((val) << 15) +#define STEPCONFIG_RFP_VREFP GENMASK(13, 12) +#define STEPCONFIG_RFP(val) FIELD_PREP(STEPCONFIG_RFP_VREFP, (val)) +#define STEPCONFIG_INM_MASK GENMASK(18, 15) +#define STEPCONFIG_INM(val) FIELD_PREP(STEPCONFIG_INM_MASK, (val)) #define STEPCONFIG_INM_ADCREFM STEPCONFIG_INM(8) -#define STEPCONFIG_INP_MASK (0xF << 19) -#define STEPCONFIG_INP(val) ((val) << 19) +#define STEPCONFIG_INP_MASK GENMASK(22, 19) +#define STEPCONFIG_INP(val) FIELD_PREP(STEPCONFIG_INP_MASK, (val)) #define STEPCONFIG_INP_AN4 STEPCONFIG_INP(4) #define STEPCONFIG_INP_ADCREFM STEPCONFIG_INP(8) #define STEPCONFIG_FIFO1 BIT(26) -#define STEPCONFIG_RFM(val) ((val) << 23) -#define STEPCONFIG_RFM_VREFN (0x3 << 23) +#define STEPCONFIG_RFM_VREFN GENMASK(24, 23) +#define STEPCONFIG_RFM(val) FIELD_PREP(STEPCONFIG_RFM_VREFN, (val)) /* Delay register */ -#define STEPDELAY_OPEN_MASK (0x3FFFF << 0) -#define STEPDELAY_OPEN(val) ((val) << 0) +#define STEPDELAY_OPEN_MASK GENMASK(17, 0) +#define STEPDELAY_OPEN(val) FIELD_PREP(STEPDELAY_OPEN_MASK, (val)) #define STEPCONFIG_OPENDLY STEPDELAY_OPEN(0x098) -#define STEPDELAY_SAMPLE_MASK (0xFF << 24) -#define STEPDELAY_SAMPLE(val) ((val) << 24) +#define STEPDELAY_SAMPLE_MASK GENMASK(31, 24) +#define STEPDELAY_SAMPLE(val) FIELD_PREP(STEPDELAY_SAMPLE_MASK, (val)) #define STEPCONFIG_SAMPLEDLY STEPDELAY_SAMPLE(0) /* Charge Config */ -#define STEPCHARGE_RFP_MASK (7 << 12) -#define STEPCHARGE_RFP(val) ((val) << 12) +#define STEPCHARGE_RFP_MASK GENMASK(14, 12) +#define STEPCHARGE_RFP(val) FIELD_PREP(STEPCHARGE_RFP_MASK, (val)) #define STEPCHARGE_RFP_XPUL STEPCHARGE_RFP(1) -#define STEPCHARGE_INM_MASK (0xF << 15) -#define STEPCHARGE_INM(val) ((val) << 15) +#define STEPCHARGE_INM_MASK GENMASK(18, 15) +#define STEPCHARGE_INM(val) FIELD_PREP(STEPCHARGE_INM_MASK, (val)) #define STEPCHARGE_INM_AN1 STEPCHARGE_INM(1) -#define STEPCHARGE_INP_MASK (0xF << 19) -#define STEPCHARGE_INP(val) ((val) << 19) -#define STEPCHARGE_RFM_MASK (3 << 23) -#define STEPCHARGE_RFM(val) ((val) << 23) +#define STEPCHARGE_INP_MASK GENMASK(22, 19) +#define STEPCHARGE_INP(val) FIELD_PREP(STEPCHARGE_INP_MASK, (val)) +#define STEPCHARGE_RFM_MASK GENMASK(24, 23) +#define STEPCHARGE_RFM(val) FIELD_PREP(STEPCHARGE_RFM_MASK, (val)) #define STEPCHARGE_RFM_XNUR STEPCHARGE_RFM(1) /* Charge delay */ -#define CHARGEDLY_OPEN_MASK (0x3FFFF << 0) -#define CHARGEDLY_OPEN(val) ((val) << 0) +#define CHARGEDLY_OPEN_MASK GENMASK(17, 0) +#define CHARGEDLY_OPEN(val) FIELD_PREP(CHARGEDLY_OPEN_MASK, (val)) #define CHARGEDLY_OPENDLY CHARGEDLY_OPEN(0x400) /* Control register */ @@ -108,16 +109,16 @@ #define CNTRLREG_STEPID BIT(1) #define CNTRLREG_STEPCONFIGWRT BIT(2) #define CNTRLREG_POWERDOWN BIT(4) -#define CNTRLREG_AFE_CTRL_MASK (3 << 5) -#define CNTRLREG_AFE_CTRL(val) ((val) << 5) +#define CNTRLREG_AFE_CTRL_MASK GENMASK(6, 5) +#define CNTRLREG_AFE_CTRL(val) FIELD_PREP(CNTRLREG_AFE_CTRL_MASK, (val)) #define CNTRLREG_4WIRE CNTRLREG_AFE_CTRL(1) #define CNTRLREG_5WIRE CNTRLREG_AFE_CTRL(2) #define CNTRLREG_8WIRE CNTRLREG_AFE_CTRL(3) #define CNTRLREG_TSCENB BIT(7) /* FIFO READ Register */ -#define FIFOREAD_DATA_MASK (0xfff << 0) -#define FIFOREAD_CHNLID_MASK (0xf << 16) +#define FIFOREAD_DATA_MASK GENMASK(11, 0) +#define FIFOREAD_CHNLID_MASK GENMASK(19, 16) /* DMA ENABLE/CLEAR Register */ #define DMA_FIFO0 BIT(0) -- cgit v1.2.3 From 133a48abf6ecc535d7eddc6da1c3e4c972445882 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Oct 2021 15:37:42 -0400 Subject: NFS: Fix up commit deadlocks If O_DIRECT bumps the commit_info rpcs_out field, then that could lead to fsync() hangs. The fix is to ensure that O_DIRECT calls nfs_commit_end(). Fixes: 723c921e7dfc ("sched/wait, fs/nfs: Convert wait_on_atomic_t() usage to the new wait_var_event() API") Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index ca547cc5458c..e58b78da7a98 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -568,6 +568,7 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); extern void nfs_commit_free(struct nfs_commit_data *data); +bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline int nfs_have_writebacks(struct inode *inode) -- cgit v1.2.3 From 0ebeebcf59601bcfa0284f4bb7abdec051eb856d Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Sun, 10 Oct 2021 18:23:13 -0400 Subject: NFS: Fix WARN_ON due to unionization of nfs_inode.nrequests Fixes the following WARN_ON WARNING: CPU: 2 PID: 18678 at fs/nfs/inode.c:123 nfs_clear_inode+0x3b/0x50 [nfs] ... Call Trace: nfs4_evict_inode+0x57/0x70 [nfsv4] evict+0xd1/0x180 dispose_list+0x48/0x60 evict_inodes+0x156/0x190 generic_shutdown_super+0x37/0x110 nfs_kill_super+0x1d/0x40 [nfs] deactivate_locked_super+0x36/0xa0 Signed-off-by: Dave Wysochanski Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index e58b78da7a98..457b866a2d9e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -573,7 +573,9 @@ bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline int nfs_have_writebacks(struct inode *inode) { - return atomic_long_read(&NFS_I(inode)->nrequests) != 0; + if (S_ISREG(inode->i_mode)) + return atomic_long_read(&NFS_I(inode)->nrequests) != 0; + return 0; } /* -- cgit v1.2.3 From e591b298d7ecb851e200f65946e3d53fe78a3c4f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 28 Sep 2021 17:41:41 -0400 Subject: NFS: Save some space in the inode Save some space in the nfs_inode by setting up an anonymous union with the fields that are peculiar to a specific type of filesystem object. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 42 ++++++++++++++++++++++++------------------ 1 file changed, 24 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 457b866a2d9e..739ca1ef934f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -155,33 +155,39 @@ struct nfs_inode { unsigned long attrtimeo_timestamp; unsigned long attr_gencount; - /* "Generation counter" for the attribute cache. This is - * bumped whenever we update the metadata on the - * server. - */ - unsigned long cache_change_attribute; struct rb_root access_cache; struct list_head access_cache_entry_lru; struct list_head access_cache_inode_lru; - /* - * This is the cookie verifier used for NFSv3 readdir - * operations - */ - __be32 cookieverf[NFS_DIR_VERIFIER_SIZE]; - - atomic_long_t nrequests; - struct nfs_mds_commit_info commit_info; + union { + /* Directory */ + struct { + /* "Generation counter" for the attribute cache. + * This is bumped whenever we update the metadata + * on the server. + */ + unsigned long cache_change_attribute; + /* + * This is the cookie verifier used for NFSv3 readdir + * operations + */ + __be32 cookieverf[NFS_DIR_VERIFIER_SIZE]; + /* Readers: in-flight sillydelete RPC calls */ + /* Writers: rmdir */ + struct rw_semaphore rmdir_sem; + }; + /* Regular file */ + struct { + atomic_long_t nrequests; + struct nfs_mds_commit_info commit_info; + struct mutex commit_mutex; + }; + }; /* Open contexts for shared mmap writes */ struct list_head open_files; - /* Readers: in-flight sillydelete RPC calls */ - /* Writers: rmdir */ - struct rw_semaphore rmdir_sem; - struct mutex commit_mutex; - #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ -- cgit v1.2.3 From e967b60eb51116d2347093655e555aa036dd40d8 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:46 +0200 Subject: mfd: ti_am335x_tscadc: Clarify the maximum values for DT entries Clearly define the maximum open delay and sample delay. Use these definitions in place of a mask (which works because this is the first field in the register) and an open-coded value. While at it reword a little bit the error messages to make them look clearer and similar. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-29-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index ae694fa2d711..31cffb6e8b17 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -84,7 +84,9 @@ #define STEPCONFIG_OPENDLY STEPDELAY_OPEN(0x098) #define STEPDELAY_SAMPLE_MASK GENMASK(31, 24) #define STEPDELAY_SAMPLE(val) FIELD_PREP(STEPDELAY_SAMPLE_MASK, (val)) +#define STEPCONFIG_MAX_OPENDLY GENMASK(17, 0) #define STEPCONFIG_SAMPLEDLY STEPDELAY_SAMPLE(0) +#define STEPCONFIG_MAX_SAMPLE GENMASK(7, 0) /* Charge Config */ #define STEPCHARGE_RFP_MASK GENMASK(14, 12) -- cgit v1.2.3 From 0fd12262613116a38fd76aefa396e9bc116fbfe2 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:47 +0200 Subject: mfd: ti_am335x_tscadc: Drop useless definitions from the header Drop useless definitions from the header like the "masks" definitions which are only used by the following definition. It could be possible to got even further by removing these definitions entirely and use FIELD_PREP() macros from the code directly, but while I have no troubles making these changes in the header, changing the values in the code directly could darkening a bit the logic and hardening future git-blames for very little added value IMHO (but this is of course a personal taste). Certain macros are using GENMASK() to define the value of a particular field, while this is purely "by chance" that the value and the mask have the same value. In this case, drop the "mask" definition, use FIELD_PREP() and GENMASK() in the macro defining the field, and use the new macro to define the particular value by feeding directly the actual number advertised in the datasheet into that macro, as in: -#define STEPCONFIG_RFM_VREFN GENMASK(24, 23) -#define STEPCONFIG_RFM(val) FIELD_PREP(STEPCONFIG_RFM_VREFN, (val)) +#define STEPCONFIG_RFM(val) FIELD_PREP(GENMASK(24, 23), (val)) +#define STEPCONFIG_RFM_VREFN STEPCONFIG_RFM(3) Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-30-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 44 +++++++++++++----------------------- 1 file changed, 16 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 31cffb6e8b17..51d987080cd3 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -52,12 +52,10 @@ #define IRQENB_PENUP BIT(9) /* Step Configuration */ -#define STEPCONFIG_MODE_MASK GENMASK(1, 0) -#define STEPCONFIG_MODE(val) FIELD_PREP(STEPCONFIG_MODE_MASK, (val)) +#define STEPCONFIG_MODE(val) FIELD_PREP(GENMASK(1, 0), (val)) #define STEPCONFIG_MODE_SWCNT STEPCONFIG_MODE(1) #define STEPCONFIG_MODE_HWSYNC STEPCONFIG_MODE(2) -#define STEPCONFIG_AVG_MASK GENMASK(4, 2) -#define STEPCONFIG_AVG(val) FIELD_PREP(STEPCONFIG_AVG_MASK, (val)) +#define STEPCONFIG_AVG(val) FIELD_PREP(GENMASK(4, 2), (val)) #define STEPCONFIG_AVG_16 STEPCONFIG_AVG(4) #define STEPCONFIG_XPP BIT(5) #define STEPCONFIG_XNN BIT(6) @@ -65,45 +63,36 @@ #define STEPCONFIG_YNN BIT(8) #define STEPCONFIG_XNP BIT(9) #define STEPCONFIG_YPN BIT(10) -#define STEPCONFIG_RFP_VREFP GENMASK(13, 12) -#define STEPCONFIG_RFP(val) FIELD_PREP(STEPCONFIG_RFP_VREFP, (val)) -#define STEPCONFIG_INM_MASK GENMASK(18, 15) -#define STEPCONFIG_INM(val) FIELD_PREP(STEPCONFIG_INM_MASK, (val)) +#define STEPCONFIG_RFP(val) FIELD_PREP(GENMASK(13, 12), (val)) +#define STEPCONFIG_RFP_VREFP STEPCONFIG_RFP(3) +#define STEPCONFIG_INM(val) FIELD_PREP(GENMASK(18, 15), (val)) #define STEPCONFIG_INM_ADCREFM STEPCONFIG_INM(8) -#define STEPCONFIG_INP_MASK GENMASK(22, 19) -#define STEPCONFIG_INP(val) FIELD_PREP(STEPCONFIG_INP_MASK, (val)) +#define STEPCONFIG_INP(val) FIELD_PREP(GENMASK(22, 19), (val)) #define STEPCONFIG_INP_AN4 STEPCONFIG_INP(4) #define STEPCONFIG_INP_ADCREFM STEPCONFIG_INP(8) #define STEPCONFIG_FIFO1 BIT(26) -#define STEPCONFIG_RFM_VREFN GENMASK(24, 23) -#define STEPCONFIG_RFM(val) FIELD_PREP(STEPCONFIG_RFM_VREFN, (val)) +#define STEPCONFIG_RFM(val) FIELD_PREP(GENMASK(24, 23), (val)) +#define STEPCONFIG_RFM_VREFN STEPCONFIG_RFM(3) /* Delay register */ -#define STEPDELAY_OPEN_MASK GENMASK(17, 0) -#define STEPDELAY_OPEN(val) FIELD_PREP(STEPDELAY_OPEN_MASK, (val)) +#define STEPDELAY_OPEN(val) FIELD_PREP(GENMASK(17, 0), (val)) #define STEPCONFIG_OPENDLY STEPDELAY_OPEN(0x098) -#define STEPDELAY_SAMPLE_MASK GENMASK(31, 24) -#define STEPDELAY_SAMPLE(val) FIELD_PREP(STEPDELAY_SAMPLE_MASK, (val)) #define STEPCONFIG_MAX_OPENDLY GENMASK(17, 0) +#define STEPDELAY_SAMPLE(val) FIELD_PREP(GENMASK(31, 24), (val)) #define STEPCONFIG_SAMPLEDLY STEPDELAY_SAMPLE(0) #define STEPCONFIG_MAX_SAMPLE GENMASK(7, 0) /* Charge Config */ -#define STEPCHARGE_RFP_MASK GENMASK(14, 12) -#define STEPCHARGE_RFP(val) FIELD_PREP(STEPCHARGE_RFP_MASK, (val)) +#define STEPCHARGE_RFP(val) FIELD_PREP(GENMASK(14, 12), (val)) #define STEPCHARGE_RFP_XPUL STEPCHARGE_RFP(1) -#define STEPCHARGE_INM_MASK GENMASK(18, 15) -#define STEPCHARGE_INM(val) FIELD_PREP(STEPCHARGE_INM_MASK, (val)) +#define STEPCHARGE_INM(val) FIELD_PREP(GENMASK(18, 15), (val)) #define STEPCHARGE_INM_AN1 STEPCHARGE_INM(1) -#define STEPCHARGE_INP_MASK GENMASK(22, 19) -#define STEPCHARGE_INP(val) FIELD_PREP(STEPCHARGE_INP_MASK, (val)) -#define STEPCHARGE_RFM_MASK GENMASK(24, 23) -#define STEPCHARGE_RFM(val) FIELD_PREP(STEPCHARGE_RFM_MASK, (val)) +#define STEPCHARGE_INP(val) FIELD_PREP(GENMASK(22, 19), (val)) +#define STEPCHARGE_RFM(val) FIELD_PREP(GENMASK(24, 23), (val)) #define STEPCHARGE_RFM_XNUR STEPCHARGE_RFM(1) /* Charge delay */ -#define CHARGEDLY_OPEN_MASK GENMASK(17, 0) -#define CHARGEDLY_OPEN(val) FIELD_PREP(CHARGEDLY_OPEN_MASK, (val)) +#define CHARGEDLY_OPEN(val) FIELD_PREP(GENMASK(17, 0), (val)) #define CHARGEDLY_OPENDLY CHARGEDLY_OPEN(0x400) /* Control register */ @@ -111,8 +100,7 @@ #define CNTRLREG_STEPID BIT(1) #define CNTRLREG_STEPCONFIGWRT BIT(2) #define CNTRLREG_POWERDOWN BIT(4) -#define CNTRLREG_AFE_CTRL_MASK GENMASK(6, 5) -#define CNTRLREG_AFE_CTRL(val) FIELD_PREP(CNTRLREG_AFE_CTRL_MASK, (val)) +#define CNTRLREG_AFE_CTRL(val) FIELD_PREP(GENMASK(6, 5), (val)) #define CNTRLREG_4WIRE CNTRLREG_AFE_CTRL(1) #define CNTRLREG_5WIRE CNTRLREG_AFE_CTRL(2) #define CNTRLREG_8WIRE CNTRLREG_AFE_CTRL(3) -- cgit v1.2.3 From c3e36b5d069241f3cbc0e647cf297c5a329cd7a6 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:48 +0200 Subject: mfd: ti_am335x_tscadc: Rename the subsystem enable macro This bit is common to all devices (ADC, Touchscreen, Magnetic reader) so make it clear that it can be used from any location by operating a mechanical rename: s/CNTRLREG_TSCSSENB/CNTRLREG_SSENB/ Signed-off-by: Miquel Raynal Acked-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-31-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 51d987080cd3..860289ae8516 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -96,7 +96,7 @@ #define CHARGEDLY_OPENDLY CHARGEDLY_OPEN(0x400) /* Control register */ -#define CNTRLREG_TSCSSENB BIT(0) +#define CNTRLREG_SSENB BIT(0) #define CNTRLREG_STEPID BIT(1) #define CNTRLREG_STEPCONFIGWRT BIT(2) #define CNTRLREG_POWERDOWN BIT(4) -- cgit v1.2.3 From 2f89c2619ce93bf2b0e6e721614fc33e8cf48f03 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:49 +0200 Subject: mfd: ti_am335x_tscadc: Add TSC prefix in certain macros While the register list (and names) between ADC0 and ADC1 are pretty close, the bits inside changed a little bit. To avoid any future confusion, let's add the TSC prefix when some bits are in a register that is common to both revisions of the ADC, but are specific to the am33xx hardware. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-32-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 860289ae8516..cc6de9258455 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -98,13 +98,13 @@ /* Control register */ #define CNTRLREG_SSENB BIT(0) #define CNTRLREG_STEPID BIT(1) -#define CNTRLREG_STEPCONFIGWRT BIT(2) +#define CNTRLREG_TSC_STEPCONFIGWRT BIT(2) #define CNTRLREG_POWERDOWN BIT(4) -#define CNTRLREG_AFE_CTRL(val) FIELD_PREP(GENMASK(6, 5), (val)) -#define CNTRLREG_4WIRE CNTRLREG_AFE_CTRL(1) -#define CNTRLREG_5WIRE CNTRLREG_AFE_CTRL(2) -#define CNTRLREG_8WIRE CNTRLREG_AFE_CTRL(3) -#define CNTRLREG_TSCENB BIT(7) +#define CNTRLREG_TSC_AFE_CTRL(val) FIELD_PREP(GENMASK(6, 5), (val)) +#define CNTRLREG_TSC_4WIRE CNTRLREG_TSC_AFE_CTRL(1) +#define CNTRLREG_TSC_5WIRE CNTRLREG_TSC_AFE_CTRL(2) +#define CNTRLREG_TSC_8WIRE CNTRLREG_TSC_AFE_CTRL(3) +#define CNTRLREG_TSC_ENB BIT(7) /* FIFO READ Register */ #define FIFOREAD_DATA_MASK GENMASK(11, 0) @@ -118,7 +118,7 @@ #define SEQ_STATUS BIT(5) #define CHARGE_STEP 0x11 -#define ADC_CLK (3 * HZ_PER_MHZ) +#define TSC_ADC_CLK (3 * HZ_PER_MHZ) #define TOTAL_STEPS 16 #define TOTAL_CHANNELS 8 #define FIFO1_THRESHOLD 19 -- cgit v1.2.3 From bf0f394c7b1e4d623ca2afdf59b3b4b95cc6f592 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:53 +0200 Subject: mfd: ti_am335x_tscadc: Introduce a helper to deal with the type of hardware One way of knowing which hardware we are dealing with is to check the compatible string. When this must be done at several places, it's best and certainly more clear to use a helper for that. Introduce ti_adc_with_touchscreen() to indicate if there is a touchscreen controller available (meaning it's an am33xx-like ADC). This helper does not indicate if it is actually used (that is the purpose of the use_tsc boolean). Introducing this helper helps making a difference in the code between what is generic to both types of ADCs and what is specific to the am33xx hardware before introducing support for the am437x hardware. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-36-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index cc6de9258455..ee160b2036c1 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -177,6 +177,12 @@ static inline struct ti_tscadc_dev *ti_tscadc_dev_get(struct platform_device *p) return *tscadc_dev; } +static inline bool ti_adc_with_touchscreen(struct ti_tscadc_dev *tscadc) +{ + return of_device_is_compatible(tscadc->dev->of_node, + "ti,am3359-tscadc"); +} + void am335x_tsc_se_set_cache(struct ti_tscadc_dev *tsadc, u32 val); void am335x_tsc_se_set_once(struct ti_tscadc_dev *tsadc, u32 val); void am335x_tsc_se_clr(struct ti_tscadc_dev *tsadc, u32 val); -- cgit v1.2.3 From 0a1233031c16d8575be6b864e6fd353b6fd758c4 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:54 +0200 Subject: mfd: ti_am335x_tscadc: Add ADC1/magnetic reader support Introduce a new compatible that has another set of driver data, targeting am437x SoCs with a magnetic reader instead of the touchscreen and a more featureful set of registers. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-37-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index ee160b2036c1..5225e3fc194d 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -106,6 +106,11 @@ #define CNTRLREG_TSC_8WIRE CNTRLREG_TSC_AFE_CTRL(3) #define CNTRLREG_TSC_ENB BIT(7) +/*Control registers bitfields for MAGADC IP */ +#define CNTRLREG_MAGADCENB BIT(0) +#define CNTRLREG_MAG_PREAMP_PWRDOWN BIT(5) +#define CNTRLREG_MAG_PREAMP_BYPASS BIT(6) + /* FIFO READ Register */ #define FIFOREAD_DATA_MASK GENMASK(11, 0) #define FIFOREAD_CHNLID_MASK GENMASK(19, 16) @@ -119,6 +124,7 @@ #define CHARGE_STEP 0x11 #define TSC_ADC_CLK (3 * HZ_PER_MHZ) +#define MAG_ADC_CLK (13 * HZ_PER_MHZ) #define TOTAL_STEPS 16 #define TOTAL_CHANNELS 8 #define FIFO1_THRESHOLD 19 -- cgit v1.2.3 From 789e5ebcc61b72a71717b02b62e6c6f10fdbb722 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:15:01 +0200 Subject: iio: adc: ti_am335x_adc: Add a unit to the timeout delay The lack of unit in the macro name kind of tricked me when I was troubleshooting an issue. Physical constants should always get a unit. Signed-off-by: Miquel Raynal Acked-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-44-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 5225e3fc194d..ba13e043d910 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -141,7 +141,7 @@ * * max processing time: 266431 * 308ns = 83ms(approx) */ -#define IDLE_TIMEOUT 83 /* milliseconds */ +#define IDLE_TIMEOUT_MS 83 /* milliseconds */ #define TSCADC_CELLS 2 -- cgit v1.2.3 From d08fd747d0ed682b6c6c280ba454cafcad33563d Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 14 Oct 2021 16:35:11 +0200 Subject: Compiler Attributes: remove GCC 5.1 mention GCC 5.1 is now the minimum version. Acked-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index e6ec63403965..87d1e773400c 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -104,7 +104,6 @@ #define __deprecated /* - * Optional: only supported since gcc >= 5.1 * Optional: not supported by clang * Optional: not supported by icc * -- cgit v1.2.3 From 7c00621dcaeea206d7489b3e8b50b1864841ae69 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 14 Oct 2021 15:23:31 +0200 Subject: compiler_types: mark __compiletime_assert failure as __noreturn `__compiletime_assert` declares a fake `extern` function which appears (to the compiler) to be called when the test fails. Therefore, compilers may emit possibly-uninitialized warnings in some cases, even if it will be an error anyway (for compilers supporting the `error` attribute, e.g. GCC and Clang >= 14) or a link failure (for those that do not, e.g. Clang < 14). Annotating the fake function as `__noreturn` gives them the information they need to avoid the warning, e.g. see https://godbolt.org/z/x1v69jjYY. Link: https://lore.kernel.org/llvm/202110100514.3h9CI4s0-lkp@intel.com/ Reported-by: kernel test robot Reviewed-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index b6ff83a714ca..ca1a66b8cd2f 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -298,7 +298,13 @@ struct ftrace_likely_data { #ifdef __OPTIMIZE__ # define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ - extern void prefix ## suffix(void) __compiletime_error(msg); \ + /* \ + * __noreturn is needed to give the compiler enough \ + * information to avoid certain possibly-uninitialized \ + * warnings (regardless of the build failing). \ + */ \ + __noreturn extern void prefix ## suffix(void) \ + __compiletime_error(msg); \ if (!(condition)) \ prefix ## suffix(); \ } while (0) -- cgit v1.2.3 From b3b180e735409ca0c76642014304b59482e0e653 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 20 Sep 2021 14:20:07 +0200 Subject: dmaengine: remove debugfs #ifdef The ptdma driver has added debugfs support, but this fails to build when debugfs is disabled: drivers/dma/ptdma/ptdma-debugfs.c: In function 'ptdma_debugfs_setup': drivers/dma/ptdma/ptdma-debugfs.c:93:54: error: 'struct dma_device' has no member named 'dbg_dev_root' 93 | debugfs_create_file("info", 0400, pt->dma_dev.dbg_dev_root, pt, | ^ drivers/dma/ptdma/ptdma-debugfs.c:96:55: error: 'struct dma_device' has no member named 'dbg_dev_root' 96 | debugfs_create_file("stats", 0400, pt->dma_dev.dbg_dev_root, pt, | ^ drivers/dma/ptdma/ptdma-debugfs.c:102:52: error: 'struct dma_device' has no member named 'dbg_dev_root' 102 | debugfs_create_dir("q", pt->dma_dev.dbg_dev_root); | ^ Remove the #ifdef in the header, as this only saves a few bytes, but would require ugly #ifdefs in each driver using it. Simplify the other user while we're at it. Fixes: e2fb2e2a33fa ("dmaengine: ptdma: Add debugfs entries for PTDMA") Fixes: 26cf132de6f7 ("dmaengine: Create debug directories for DMA devices") Signed-off-by: Arnd Bergmann Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20210920122017.205975-1-arnd@kernel.org Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index e5c2c9e71bf1..9000f3ffce8b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -944,10 +944,8 @@ struct dma_device { void (*device_issue_pending)(struct dma_chan *chan); void (*device_release)(struct dma_device *dev); /* debugfs support */ -#ifdef CONFIG_DEBUG_FS void (*dbg_summary_show)(struct seq_file *s, struct dma_device *dev); struct dentry *dbg_dev_root; -#endif }; static inline int dmaengine_slave_config(struct dma_chan *chan, -- cgit v1.2.3 From 9baf93d68bcc3d0a6042283b82603c076e25e4f5 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 25 Oct 2021 16:27:16 -0300 Subject: fsnotify: pass data_type to fsnotify_name() Align the arguments of fsnotify_name() to those of fsnotify(). Link: https://lore.kernel.org/r/20211025192746.66445-2-krisman@collabora.com Reviewed-by: Jan Kara Signed-off-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 12d3a7d308ab..d1144d7c3536 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -26,20 +26,21 @@ * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ -static inline void fsnotify_name(struct inode *dir, __u32 mask, - struct inode *child, - const struct qstr *name, u32 cookie) +static inline int fsnotify_name(__u32 mask, const void *data, int data_type, + struct inode *dir, const struct qstr *name, + u32 cookie) { if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0) - return; + return 0; - fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie); + return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { - fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0); + fsnotify_name(mask, d_inode(dentry), FSNOTIFY_EVENT_INODE, + dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) @@ -154,8 +155,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, new_dir_mask |= FS_ISDIR; } - fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie); - fsnotify_name(new_dir, new_dir_mask, source, new_name, fs_cookie); + fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, + old_dir, old_name, fs_cookie); + fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, + new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); @@ -209,7 +212,8 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_name(dir, FS_CREATE, inode, &new_dentry->d_name, 0); + fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, + dir, &new_dentry->d_name, 0); } /* -- cgit v1.2.3 From fd5a3ff49a19aa69e2bc1e26e98037c2d778e61a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 25 Oct 2021 16:27:17 -0300 Subject: fsnotify: pass dentry instead of inode data Define a new data type to pass for event - FSNOTIFY_EVENT_DENTRY. Use it to pass the dentry instead of it's ->d_inode where available. This is needed in preparation to the refactor to retrieve the super block from the data field. In some cases (i.e. mkdir in kernfs), the data inode comes from a negative dentry, such that no super block information would be available. By receiving the dentry itself, instead of the inode, fsnotify can derive the super block even on these cases. Link: https://lore.kernel.org/r/20211025192746.66445-3-krisman@collabora.com Reviewed-by: Jan Kara Signed-off-by: Amir Goldstein [Expand explanation in commit message] Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 5 ++--- include/linux/fsnotify_backend.h | 16 ++++++++++++++++ 2 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index d1144d7c3536..df0fa4687a18 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -39,8 +39,7 @@ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { - fsnotify_name(mask, d_inode(dentry), FSNOTIFY_EVENT_INODE, - dir, &dentry->d_name, 0); + fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) @@ -87,7 +86,7 @@ notify_child: */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { - fsnotify_parent(dentry, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE); + fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_file(struct file *file, __u32 mask) diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 1ce66748a2d2..a2db821e8a8f 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -248,6 +248,7 @@ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, + FSNOTIFY_EVENT_DENTRY, }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) @@ -255,6 +256,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; + case FSNOTIFY_EVENT_DENTRY: + return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); default: @@ -262,6 +265,19 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) } } +static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_DENTRY: + /* Non const is needed for dget() */ + return (struct dentry *)data; + case FSNOTIFY_EVENT_PATH: + return ((const struct path *)data)->dentry; + default: + return NULL; + } +} + static inline const struct path *fsnotify_data_path(const void *data, int data_type) { -- cgit v1.2.3 From dabe729dddca550446e9cc118c96d1f91703345b Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 25 Oct 2021 16:27:18 -0300 Subject: fsnotify: clarify contract for create event hooks Clarify argument names and contract for fsnotify_create() and fsnotify_mkdir() to reflect the anomaly of kernfs, which leaves dentries negavite after mkdir/create. Remove the WARN_ON(!inode) in audit code that were added by the Fixes commit under the wrong assumption that dentries cannot be negative after mkdir/create. Fixes: aa93bdc5500c ("fsnotify: use helpers to access data by data_type") Link: https://lore.kernel.org/linux-fsdevel/87mtp5yz0q.fsf@collabora.com/ Link: https://lore.kernel.org/r/20211025192746.66445-4-krisman@collabora.com Reviewed-by: Jan Kara Reported-by: Gabriel Krisman Bertazi Signed-off-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index df0fa4687a18..1e5f7435a4b5 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -192,16 +192,22 @@ static inline void fsnotify_inoderemove(struct inode *inode) /* * fsnotify_create - 'name' was linked in + * + * Caller must make sure that dentry->d_name is stable. + * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate + * ->d_inode later */ -static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) +static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { - audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); + audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_dirent(inode, dentry, FS_CREATE); + fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory + * + * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ @@ -230,12 +236,16 @@ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) /* * fsnotify_mkdir - directory 'name' was created + * + * Caller must make sure that dentry->d_name is stable. + * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate + * ->d_inode later */ -static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) +static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { - audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); + audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_dirent(inode, dentry, FS_CREATE | FS_ISDIR); + fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* -- cgit v1.2.3 From 808967a0a4d2f4ce6a2005c5692fffbecaf018c1 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:23 -0300 Subject: fsnotify: Add helper to detect overflow_event Similarly to fanotify_is_perm_event and friends, provide a helper predicate to say whether a mask is of an overflow event. Link: https://lore.kernel.org/r/20211025192746.66445-9-krisman@collabora.com Suggested-by: Amir Goldstein Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index a2db821e8a8f..749bc85e1d1c 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -510,6 +510,11 @@ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) fsnotify_add_event(group, group->overflow_event, NULL, NULL); } +static inline bool fsnotify_is_overflow_event(u32 mask) +{ + return mask & FS_Q_OVERFLOW; +} + static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); -- cgit v1.2.3 From 1ad03c3a326a86e259389592117252c851873395 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:24 -0300 Subject: fsnotify: Add wrapper around fsnotify_add_event fsnotify_add_event is growing in number of parameters, which in most case are just passed a NULL pointer. So, split out a new fsnotify_insert_event function to clean things up for users who don't need an insert hook. Link: https://lore.kernel.org/r/20211025192746.66445-10-krisman@collabora.com Suggested-by: Amir Goldstein Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 749bc85e1d1c..b323d0c4b967 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -498,16 +498,25 @@ extern int fsnotify_fasync(int fd, struct file *file, int on); extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ -extern int fsnotify_add_event(struct fsnotify_group *group, - struct fsnotify_event *event, - int (*merge)(struct fsnotify_group *, - struct fsnotify_event *), - void (*insert)(struct fsnotify_group *, - struct fsnotify_event *)); +extern int fsnotify_insert_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *), + void (*insert)(struct fsnotify_group *, + struct fsnotify_event *)); + +static inline int fsnotify_add_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *)) +{ + return fsnotify_insert_event(group, event, merge, NULL); +} + /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { - fsnotify_add_event(group, group->overflow_event, NULL, NULL); + fsnotify_add_event(group, group->overflow_event, NULL); } static inline bool fsnotify_is_overflow_event(u32 mask) -- cgit v1.2.3 From 29335033c574a15334015d8c4e36862cff3d3384 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:25 -0300 Subject: fsnotify: Retrieve super block from the data field Some file system events (i.e. FS_ERROR) might not be associated with an inode or directory. For these, we can retrieve the super block from the data field. But, since the super_block is available in the data field on every event type, simplify the code to always retrieve it from there, through a new helper. Link: https://lore.kernel.org/r/20211025192746.66445-11-krisman@collabora.com Suggested-by: Jan Kara Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b323d0c4b967..035438fe4a43 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -289,6 +289,21 @@ static inline const struct path *fsnotify_data_path(const void *data, } } +static inline struct super_block *fsnotify_data_sb(const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_INODE: + return ((struct inode *)data)->i_sb; + case FSNOTIFY_EVENT_DENTRY: + return ((struct dentry *)data)->d_sb; + case FSNOTIFY_EVENT_PATH: + return ((const struct path *)data)->dentry->d_sb; + default: + return NULL; + } +} + enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_PARENT, -- cgit v1.2.3 From 24dca90590509a7a6cbe0650100c90c5b8a3468a Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:26 -0300 Subject: fsnotify: Protect fsnotify_handle_inode_event from no-inode events FAN_FS_ERROR allows events without inodes - i.e. for file system-wide errors. Even though fsnotify_handle_inode_event is not currently used by fanotify, this patch protects other backends from cases where neither inode or dir are provided. Also document the constraints of the interface (inode and dir cannot be both NULL). Link: https://lore.kernel.org/r/20211025192746.66445-12-krisman@collabora.com Suggested-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 035438fe4a43..b71dc788018e 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -136,6 +136,7 @@ struct mem_cgroup; * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. + * Either @inode or @dir must be non-NULL. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * -- cgit v1.2.3 From 330ae77d2a5b0af32c0f29e139bf28ec8591de59 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:27 -0300 Subject: fsnotify: Pass group argument to free_event For group-wide mempool backed events, like FS_ERROR, the free_event callback will need to reference the group's mempool to free the memory. Wire that argument into the current callers. Link: https://lore.kernel.org/r/20211025192746.66445-13-krisman@collabora.com Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b71dc788018e..3a7c31436182 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -156,7 +156,7 @@ struct fsnotify_ops { const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); - void (*free_event)(struct fsnotify_event *event); + void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; -- cgit v1.2.3 From 4fe595cf1c80e7a5af4d00c4da29def64aff57a2 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:31 -0300 Subject: fanotify: Require fid_mode for any non-fd event Like inode events, FAN_FS_ERROR will require fid mode. Therefore, convert the verification during fanotify_mark(2) to require fid for any non-fd event. This means fid_mode will not only be required for inode events, but for any event that doesn't provide a descriptor. Link: https://lore.kernel.org/r/20211025192746.66445-17-krisman@collabora.com Suggested-by: Amir Goldstein Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fanotify.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index eec3b7c40811..52d464802d99 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -84,6 +84,9 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ */ #define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE) +/* Events that can be reported with event->fd */ +#define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS) + /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */ #define FANOTIFY_INODE_EVENTS (FANOTIFY_DIRENT_EVENTS | \ FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF) -- cgit v1.2.3 From 9daa811073fa19c08e8aad3b90f9235fed161acf Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:32 -0300 Subject: fsnotify: Support FS_ERROR event type Expose a new type of fsnotify event for filesystems to report errors for userspace monitoring tools. fanotify will send this type of notification for FAN_FS_ERROR events. This also introduce a helper for generating the new event. Link: https://lore.kernel.org/r/20211025192746.66445-18-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 13 +++++++++++++ include/linux/fsnotify_backend.h | 32 +++++++++++++++++++++++++++++++- 2 files changed, 44 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1e5f7435a4b5..787545e87eeb 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -339,4 +339,17 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) fsnotify_dentry(dentry, mask); } +static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, + int error) +{ + struct fs_error_report report = { + .error = error, + .inode = inode, + .sb = sb, + }; + + return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, + NULL, NULL, NULL, 0); +} + #endif /* _LINUX_FS_NOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 3a7c31436182..00dbaafbcf95 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -42,6 +42,12 @@ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */ + +/* + * FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify + * which does not support FS_ERROR. + */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ @@ -95,7 +101,8 @@ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \ - FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED) + FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ + FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ @@ -250,6 +257,13 @@ enum fsnotify_data_type { FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, + FSNOTIFY_EVENT_ERROR, +}; + +struct fs_error_report { + int error; + struct inode *inode; + struct super_block *sb; }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) @@ -261,6 +275,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); + case FSNOTIFY_EVENT_ERROR: + return ((struct fs_error_report *)data)->inode; default: return NULL; } @@ -300,6 +316,20 @@ static inline struct super_block *fsnotify_data_sb(const void *data, return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; + case FSNOTIFY_EVENT_ERROR: + return ((struct fs_error_report *) data)->sb; + default: + return NULL; + } +} + +static inline struct fs_error_report *fsnotify_data_error_report( + const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_ERROR: + return (struct fs_error_report *) data; default: return NULL; } -- cgit v1.2.3 From 734a1a5eccc5f7473002b0669f788e135f1f64aa Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:34 -0300 Subject: fanotify: Pre-allocate pool of error events Pre-allocate slots for file system errors to have greater chances of succeeding, since error events can happen in GFP_NOFS context. This patch introduces a group-wide mempool of error events, shared by all FAN_FS_ERROR marks in this group. Link: https://lore.kernel.org/r/20211025192746.66445-20-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 00dbaafbcf95..51ef2b079bfa 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -19,6 +19,7 @@ #include #include #include +#include /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily @@ -246,6 +247,7 @@ struct fsnotify_group { int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ struct ucounts *ucounts; + mempool_t error_events_pool; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; -- cgit v1.2.3 From 9709bd548f11a092d124698118013f66e1740f9b Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:43 -0300 Subject: fanotify: Allow users to request FAN_FS_ERROR events Wire up the FAN_FS_ERROR event in the fanotify_mark syscall, allowing user space to request the monitoring of FAN_FS_ERROR events. These events are limited to filesystem marks, so check it is the case in the syscall handler. Link: https://lore.kernel.org/r/20211025192746.66445-29-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fanotify.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 52d464802d99..616af2ea20f3 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -91,9 +91,13 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_INODE_EVENTS (FANOTIFY_DIRENT_EVENTS | \ FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF) +/* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */ +#define FANOTIFY_ERROR_EVENTS (FAN_FS_ERROR) + /* Events that user can request to be notified on */ #define FANOTIFY_EVENTS (FANOTIFY_PATH_EVENTS | \ - FANOTIFY_INODE_EVENTS) + FANOTIFY_INODE_EVENTS | \ + FANOTIFY_ERROR_EVENTS) /* Events that require a permission response from user */ #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ -- cgit v1.2.3 From ee12203746e5cec678c7d126c9901548bfec1dd5 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Sat, 9 Oct 2021 09:44:39 -0700 Subject: PCI: Add pci_find_dvsec_capability to find designated VSEC Add pci_find_dvsec_capability to locate a Designated Vendor-Specific Extended Capability with the specified Vendor ID and Capability ID. The Designated Vendor-Specific Extended Capability (DVSEC) allows one or more "vendor" specific capabilities that are not tied to the Vendor ID of the PCI component. Where the DVSEC Vendor may be a standards body like CXL. Cc: David E. Box Cc: Jonathan Cameron Cc: Bjorn Helgaas Cc: Dan Williams Cc: linux-pci@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: Andrew Donnellan Cc: Lu Baolu Reviewed-by: Frederic Barrat Signed-off-by: Ben Widawsky Reviewed-by: Andrew Donnellan Acked-by: Bjorn Helgaas Tested-by: Kan Liang Signed-off-by: Kan Liang Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163379787943.692348.6814373487017444007.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..c93ccfa4571b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1130,6 +1130,7 @@ u16 pci_find_ext_capability(struct pci_dev *dev, int cap); u16 pci_find_next_ext_capability(struct pci_dev *dev, u16 pos, int cap); struct pci_bus *pci_find_next_bus(const struct pci_bus *from); u16 pci_find_vsec_capability(struct pci_dev *dev, u16 vendor, int cap); +u16 pci_find_dvsec_capability(struct pci_dev *dev, u16 vendor, u16 dvsec); u64 pci_get_dsn(struct pci_dev *dev); -- cgit v1.2.3 From 26d5badbccddcc063dc5174a2baffd13a23322aa Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 20 Oct 2021 12:43:59 -0500 Subject: signal: Implement force_fatal_sig Add a simple helper force_fatal_sig that causes a signal to be delivered to a process as if the signal handler was set to SIG_DFL. Reimplement force_sigsegv based upon this new helper. This fixes force_sigsegv so that when it forces the default signal handler to be used the code now forces the signal to be unblocked as well. Reusing the tested logic in force_sig_info_to_task that was built for force_sig_seccomp this makes the implementation trivial. This is interesting both because it makes force_sigsegv simpler and because there are a couple of buggy places in the kernel that call do_exit(SIGILL) or do_exit(SIGSYS) because there is no straight forward way today for those places to simply force the exit of a process with the chosen signal. Creating force_fatal_sig allows those places to be implemented with normal signal exits. Link: https://lkml.kernel.org/r/20211020174406.17889-13-ebiederm@xmission.com Signed-off-by: Eric W. Biederman --- include/linux/sched/signal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index e5f4ce622ee6..e2dc9f119ada 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -338,6 +338,7 @@ extern int kill_pid(struct pid *pid, int sig, int priv); extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); +extern void force_fatal_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); -- cgit v1.2.3 From 7ff22787ba49c2e66dcec92f3e2b79ef6b6a0d71 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Mon, 4 Oct 2021 10:07:09 -0700 Subject: platform/chrome: cros_ec_proto: Use EC struct for features The Chrome EC's features are returned through an ec_response_get_features struct, but they are stored in an independent array. Although the two are effectively the same at present (2 unsigned 32 bit ints), there is the possibility that they could go out of sync. Avoid this by only using the EC struct to store the features. Signed-off-by: Prashant Malani Link: https://lore.kernel.org/r/20211004170716.86601-1-pmalani@chromium.org Signed-off-by: Benson Leung --- include/linux/platform_data/cros_ec_proto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 9d370816a419..df3c78c92ca2 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -205,7 +205,7 @@ struct cros_ec_dev { struct cros_ec_debugfs *debug_info; bool has_kb_wake_angle; u16 cmd_offset; - u32 features[2]; + struct ec_response_get_features features; }; #define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev) -- cgit v1.2.3 From 74128d801b5165650ae6222e8cf23780fbc55e67 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 23 Sep 2021 01:09:45 +0200 Subject: watchdog: ux500_wdt: Drop platform data Drop the platform data passing from the PRCMU driver. This platform data was part of the ambition to support more SoCs, which in turn were never mass produced. Only a name remains of the MFD cell so switch to MFD_CELL_NAME(). Cc: Lee Jones Signed-off-by: Linus Walleij Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20210922230947.1864357-1-linus.walleij@linaro.org Acked-by: Lee Jones Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/platform_data/ux500_wdt.h | 18 ------------------ 1 file changed, 18 deletions(-) delete mode 100644 include/linux/platform_data/ux500_wdt.h (limited to 'include/linux') diff --git a/include/linux/platform_data/ux500_wdt.h b/include/linux/platform_data/ux500_wdt.h deleted file mode 100644 index de6a4ad41e76..000000000000 --- a/include/linux/platform_data/ux500_wdt.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST Ericsson SA 2011 - * - * STE Ux500 Watchdog platform data - */ -#ifndef __UX500_WDT_H -#define __UX500_WDT_H - -/** - * struct ux500_wdt_data - */ -struct ux500_wdt_data { - unsigned int timeout; - bool has_28_bits_resolution; -}; - -#endif /* __UX500_WDT_H */ -- cgit v1.2.3 From ca7752caeaa70bd31d1714af566c9809688544af Mon Sep 17 00:00:00 2001 From: Michael Pratt Date: Mon, 1 Nov 2021 17:06:15 -0400 Subject: posix-cpu-timers: Clear task::posix_cputimers_work in copy_process() copy_process currently copies task_struct.posix_cputimers_work as-is. If a timer interrupt arrives while handling clone and before dup_task_struct completes then the child task will have: 1. posix_cputimers_work.scheduled = true 2. posix_cputimers_work.work queued. copy_process clears task_struct.task_works, so (2) will have no effect and posix_cpu_timers_work will never run (not to mention it doesn't make sense for two tasks to share a common linked list). Since posix_cpu_timers_work never runs, posix_cputimers_work.scheduled is never cleared. Since scheduled is set, future timer interrupts will skip scheduling work, with the ultimate result that the task will never receive timer expirations. Together, the complete flow is: 1. Task 1 calls clone(), enters kernel. 2. Timer interrupt fires, schedules task work on Task 1. 2a. task_struct.posix_cputimers_work.scheduled = true 2b. task_struct.posix_cputimers_work.work added to task_struct.task_works. 3. dup_task_struct() copies Task 1 to Task 2. 4. copy_process() clears task_struct.task_works for Task 2. 5. Future timer interrupts on Task 2 see task_struct.posix_cputimers_work.scheduled = true and skip scheduling work. Fix this by explicitly clearing contents of task_struct.posix_cputimers_work in copy_process(). This was never meant to be shared or inherited across tasks in the first place. Fixes: 1fb497dd0030 ("posix-cpu-timers: Provide mechanisms to defer timer handling to task_work") Reported-by: Rhys Hiltner Signed-off-by: Michael Pratt Signed-off-by: Thomas Gleixner Cc: Link: https://lore.kernel.org/r/20211101210615.716522-1-mpratt@google.com --- include/linux/posix-timers.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 00fef0064355..5bbcd280bfd2 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -184,8 +184,10 @@ static inline void posix_cputimers_group_init(struct posix_cputimers *pct, #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK +void clear_posix_cputimers_work(struct task_struct *p); void posix_cputimers_init_work(void); #else +static inline void clear_posix_cputimers_work(struct task_struct *p) { } static inline void posix_cputimers_init_work(void) { } #endif -- cgit v1.2.3 From 8791545eda52e8f3bc48e3cd902e38bf4ba4c9de Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 22 Oct 2021 16:17:03 -0400 Subject: NFS: Move NFS protocol display macros to global header Refactor: surface useful show_ macros so they can be shared between the client and server trace code. Additional clean up: - Housekeeping: ensure the correct #include files are pulled in and add proper TRACE_DEFINE_ENUM where they are missing - Use a consistent naming scheme for the helpers - Store values to be displayed symbolically as unsigned long, as that is the type that the __print_yada() functions take Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 15004c469807..5662d8be04eb 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -292,6 +292,10 @@ enum nfsstat4 { NFS4ERR_XATTR2BIG = 10096, }; +/* error codes for internal client use */ +#define NFS4ERR_RESET_TO_MDS 12001 +#define NFS4ERR_RESET_TO_PNFS 12002 + static inline bool seqid_mutating_err(u32 err) { /* See RFC 7530, section 9.1.7 */ -- cgit v1.2.3 From 5fe11512cdc24ccc66ac5da3c815ac9e59449abc Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 2 Nov 2021 16:33:13 -0700 Subject: Input: remove unused header Commit 83b41248ed04 ("Input: cy8ctmg110_ts - switch to using gpiod API") remove the last use of but left the header file behind. Nothing uses it now, delete it. Signed-off-by: Jonathan Corbet Link: https://lore.kernel.org/r/20211102220203.940290-6-corbet@lwn.net Signed-off-by: Dmitry Torokhov --- include/linux/input/cy8ctmg110_pdata.h | 10 ---------- 1 file changed, 10 deletions(-) delete mode 100644 include/linux/input/cy8ctmg110_pdata.h (limited to 'include/linux') diff --git a/include/linux/input/cy8ctmg110_pdata.h b/include/linux/input/cy8ctmg110_pdata.h deleted file mode 100644 index ee1d44545f30..000000000000 --- a/include/linux/input/cy8ctmg110_pdata.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_CY8CTMG110_PDATA_H -#define _LINUX_CY8CTMG110_PDATA_H - -struct cy8ctmg110_pdata -{ - int reset_pin; /* Reset pin is wired to this GPIO (optional) */ -}; - -#endif -- cgit v1.2.3 From c4777efa751d293e369aec464ce6875e957be255 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 1 Nov 2021 17:45:55 -0700 Subject: net: add and use skb_unclone_keeptruesize() helper While commit 097b9146c0e2 ("net: fix up truesize of cloned skb in skb_prepare_for_shift()") fixed immediate issues found when KFENCE was enabled/tested, there are still similar issues, when tcp_trim_head() hits KFENCE while the master skb is cloned. This happens under heavy networking TX workloads, when the TX completion might be delayed after incoming ACK. This patch fixes the WARNING in sk_stream_kill_queues when sk->sk_mem_queued/sk->sk_forward_alloc are not zero. Fixes: d3fb45f370d9 ("mm, kfence: insert KFENCE hooks for SLAB") Signed-off-by: Eric Dumazet Acked-by: Marco Elver Link: https://lore.kernel.org/r/20211102004555.1359210-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0bd6520329f6..a63e13082397 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1675,6 +1675,22 @@ static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) return 0; } +/* This variant of skb_unclone() makes sure skb->truesize is not changed */ +static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) +{ + might_sleep_if(gfpflags_allow_blocking(pri)); + + if (skb_cloned(skb)) { + unsigned int save = skb->truesize; + int res; + + res = pskb_expand_head(skb, 0, 0, pri); + skb->truesize = save; + return res; + } + return 0; +} + /** * skb_header_cloned - is the header a clone * @skb: buffer to check -- cgit v1.2.3 From 0dc54bd4d6e03be1f0b678c4297170b79f1a44ab Mon Sep 17 00:00:00 2001 From: Dominique Martinet Date: Wed, 3 Nov 2021 17:34:05 +0900 Subject: fscache_cookie_enabled: check cookie is valid before accessing it fscache_cookie_enabled() could be called on NULL cookies and cause a null pointer dereference when accessing cookie flags: just make sure the cookie is valid first Suggested-by: David Howells Acked-by: David Howells Signed-off-by: Dominique Martinet --- include/linux/fscache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index a4dab5998613..3b2282c157f7 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -167,7 +167,7 @@ struct fscache_cookie { static inline bool fscache_cookie_enabled(struct fscache_cookie *cookie) { - return test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); + return fscache_cookie_valid(cookie) && test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); } /* -- cgit v1.2.3 From c081d53f97a1a90a38e4296dd3d6fda5e38dca2c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 2 Nov 2021 08:02:47 -0400 Subject: security: pass asoc to sctp_assoc_request and sctp_sk_clone This patch is to move secid and peer_secid from endpoint to association, and pass asoc to sctp_assoc_request and sctp_sk_clone instead of ep. As ep is the local endpoint and asoc represents a connection, and in SCTP one sk/ep could have multiple asoc/connection, saving secid/peer_secid for new asoc will overwrite the old asoc's. Note that since asoc can be passed as NULL, security_sctp_assoc_request() is moved to the place right after the new_asoc is created in sctp_sf_do_5_1B_init() and sctp_sf_do_unexpected_init(). v1->v2: - fix the description of selinux_netlbl_skbuff_setsid(), as Jakub noticed. - fix the annotation in selinux_sctp_assoc_request(), as Richard Noticed. Fixes: 72e89f50084c ("security: Add support for SCTP security hooks") Reported-by: Prashanth Prahlad Reviewed-by: Richard Haines Tested-by: Richard Haines Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/lsm_hook_defs.h | 4 ++-- include/linux/lsm_hooks.h | 8 ++++---- include/linux/security.h | 10 +++++----- 3 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index a9ac70ae01ab..df8de62f4710 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -329,11 +329,11 @@ LSM_HOOK(int, 0, tun_dev_create, void) LSM_HOOK(int, 0, tun_dev_attach_queue, void *security) LSM_HOOK(int, 0, tun_dev_attach, struct sock *sk, void *security) LSM_HOOK(int, 0, tun_dev_open, void *security) -LSM_HOOK(int, 0, sctp_assoc_request, struct sctp_endpoint *ep, +LSM_HOOK(int, 0, sctp_assoc_request, struct sctp_association *asoc, struct sk_buff *skb) LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) -LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_endpoint *ep, +LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) #endif /* CONFIG_SECURITY_NETWORK */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 0bada4df23fc..d45b6f6e27fd 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1027,9 +1027,9 @@ * Security hooks for SCTP * * @sctp_assoc_request: - * Passes the @ep and @chunk->skb of the association INIT packet to + * Passes the @asoc and @chunk->skb of the association INIT packet to * the security module. - * @ep pointer to sctp endpoint structure. + * @asoc pointer to sctp association structure. * @skb pointer to skbuff of association packet. * Return 0 on success, error on failure. * @sctp_bind_connect: @@ -1047,9 +1047,9 @@ * Called whenever a new socket is created by accept(2) (i.e. a TCP * style socket) or when a socket is 'peeled off' e.g userspace * calls sctp_peeloff(3). - * @ep pointer to current sctp endpoint structure. + * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. - * @sk pointer to new sock structure. + * @newsk pointer to new sock structure. * * Security hooks for Infiniband * diff --git a/include/linux/security.h b/include/linux/security.h index 7e0ba63b5dde..bbf44a466832 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -179,7 +179,7 @@ struct xfrm_policy; struct xfrm_state; struct xfrm_user_sec_ctx; struct seq_file; -struct sctp_endpoint; +struct sctp_association; #ifdef CONFIG_MMU extern unsigned long mmap_min_addr; @@ -1425,10 +1425,10 @@ int security_tun_dev_create(void); int security_tun_dev_attach_queue(void *security); int security_tun_dev_attach(struct sock *sk, void *security); int security_tun_dev_open(void *security); -int security_sctp_assoc_request(struct sctp_endpoint *ep, struct sk_buff *skb); +int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb); int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); -void security_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, +void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); #else /* CONFIG_SECURITY_NETWORK */ @@ -1631,7 +1631,7 @@ static inline int security_tun_dev_open(void *security) return 0; } -static inline int security_sctp_assoc_request(struct sctp_endpoint *ep, +static inline int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { return 0; @@ -1644,7 +1644,7 @@ static inline int security_sctp_bind_connect(struct sock *sk, int optname, return 0; } -static inline void security_sctp_sk_clone(struct sctp_endpoint *ep, +static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { -- cgit v1.2.3 From 7c2ef0240e6abfd3cc59511339517358350a8910 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 2 Nov 2021 08:02:49 -0400 Subject: security: add sctp_assoc_established hook security_sctp_assoc_established() is added to replace security_inet_conn_established() called in sctp_sf_do_5_1E_ca(), so that asoc can be accessed in security subsystem and save the peer secid to asoc->peer_secid. v1->v2: - fix the return value of security_sctp_assoc_established() in security.h, found by kernel test robot and Ondrej. Fixes: 72e89f50084c ("security: Add support for SCTP security hooks") Reported-by: Prashanth Prahlad Reviewed-by: Richard Haines Tested-by: Richard Haines Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/lsm_hook_defs.h | 2 ++ include/linux/lsm_hooks.h | 5 +++++ include/linux/security.h | 7 +++++++ 3 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index df8de62f4710..442a611fa0fb 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -335,6 +335,8 @@ LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) +LSM_HOOK(void, LSM_RET_VOID, sctp_assoc_established, struct sctp_association *asoc, + struct sk_buff *skb) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d45b6f6e27fd..d6823214d5c1 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1050,6 +1050,11 @@ * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. * @newsk pointer to new sock structure. + * @sctp_assoc_established: + * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet + * to the security module. + * @asoc pointer to sctp association structure. + * @skb pointer to skbuff of association packet. * * Security hooks for Infiniband * diff --git a/include/linux/security.h b/include/linux/security.h index bbf44a466832..06eac4e61a13 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1430,6 +1430,8 @@ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); +void security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb); #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, @@ -1649,6 +1651,11 @@ static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *newsk) { } + +static inline void security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb) +{ +} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND -- cgit v1.2.3 From 9b65b17db72313b7a4fe9bc9502928c88be57986 Mon Sep 17 00:00:00 2001 From: Talal Ahmad Date: Tue, 2 Nov 2021 22:58:44 -0400 Subject: net: avoid double accounting for pure zerocopy skbs Track skbs containing only zerocopy data and avoid charging them to kernel memory to correctly account the memory utilization for msg_zerocopy. All of the data in such skbs is held in user pages which are already accounted to user. Before this change, they are charged again in kernel in __zerocopy_sg_from_iter. The charging in kernel is excessive because data is not being copied into skb frags. This excessive charging can lead to kernel going into memory pressure state which impacts all sockets in the system adversely. Mark pure zerocopy skbs with a SKBFL_PURE_ZEROCOPY flag and remove charge/uncharge for data in such skbs. Initially, an skb is marked pure zerocopy when it is empty and in zerocopy path. skb can then change from a pure zerocopy skb to mixed data skb (zerocopy and copy data) if it is at tail of write queue and there is room available in it and non-zerocopy data is being sent in the next sendmsg call. At this time sk_mem_charge is done for the pure zerocopied data and the pure zerocopy flag is unmarked. We found that this happens very rarely on workloads that pass MSG_ZEROCOPY. A pure zerocopy skb can later be coalesced into normal skb if they are next to each other in queue but this patch prevents coalescing from happening. This avoids complexity of charging when skb downgrades from pure zerocopy to mixed. This is also rare. In sk_wmem_free_skb, if it is a pure zerocopy skb, an sk_mem_uncharge for SKB_TRUESIZE(skb_end_offset(skb)) is done for sk_mem_charge in tcp_skb_entail for an skb without data. Testing with the msg_zerocopy.c benchmark between two hosts(100G nics) with zerocopy showed that before this patch the 'sock' variable in memory.stat for cgroup2 that tracks sum of sk_forward_alloc, sk_rmem_alloc and sk_wmem_queued is around 1822720 and with this change it is 0. This is due to no charge to sk_forward_alloc for zerocopy data and shows memory utilization for kernel is lowered. With this commit we don't see the warning we saw in previous commit which resulted in commit 84882cf72cd774cf16fd338bdbf00f69ac9f9194. Signed-off-by: Talal Ahmad Acked-by: Arjun Roy Acked-by: Soheil Hassas Yeganeh Signed-off-by: Willem de Bruijn Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a63e13082397..686a666d073d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -454,9 +454,15 @@ enum { * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), + + /* segment contains only zerocopy data and should not be + * charged to the kernel memory. + */ + SKBFL_PURE_ZEROCOPY = BIT(2), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) +#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -1464,6 +1470,17 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } +static inline bool skb_zcopy_pure(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; +} + +static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, + const struct sk_buff *skb2) +{ + return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); +} + static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); @@ -1528,7 +1545,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (!skb_zcopy_is_nouarg(skb)) uarg->callback(skb, uarg, zerocopy_success); - skb_shinfo(skb)->flags &= ~SKBFL_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } -- cgit v1.2.3 From 1aabe578dd86e9f2867c4db4fba9a15f4ba1825d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 2 Nov 2021 15:02:36 -0700 Subject: ethtool: fix ethtool msg len calculation for pause stats ETHTOOL_A_PAUSE_STAT_MAX is the MAX attribute id, so we need to subtract non-stats and add one to get a count (IOW -2+1 == -1). Otherwise we'll see: ethnl cmd 21: calculated reply length 40, but consumed 52 Fixes: 9a27a33027f2 ("ethtool: add standard pause stats") Signed-off-by: Jakub Kicinski Reviewed-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 1e7bf78cb382..aba348d58ff6 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -10,6 +10,9 @@ #define __ETHTOOL_LINK_MODE_MASK_NWORDS \ DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) +#define ETHTOOL_PAUSE_STAT_CNT (__ETHTOOL_A_PAUSE_STAT_CNT - \ + ETHTOOL_A_PAUSE_STAT_TX_FRAMES) + enum ethtool_multicast_groups { ETHNL_MCGRP_MONITOR, }; -- cgit v1.2.3 From 4330fe35b8213e92ff51907b4cb6323be943a9ad Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 2 Nov 2021 16:01:56 -0600 Subject: nfs: remove unused header Commit 19fcae3d4f2dd ("scsi: remove the SCSI OSD library") deleted the last file that included but left that file behind. It's unused, get rid of it now. Cc: Christoph Hellwig Cc: Trond Myklebust Cc: Anna Schumaker Cc: linux-nfs@vger.kernel.org Signed-off-by: Jonathan Corbet Signed-off-by: Trond Myklebust --- include/linux/pnfs_osd_xdr.h | 317 ------------------------------------------- 1 file changed, 317 deletions(-) delete mode 100644 include/linux/pnfs_osd_xdr.h (limited to 'include/linux') diff --git a/include/linux/pnfs_osd_xdr.h b/include/linux/pnfs_osd_xdr.h deleted file mode 100644 index 17d7d0d20eca..000000000000 --- a/include/linux/pnfs_osd_xdr.h +++ /dev/null @@ -1,317 +0,0 @@ -/* - * pNFS-osd on-the-wire data structures - * - * Copyright (C) 2007 Panasas Inc. [year of first publication] - * All rights reserved. - * - * Benny Halevy - * Boaz Harrosh - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * See the file COPYING included with this distribution for more details. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the Panasas company nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ -#ifndef __PNFS_OSD_XDR_H__ -#define __PNFS_OSD_XDR_H__ - -#include - -/* - * draft-ietf-nfsv4-minorversion-22 - * draft-ietf-nfsv4-pnfs-obj-12 - */ - -/* Layout Structure */ - -enum pnfs_osd_raid_algorithm4 { - PNFS_OSD_RAID_0 = 1, - PNFS_OSD_RAID_4 = 2, - PNFS_OSD_RAID_5 = 3, - PNFS_OSD_RAID_PQ = 4 /* Reed-Solomon P+Q */ -}; - -/* struct pnfs_osd_data_map4 { - * uint32_t odm_num_comps; - * length4 odm_stripe_unit; - * uint32_t odm_group_width; - * uint32_t odm_group_depth; - * uint32_t odm_mirror_cnt; - * pnfs_osd_raid_algorithm4 odm_raid_algorithm; - * }; - */ -struct pnfs_osd_data_map { - u32 odm_num_comps; - u64 odm_stripe_unit; - u32 odm_group_width; - u32 odm_group_depth; - u32 odm_mirror_cnt; - u32 odm_raid_algorithm; -}; - -/* struct pnfs_osd_objid4 { - * deviceid4 oid_device_id; - * uint64_t oid_partition_id; - * uint64_t oid_object_id; - * }; - */ -struct pnfs_osd_objid { - struct nfs4_deviceid oid_device_id; - u64 oid_partition_id; - u64 oid_object_id; -}; - -/* For printout. I use: - * kprint("dev(%llx:%llx)", _DEVID_LO(pointer), _DEVID_HI(pointer)); - * BE style - */ -#define _DEVID_LO(oid_device_id) \ - (unsigned long long)be64_to_cpup((__be64 *)(oid_device_id)->data) - -#define _DEVID_HI(oid_device_id) \ - (unsigned long long)be64_to_cpup(((__be64 *)(oid_device_id)->data) + 1) - -enum pnfs_osd_version { - PNFS_OSD_MISSING = 0, - PNFS_OSD_VERSION_1 = 1, - PNFS_OSD_VERSION_2 = 2 -}; - -struct pnfs_osd_opaque_cred { - u32 cred_len; - void *cred; -}; - -enum pnfs_osd_cap_key_sec { - PNFS_OSD_CAP_KEY_SEC_NONE = 0, - PNFS_OSD_CAP_KEY_SEC_SSV = 1, -}; - -/* struct pnfs_osd_object_cred4 { - * pnfs_osd_objid4 oc_object_id; - * pnfs_osd_version4 oc_osd_version; - * pnfs_osd_cap_key_sec4 oc_cap_key_sec; - * opaque oc_capability_key<>; - * opaque oc_capability<>; - * }; - */ -struct pnfs_osd_object_cred { - struct pnfs_osd_objid oc_object_id; - u32 oc_osd_version; - u32 oc_cap_key_sec; - struct pnfs_osd_opaque_cred oc_cap_key; - struct pnfs_osd_opaque_cred oc_cap; -}; - -/* struct pnfs_osd_layout4 { - * pnfs_osd_data_map4 olo_map; - * uint32_t olo_comps_index; - * pnfs_osd_object_cred4 olo_components<>; - * }; - */ -struct pnfs_osd_layout { - struct pnfs_osd_data_map olo_map; - u32 olo_comps_index; - u32 olo_num_comps; - struct pnfs_osd_object_cred *olo_comps; -}; - -/* Device Address */ -enum pnfs_osd_targetid_type { - OBJ_TARGET_ANON = 1, - OBJ_TARGET_SCSI_NAME = 2, - OBJ_TARGET_SCSI_DEVICE_ID = 3, -}; - -/* union pnfs_osd_targetid4 switch (pnfs_osd_targetid_type4 oti_type) { - * case OBJ_TARGET_SCSI_NAME: - * string oti_scsi_name<>; - * - * case OBJ_TARGET_SCSI_DEVICE_ID: - * opaque oti_scsi_device_id<>; - * - * default: - * void; - * }; - * - * union pnfs_osd_targetaddr4 switch (bool ota_available) { - * case TRUE: - * netaddr4 ota_netaddr; - * case FALSE: - * void; - * }; - * - * struct pnfs_osd_deviceaddr4 { - * pnfs_osd_targetid4 oda_targetid; - * pnfs_osd_targetaddr4 oda_targetaddr; - * uint64_t oda_lun; - * opaque oda_systemid<>; - * pnfs_osd_object_cred4 oda_root_obj_cred; - * opaque oda_osdname<>; - * }; - */ -struct pnfs_osd_targetid { - u32 oti_type; - struct nfs4_string oti_scsi_device_id; -}; - -/* struct netaddr4 { - * // see struct rpcb in RFC1833 - * string r_netid<>; // network id - * string r_addr<>; // universal address - * }; - */ -struct pnfs_osd_net_addr { - struct nfs4_string r_netid; - struct nfs4_string r_addr; -}; - -struct pnfs_osd_targetaddr { - u32 ota_available; - struct pnfs_osd_net_addr ota_netaddr; -}; - -struct pnfs_osd_deviceaddr { - struct pnfs_osd_targetid oda_targetid; - struct pnfs_osd_targetaddr oda_targetaddr; - u8 oda_lun[8]; - struct nfs4_string oda_systemid; - struct pnfs_osd_object_cred oda_root_obj_cred; - struct nfs4_string oda_osdname; -}; - -/* LAYOUTCOMMIT: layoutupdate */ - -/* union pnfs_osd_deltaspaceused4 switch (bool dsu_valid) { - * case TRUE: - * int64_t dsu_delta; - * case FALSE: - * void; - * }; - * - * struct pnfs_osd_layoutupdate4 { - * pnfs_osd_deltaspaceused4 olu_delta_space_used; - * bool olu_ioerr_flag; - * }; - */ -struct pnfs_osd_layoutupdate { - u32 dsu_valid; - s64 dsu_delta; - u32 olu_ioerr_flag; -}; - -/* LAYOUTRETURN: I/O Rrror Report */ - -enum pnfs_osd_errno { - PNFS_OSD_ERR_EIO = 1, - PNFS_OSD_ERR_NOT_FOUND = 2, - PNFS_OSD_ERR_NO_SPACE = 3, - PNFS_OSD_ERR_BAD_CRED = 4, - PNFS_OSD_ERR_NO_ACCESS = 5, - PNFS_OSD_ERR_UNREACHABLE = 6, - PNFS_OSD_ERR_RESOURCE = 7 -}; - -/* struct pnfs_osd_ioerr4 { - * pnfs_osd_objid4 oer_component; - * length4 oer_comp_offset; - * length4 oer_comp_length; - * bool oer_iswrite; - * pnfs_osd_errno4 oer_errno; - * }; - */ -struct pnfs_osd_ioerr { - struct pnfs_osd_objid oer_component; - u64 oer_comp_offset; - u64 oer_comp_length; - u32 oer_iswrite; - u32 oer_errno; -}; - -/* OSD XDR Client API */ -/* Layout helpers */ -/* Layout decoding is done in two parts: - * 1. First Call pnfs_osd_xdr_decode_layout_map to read in only the header part - * of the layout. @iter members need not be initialized. - * Returned: - * @layout members are set. (@layout->olo_comps set to NULL). - * - * Zero on success, or negative error if passed xdr is broken. - * - * 2. 2nd Call pnfs_osd_xdr_decode_layout_comp() in a loop until it returns - * false, to decode the next component. - * Returned: - * true if there is more to decode or false if we are done or error. - * - * Example: - * struct pnfs_osd_xdr_decode_layout_iter iter; - * struct pnfs_osd_layout layout; - * struct pnfs_osd_object_cred comp; - * int status; - * - * status = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr); - * if (unlikely(status)) - * goto err; - * while(pnfs_osd_xdr_decode_layout_comp(&comp, &iter, xdr, &status)) { - * // All of @comp strings point to inside the xdr_buffer - * // or scrach buffer. Copy them out to user memory eg. - * copy_single_comp(dest_comp++, &comp); - * } - * if (unlikely(status)) - * goto err; - */ - -struct pnfs_osd_xdr_decode_layout_iter { - unsigned total_comps; - unsigned decoded_comps; -}; - -extern int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout, - struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr); - -extern bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp, - struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr, - int *err); - -/* Device Info helpers */ - -/* Note: All strings inside @deviceaddr point to space inside @p. - * @p should stay valid while @deviceaddr is in use. - */ -extern void pnfs_osd_xdr_decode_deviceaddr( - struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p); - -/* layoutupdate (layout_commit) xdr helpers */ -extern int -pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr, - struct pnfs_osd_layoutupdate *lou); - -/* osd_ioerror encoding (layout_return) */ -extern __be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr); -extern void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr); - -#endif /* __PNFS_OSD_XDR_H__ */ -- cgit v1.2.3 From 92f62485b3715882cd397b0cbd80a96d179b86d6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 2 Nov 2021 21:31:22 +0200 Subject: net: dsa: felix: fix broken VLAN-tagged PTP under VLAN-aware bridge Normally it is expected that the dsa_device_ops :: rcv() method finishes parsing the DSA tag and consumes it, then never looks at it again. But commit c0bcf537667c ("net: dsa: ocelot: add hardware timestamping support for Felix") added support for RX timestamping in a very unconventional way. On this switch, a partial timestamp is available in the DSA header, but the driver got away with not parsing that timestamp right away, but instead delayed that parsing for a little longer: dsa_switch_rcv(): nskb = cpu_dp->rcv(skb, dev); <------------- not here -> ocelot_rcv() ... skb = nskb; skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); ... if (dsa_skb_defer_rx_timestamp(p, skb)) <--- but here -> felix_rxtstamp() return 0; When in felix_rxtstamp(), this driver accounted for the fact that eth_type_trans() happened in the meanwhile, so it got a hold of the extraction header again by subtracting (ETH_HLEN + OCELOT_TAG_LEN) bytes from the current skb->data. This worked for quite some time but was quite fragile from the very beginning. Not to mention that having DSA tag parsing split in two different files, under different folders (net/dsa/tag_ocelot.c vs drivers/net/dsa/ocelot/felix.c) made it quite non-obvious for patches to come that they might break this. Finally, the blamed commit does the following: at the end of ocelot_rcv(), it checks whether the skb payload contains a VLAN header. If it does, and this port is under a VLAN-aware bridge, that VLAN ID might not be correct in the sense that the packet might have suffered VLAN rewriting due to TCAM rules (VCAP IS1). So we consume the VLAN ID from the skb payload using __skb_vlan_pop(), and take the classified VLAN ID from the DSA tag, and construct a hwaccel VLAN tag with the classified VLAN, and the skb payload is VLAN-untagged. The big problem is that __skb_vlan_pop() does: memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); __skb_pull(skb, VLAN_HLEN); aka it moves the Ethernet header 4 bytes to the right, and pulls 4 bytes from the skb headroom (effectively also moving skb->data, by definition). So for felix_rxtstamp()'s fragile logic, all bets are off now. Instead of having the "extraction" pointer point to the DSA header, it actually points to 4 bytes _inside_ the extraction header. Corollary, the last 4 bytes of the "extraction" header are in fact 4 stale bytes of the destination MAC address from the Ethernet header, from prior to the __skb_vlan_pop() movement. So of course, RX timestamps are completely bogus when the system is configured in this way. The fix is actually very simple: just don't structure the code like that. For better or worse, the DSA PTP timestamping API does not offer a straightforward way for drivers to present their RX timestamps, but other drivers (sja1105) have established a simple mechanism to carry their RX timestamp from dsa_device_ops :: rcv() all the way to dsa_switch_ops :: port_rxtstamp() and even later. That mechanism is to simply save the partial timestamp to the skb->cb, and complete it later. Question: why don't we simply populate the skb's struct skb_shared_hwtstamps from ocelot_rcv(), and bother with this complication of propagating the timestamp to felix_rxtstamp()? Answer: dsa_switch_ops :: port_rxtstamp() answers the question whether PTP packets need sleepable context to retrieve the full RX timestamp. Currently felix_rxtstamp() answers "no, thanks" to that question, and calls ocelot_ptp_gettime64() from softirq atomic context. This is understandable, since Felix VSC9959 is a PCIe memory-mapped switch, so hardware access does not require sleeping. But the felix driver is preparing for the introduction of other switches where hardware access is over a slow bus like SPI or MDIO: https://lore.kernel.org/lkml/20210814025003.2449143-1-colin.foster@in-advantage.com/ So I would like to keep this code structure, so the rework needed when that driver will need PTP support will be minimal (answer "yes, I need deferred context for this skb's RX timestamp", then the partial timestamp will still be found in the skb->cb. Fixes: ea440cd2d9b2 ("net: dsa: tag_ocelot: use VLAN information from tagging header when available") Reported-by: Po Liu Cc: Yangbo Lu Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/ocelot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index d42010cf5468..7ee708ad7df2 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -12,6 +12,7 @@ struct ocelot_skb_cb { struct sk_buff *clone; unsigned int ptp_class; /* valid only for clones */ + u32 tstamp_lo; u8 ptp_cmd; u8 ts_id; }; -- cgit v1.2.3 From 6429e46304ac7820eebbea2bf5d73b90c18e0e06 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 28 Oct 2021 10:47:21 +0100 Subject: libfs: Move shmem_exchange to simple_rename_exchange Move shmem_exchange and make it available to other callers. Suggested-by: Miklos Szeredi Signed-off-by: Lorenz Bauer Signed-off-by: Daniel Borkmann Acked-by: Miklos Szeredi Cc: Al Viro Cc: Christian Brauner Cc: Greg Kroah-Hartman Link: https://lore.kernel.org/bpf/20211028094724.59043-2-lmb@cloudflare.com --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f3cfca5edc9a..bc4e97b82ddd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3383,6 +3383,8 @@ extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); +extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename(struct user_namespace *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); -- cgit v1.2.3 From b18c1ad685d9a6af5189d4cc037a653270a07b4c Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 18 Oct 2021 15:17:25 +0300 Subject: i2c: Allow an ACPI driver to manage the device's power state during probe Enable drivers to tell ACPI that there's no need to power on a device for probe. Drivers should still perform this by themselves if there's a need to. In some cases powering on the device during probe is undesirable, and this change enables a driver to choose what fits best for it. Add a field called "flags" into struct i2c_driver for driver flags, and a flag I2C_DRV_ACPI_WAIVE_D0_PROBE to tell a driver supports probe in ACPI D states other than 0. Signed-off-by: Sakari Ailus Reviewed-by: Tomasz Figa Acked-by: Wolfram Sang Signed-off-by: Rafael J. Wysocki --- include/linux/i2c.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 2ce3efbe9198..16119ac1aa97 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -11,6 +11,7 @@ #define _LINUX_I2C_H #include /* for acpi_handle */ +#include #include #include /* for struct device */ #include /* for completion */ @@ -222,6 +223,15 @@ enum i2c_alert_protocol { I2C_PROTOCOL_SMBUS_HOST_NOTIFY, }; +/** + * enum i2c_driver_flags - Flags for an I2C device driver + * + * @I2C_DRV_ACPI_WAIVE_D0_PROBE: Don't put the device in D0 state for probe + */ +enum i2c_driver_flags { + I2C_DRV_ACPI_WAIVE_D0_PROBE = BIT(0), +}; + /** * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) @@ -236,6 +246,7 @@ enum i2c_alert_protocol { * @detect: Callback for device detection * @address_list: The I2C addresses to probe (for detect) * @clients: List of detected clients we created (for i2c-core use only) + * @flags: A bitmask of flags defined in &enum i2c_driver_flags * * The driver.owner field should be set to the module owner of this driver. * The driver.name field should be set to the name of this driver. @@ -294,6 +305,8 @@ struct i2c_driver { int (*detect)(struct i2c_client *client, struct i2c_board_info *info); const unsigned short *address_list; struct list_head clients; + + u32 flags; }; #define to_i2c_driver(d) container_of(d, struct i2c_driver, driver) @@ -1015,6 +1028,7 @@ u32 i2c_acpi_find_bus_speed(struct device *dev); struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info); struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle); +bool i2c_acpi_waive_d0_probe(struct device *dev); #else static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c) @@ -1038,6 +1052,10 @@ static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle ha { return NULL; } +static inline bool i2c_acpi_waive_d0_probe(struct device *dev) +{ + return false; +} #endif /* CONFIG_ACPI */ #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From b82a7df4a7f3841896aaec1ad81e654bc87b5989 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 18 Oct 2021 15:17:27 +0300 Subject: ACPI: Add a convenience function to tell a device is in D0 state Add a convenience function to tell whether a device is in D0 state, primarily for use in drivers' probe or remove functions on busses where the custom is to power on the device for the duration of both. Returns false on non-ACPI systems. Suggested-by: Mika Westerberg Signed-off-by: Sakari Ailus Reviewed-by: Tomasz Figa Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index fbc2146050a4..df70fc27afd7 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1016,6 +1016,7 @@ int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); bool acpi_storage_d3(struct device *dev); +bool acpi_dev_state_d0(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } @@ -1027,6 +1028,10 @@ static inline bool acpi_storage_d3(struct device *dev) { return false; } +static inline bool acpi_dev_state_d0(struct device *dev) +{ + return true; +} #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) -- cgit v1.2.3 From 00b06da29cf9dc633cdba87acd3f57f4df3fd5c7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 29 Oct 2021 09:14:19 -0500 Subject: signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed As Andy pointed out that there are races between force_sig_info_to_task and sigaction[1] when force_sig_info_task. As Kees discovered[2] ptrace is also able to change these signals. In the case of seeccomp killing a process with a signal it is a security violation to allow the signal to be caught or manipulated. Solve this problem by introducing a new flag SA_IMMUTABLE that prevents sigaction and ptrace from modifying these forced signals. This flag is carefully made kernel internal so that no new ABI is introduced. Longer term I think this can be solved by guaranteeing short circuit delivery of signals in this case. Unfortunately reliable and guaranteed short circuit delivery of these signals is still a ways off from being implemented, tested, and merged. So I have implemented a much simpler alternative for now. [1] https://lkml.kernel.org/r/b5d52d25-7bde-4030-a7b1-7c6f8ab90660@www.fastmail.com [2] https://lkml.kernel.org/r/202110281136.5CE65399A7@keescook Cc: stable@vger.kernel.org Fixes: 307d522f5eb8 ("signal/seccomp: Refactor seccomp signal and coredump generation") Tested-by: Andrea Righi Tested-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/signal_types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 34cb28b8f16c..a70b2bdbf4d9 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -70,6 +70,9 @@ struct ksignal { int sig; }; +/* Used to kill the race between sigaction and forced signals */ +#define SA_IMMUTABLE 0x00800000 + #ifndef __ARCH_UAPI_SA_FLAGS #ifdef SA_RESTORER #define __ARCH_UAPI_SA_FLAGS SA_RESTORER -- cgit v1.2.3 From 2116274af46b12df7cea1dc5698f3cf2f231f8a9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 4 Nov 2021 18:20:37 +0100 Subject: block: add a loff_t cast to bdev_nr_bytes Not really needed as both loff_t and sector_t are always 64-bits wide, but this documents the different types a bit better. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211104172037.531803-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 900325aa5d31..1dce769c4596 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -243,7 +243,7 @@ static inline sector_t bdev_nr_sectors(struct block_device *bdev) static inline loff_t bdev_nr_bytes(struct block_device *bdev) { - return bdev_nr_sectors(bdev) << SECTOR_SHIFT; + return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT; } static inline sector_t get_capacity(struct gendisk *disk) -- cgit v1.2.3 From 0ab8d0f6ae3f1234e38eaedc3ff7c22bfdf7f78c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 29 Sep 2021 17:38:34 +0100 Subject: irqdomain: Make of_phandle_args_to_fwspec() generally available of_phandle_args_to_fwspec() can be generally useful to code extracting a DT of_phandle and using an irq_fwspec to use the hierarchical irqdomain API. Make it visible to the rest of the kernel, including modules. Link: https://lore.kernel.org/r/20210929163847.2807812-2-maz@kernel.org Tested-by: Alyssa Rosenzweig Signed-off-by: Marc Zyngier Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/irqdomain.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 23e4ee523576..cfd442316f39 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -64,6 +64,10 @@ struct irq_fwspec { u32 param[IRQ_DOMAIN_IRQ_SPEC_PARAMS]; }; +/* Conversion function from of_phandle_args fields to fwspec */ +void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, + unsigned int count, struct irq_fwspec *fwspec); + /* * Should several domains have the same device node, but serve * different purposes (for example one domain is for PCI/MSI, and the -- cgit v1.2.3 From 439b08c57c3fe1df85cfe9d00accdf9b62cb3275 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 3 Nov 2021 16:51:36 +0100 Subject: Revert "usb: core: hcd: Add support for deferring roothub registration" This reverts commit 58877b0824da15698bd85a0a9dbfa8c354e6ecb7. It has been reported to be causing problems in Arch and Fedora bug reports. Reported-by: Hans de Goede Link: https://bbs.archlinux.org/viewtopic.php?pid=2000956#p2000956 Link: https://bugzilla.redhat.com/show_bug.cgi?id=2019542 Link: https://bugzilla.redhat.com/show_bug.cgi?id=2019576 Link: https://lore.kernel.org/r/42bcbea6-5eb8-16c7-336a-2cb72e71bc36@redhat.com Cc: Mathias Nyman Cc: Chris Chiu Cc: Alan Stern Cc: Kishon Vijay Abraham I Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 2c1fc9212cf2..548a028f2dab 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -124,7 +124,6 @@ struct usb_hcd { #define HCD_FLAG_RH_RUNNING 5 /* root hub is running? */ #define HCD_FLAG_DEAD 6 /* controller has died? */ #define HCD_FLAG_INTF_AUTHORIZED 7 /* authorize interfaces? */ -#define HCD_FLAG_DEFER_RH_REGISTER 8 /* Defer roothub registration */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). @@ -135,7 +134,6 @@ struct usb_hcd { #define HCD_WAKEUP_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING)) #define HCD_RH_RUNNING(hcd) ((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING)) #define HCD_DEAD(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEAD)) -#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER)) /* * Specifies if interfaces are authorized by default -- cgit v1.2.3 From 27d9a4d69433af1827a764fe235866d5d5501fdb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 9 Sep 2021 11:48:48 +0200 Subject: pwm: Add might_sleep() annotations for !CONFIG_PWM API functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The normal implementations of these functions make use of mutexes. To make it obvious that these functions might sleep also add annotations to the dummy implementations in the !CONFIG_PWM case. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/linux/pwm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 725c9b784e60..515e33978e97 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -429,11 +429,13 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev, #else static inline struct pwm_device *pwm_request(int pwm_id, const char *label) { + might_sleep(); return ERR_PTR(-ENODEV); } static inline void pwm_free(struct pwm_device *pwm) { + might_sleep(); } static inline int pwm_apply_state(struct pwm_device *pwm, @@ -493,12 +495,14 @@ static inline struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, unsigned int index, const char *label) { + might_sleep(); return ERR_PTR(-ENODEV); } static inline struct pwm_device *pwm_get(struct device *dev, const char *consumer) { + might_sleep(); return ERR_PTR(-ENODEV); } @@ -506,16 +510,19 @@ static inline struct pwm_device *of_pwm_get(struct device *dev, struct device_node *np, const char *con_id) { + might_sleep(); return ERR_PTR(-ENODEV); } static inline void pwm_put(struct pwm_device *pwm) { + might_sleep(); } static inline struct pwm_device *devm_pwm_get(struct device *dev, const char *consumer) { + might_sleep(); return ERR_PTR(-ENODEV); } @@ -523,6 +530,7 @@ static inline struct pwm_device *devm_of_pwm_get(struct device *dev, struct device_node *np, const char *con_id) { + might_sleep(); return ERR_PTR(-ENODEV); } @@ -530,6 +538,7 @@ static inline struct pwm_device * devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, const char *con_id) { + might_sleep(); return ERR_PTR(-ENODEV); } #endif -- cgit v1.2.3 From 4ad91a227817ae48f931595d1101fc7100073ce9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 9 Sep 2021 11:48:49 +0200 Subject: pwm: Make it explicit that pwm_apply_state() might sleep MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit At least some implementations sleep. So mark pwm_apply_state() with a might_sleep() to make callers aware. In the worst case this uncovers a valid atomic user, then we revert this patch and at least gained some more knowledge and then can work on a concept similar to gpio_get_value/gpio_get_value_cansleep. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/linux/pwm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 515e33978e97..e6dac95e4960 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -441,6 +441,7 @@ static inline void pwm_free(struct pwm_device *pwm) static inline int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state) { + might_sleep(); return -ENOTSUPP; } @@ -452,6 +453,7 @@ static inline int pwm_adjust_config(struct pwm_device *pwm) static inline int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns) { + might_sleep(); return -EINVAL; } @@ -464,11 +466,13 @@ static inline int pwm_capture(struct pwm_device *pwm, static inline int pwm_enable(struct pwm_device *pwm) { + might_sleep(); return -EINVAL; } static inline void pwm_disable(struct pwm_device *pwm) { + might_sleep(); } static inline int pwm_set_chip_data(struct pwm_device *pwm, void *data) -- cgit v1.2.3 From c9a20383578abd8f7fb8ba88f4c6d25b47924c34 Mon Sep 17 00:00:00 2001 From: Carlos de Paula Date: Mon, 30 Aug 2021 16:53:45 -0300 Subject: mfd: da9063: Add support for latest EA silicon revision This update adds new regmap to support the latest EA silicon which will be selected based on the chip and variant information read from the device. Signed-off-by: Carlos de Paula Reviewed-by: Adam Thomson Signed-off-by: Lee Jones --- include/linux/mfd/da9063/core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index fa7a43f02f27..8db52324f416 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -36,6 +36,7 @@ enum da9063_variant_codes { PMIC_DA9063_BB = 0x5, PMIC_DA9063_CA = 0x6, PMIC_DA9063_DA = 0x7, + PMIC_DA9063_EA = 0x8, }; /* Interrupts */ -- cgit v1.2.3 From ec14d90dee8ec6960324ae9f1116103efcde8a52 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 12 Oct 2021 17:39:35 +0200 Subject: mfd: tps65912: Make tps65912_device_exit() return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Up to now tps65912_device_exit() returns zero unconditionally. Make it return void instead which makes it easier to see in the callers that there is no error to handle. Also the return value of i2c and spi remove callbacks is ignored anyway. Signed-off-by: Uwe Kleine-König Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211012153945.2651412-11-u.kleine-koenig@pengutronix.de --- include/linux/mfd/tps65912.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index 7943e413deae..8a61386cb8c1 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -322,6 +322,6 @@ struct tps65912 { extern const struct regmap_config tps65912_regmap_config; int tps65912_device_init(struct tps65912 *tps); -int tps65912_device_exit(struct tps65912 *tps); +void tps65912_device_exit(struct tps65912 *tps); #endif /* __LINUX_MFD_TPS65912_H */ -- cgit v1.2.3 From 0cee0416563d7cac807c8f092941f3e37ede05db Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Tue, 19 Oct 2021 16:59:11 +0200 Subject: mfd: max77686: Correct tab-based alignment of register addresses Some lines have an extra tab, remove them for proper visual alignment as present on the rest of this file. Signed-off-by: Luca Ceresoli Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211019145919.7327-2-luca@lucaceresoli.net --- include/linux/mfd/max77686-private.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h index 833e578e051e..b1482b3cf353 100644 --- a/include/linux/mfd/max77686-private.h +++ b/include/linux/mfd/max77686-private.h @@ -133,35 +133,35 @@ enum max77686_pmic_reg { /* Reserved: 0x7A-0x7D */ MAX77686_REG_BBAT_CHG = 0x7E, - MAX77686_REG_32KHZ = 0x7F, + MAX77686_REG_32KHZ = 0x7F, MAX77686_REG_PMIC_END = 0x80, }; enum max77686_rtc_reg { - MAX77686_RTC_INT = 0x00, - MAX77686_RTC_INTM = 0x01, + MAX77686_RTC_INT = 0x00, + MAX77686_RTC_INTM = 0x01, MAX77686_RTC_CONTROLM = 0x02, MAX77686_RTC_CONTROL = 0x03, MAX77686_RTC_UPDATE0 = 0x04, /* Reserved: 0x5 */ MAX77686_WTSR_SMPL_CNTL = 0x06, - MAX77686_RTC_SEC = 0x07, - MAX77686_RTC_MIN = 0x08, - MAX77686_RTC_HOUR = 0x09, + MAX77686_RTC_SEC = 0x07, + MAX77686_RTC_MIN = 0x08, + MAX77686_RTC_HOUR = 0x09, MAX77686_RTC_WEEKDAY = 0x0A, - MAX77686_RTC_MONTH = 0x0B, - MAX77686_RTC_YEAR = 0x0C, - MAX77686_RTC_DATE = 0x0D, - MAX77686_ALARM1_SEC = 0x0E, - MAX77686_ALARM1_MIN = 0x0F, + MAX77686_RTC_MONTH = 0x0B, + MAX77686_RTC_YEAR = 0x0C, + MAX77686_RTC_DATE = 0x0D, + MAX77686_ALARM1_SEC = 0x0E, + MAX77686_ALARM1_MIN = 0x0F, MAX77686_ALARM1_HOUR = 0x10, MAX77686_ALARM1_WEEKDAY = 0x11, MAX77686_ALARM1_MONTH = 0x12, MAX77686_ALARM1_YEAR = 0x13, MAX77686_ALARM1_DATE = 0x14, - MAX77686_ALARM2_SEC = 0x15, - MAX77686_ALARM2_MIN = 0x16, + MAX77686_ALARM2_SEC = 0x15, + MAX77686_ALARM2_MIN = 0x16, MAX77686_ALARM2_HOUR = 0x17, MAX77686_ALARM2_WEEKDAY = 0x18, MAX77686_ALARM2_MONTH = 0x19, -- cgit v1.2.3 From b20cd02f7fef68ae395d9df0a9fb9edcf414b5a2 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 21 Oct 2021 22:22:58 +0300 Subject: mfd: tps80031: Remove driver Driver was upstreamed in 2013 and never got a user, remove it. Signed-off-by: Dmitry Osipenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211021192258.21968-4-digetx@gmail.com --- include/linux/mfd/tps80031.h | 637 ------------------------------------------- 1 file changed, 637 deletions(-) delete mode 100644 include/linux/mfd/tps80031.h (limited to 'include/linux') diff --git a/include/linux/mfd/tps80031.h b/include/linux/mfd/tps80031.h deleted file mode 100644 index 2c75c9c9318f..000000000000 --- a/include/linux/mfd/tps80031.h +++ /dev/null @@ -1,637 +0,0 @@ -/* - * tps80031.h -- TI TPS80031 and TI TPS80032 PMIC driver. - * - * Copyright (c) 2012, NVIDIA Corporation. - * - * Author: Laxman Dewangan - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind, - * whether express or implied; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA - * 02111-1307, USA - */ - -#ifndef __LINUX_MFD_TPS80031_H -#define __LINUX_MFD_TPS80031_H - -#include -#include - -/* Pull-ups/Pull-downs */ -#define TPS80031_CFG_INPUT_PUPD1 0xF0 -#define TPS80031_CFG_INPUT_PUPD2 0xF1 -#define TPS80031_CFG_INPUT_PUPD3 0xF2 -#define TPS80031_CFG_INPUT_PUPD4 0xF3 -#define TPS80031_CFG_LDO_PD1 0xF4 -#define TPS80031_CFG_LDO_PD2 0xF5 -#define TPS80031_CFG_SMPS_PD 0xF6 - -/* Real Time Clock */ -#define TPS80031_SECONDS_REG 0x00 -#define TPS80031_MINUTES_REG 0x01 -#define TPS80031_HOURS_REG 0x02 -#define TPS80031_DAYS_REG 0x03 -#define TPS80031_MONTHS_REG 0x04 -#define TPS80031_YEARS_REG 0x05 -#define TPS80031_WEEKS_REG 0x06 -#define TPS80031_ALARM_SECONDS_REG 0x08 -#define TPS80031_ALARM_MINUTES_REG 0x09 -#define TPS80031_ALARM_HOURS_REG 0x0A -#define TPS80031_ALARM_DAYS_REG 0x0B -#define TPS80031_ALARM_MONTHS_REG 0x0C -#define TPS80031_ALARM_YEARS_REG 0x0D -#define TPS80031_RTC_CTRL_REG 0x10 -#define TPS80031_RTC_STATUS_REG 0x11 -#define TPS80031_RTC_INTERRUPTS_REG 0x12 -#define TPS80031_RTC_COMP_LSB_REG 0x13 -#define TPS80031_RTC_COMP_MSB_REG 0x14 -#define TPS80031_RTC_RESET_STATUS_REG 0x16 - -/*PMC Master Module */ -#define TPS80031_PHOENIX_START_CONDITION 0x1F -#define TPS80031_PHOENIX_MSK_TRANSITION 0x20 -#define TPS80031_STS_HW_CONDITIONS 0x21 -#define TPS80031_PHOENIX_LAST_TURNOFF_STS 0x22 -#define TPS80031_VSYSMIN_LO_THRESHOLD 0x23 -#define TPS80031_VSYSMIN_HI_THRESHOLD 0x24 -#define TPS80031_PHOENIX_DEV_ON 0x25 -#define TPS80031_STS_PWR_GRP_STATE 0x27 -#define TPS80031_PH_CFG_VSYSLOW 0x28 -#define TPS80031_PH_STS_BOOT 0x29 -#define TPS80031_PHOENIX_SENS_TRANSITION 0x2A -#define TPS80031_PHOENIX_SEQ_CFG 0x2B -#define TPS80031_PRIMARY_WATCHDOG_CFG 0X2C -#define TPS80031_KEY_PRESS_DUR_CFG 0X2D -#define TPS80031_SMPS_LDO_SHORT_STS 0x2E - -/* PMC Slave Module - Broadcast */ -#define TPS80031_BROADCAST_ADDR_ALL 0x31 -#define TPS80031_BROADCAST_ADDR_REF 0x32 -#define TPS80031_BROADCAST_ADDR_PROV 0x33 -#define TPS80031_BROADCAST_ADDR_CLK_RST 0x34 - -/* PMC Slave Module SMPS Regulators */ -#define TPS80031_SMPS4_CFG_TRANS 0x41 -#define TPS80031_SMPS4_CFG_STATE 0x42 -#define TPS80031_SMPS4_CFG_VOLTAGE 0x44 -#define TPS80031_VIO_CFG_TRANS 0x47 -#define TPS80031_VIO_CFG_STATE 0x48 -#define TPS80031_VIO_CFG_FORCE 0x49 -#define TPS80031_VIO_CFG_VOLTAGE 0x4A -#define TPS80031_VIO_CFG_STEP 0x48 -#define TPS80031_SMPS1_CFG_TRANS 0x53 -#define TPS80031_SMPS1_CFG_STATE 0x54 -#define TPS80031_SMPS1_CFG_FORCE 0x55 -#define TPS80031_SMPS1_CFG_VOLTAGE 0x56 -#define TPS80031_SMPS1_CFG_STEP 0x57 -#define TPS80031_SMPS2_CFG_TRANS 0x59 -#define TPS80031_SMPS2_CFG_STATE 0x5A -#define TPS80031_SMPS2_CFG_FORCE 0x5B -#define TPS80031_SMPS2_CFG_VOLTAGE 0x5C -#define TPS80031_SMPS2_CFG_STEP 0x5D -#define TPS80031_SMPS3_CFG_TRANS 0x65 -#define TPS80031_SMPS3_CFG_STATE 0x66 -#define TPS80031_SMPS3_CFG_VOLTAGE 0x68 - -/* PMC Slave Module LDO Regulators */ -#define TPS80031_VANA_CFG_TRANS 0x81 -#define TPS80031_VANA_CFG_STATE 0x82 -#define TPS80031_VANA_CFG_VOLTAGE 0x83 -#define TPS80031_LDO2_CFG_TRANS 0x85 -#define TPS80031_LDO2_CFG_STATE 0x86 -#define TPS80031_LDO2_CFG_VOLTAGE 0x87 -#define TPS80031_LDO4_CFG_TRANS 0x89 -#define TPS80031_LDO4_CFG_STATE 0x8A -#define TPS80031_LDO4_CFG_VOLTAGE 0x8B -#define TPS80031_LDO3_CFG_TRANS 0x8D -#define TPS80031_LDO3_CFG_STATE 0x8E -#define TPS80031_LDO3_CFG_VOLTAGE 0x8F -#define TPS80031_LDO6_CFG_TRANS 0x91 -#define TPS80031_LDO6_CFG_STATE 0x92 -#define TPS80031_LDO6_CFG_VOLTAGE 0x93 -#define TPS80031_LDOLN_CFG_TRANS 0x95 -#define TPS80031_LDOLN_CFG_STATE 0x96 -#define TPS80031_LDOLN_CFG_VOLTAGE 0x97 -#define TPS80031_LDO5_CFG_TRANS 0x99 -#define TPS80031_LDO5_CFG_STATE 0x9A -#define TPS80031_LDO5_CFG_VOLTAGE 0x9B -#define TPS80031_LDO1_CFG_TRANS 0x9D -#define TPS80031_LDO1_CFG_STATE 0x9E -#define TPS80031_LDO1_CFG_VOLTAGE 0x9F -#define TPS80031_LDOUSB_CFG_TRANS 0xA1 -#define TPS80031_LDOUSB_CFG_STATE 0xA2 -#define TPS80031_LDOUSB_CFG_VOLTAGE 0xA3 -#define TPS80031_LDO7_CFG_TRANS 0xA5 -#define TPS80031_LDO7_CFG_STATE 0xA6 -#define TPS80031_LDO7_CFG_VOLTAGE 0xA7 - -/* PMC Slave Module External Control */ -#define TPS80031_REGEN1_CFG_TRANS 0xAE -#define TPS80031_REGEN1_CFG_STATE 0xAF -#define TPS80031_REGEN2_CFG_TRANS 0xB1 -#define TPS80031_REGEN2_CFG_STATE 0xB2 -#define TPS80031_SYSEN_CFG_TRANS 0xB4 -#define TPS80031_SYSEN_CFG_STATE 0xB5 - -/* PMC Slave Module Internal Control */ -#define TPS80031_NRESPWRON_CFG_TRANS 0xB7 -#define TPS80031_NRESPWRON_CFG_STATE 0xB8 -#define TPS80031_CLK32KAO_CFG_TRANS 0xBA -#define TPS80031_CLK32KAO_CFG_STATE 0xBB -#define TPS80031_CLK32KG_CFG_TRANS 0xBD -#define TPS80031_CLK32KG_CFG_STATE 0xBE -#define TPS80031_CLK32KAUDIO_CFG_TRANS 0xC0 -#define TPS80031_CLK32KAUDIO_CFG_STATE 0xC1 -#define TPS80031_VRTC_CFG_TRANS 0xC3 -#define TPS80031_VRTC_CFG_STATE 0xC4 -#define TPS80031_BIAS_CFG_TRANS 0xC6 -#define TPS80031_BIAS_CFG_STATE 0xC7 -#define TPS80031_VSYSMIN_HI_CFG_TRANS 0xC9 -#define TPS80031_VSYSMIN_HI_CFG_STATE 0xCA -#define TPS80031_RC6MHZ_CFG_TRANS 0xCC -#define TPS80031_RC6MHZ_CFG_STATE 0xCD -#define TPS80031_TMP_CFG_TRANS 0xCF -#define TPS80031_TMP_CFG_STATE 0xD0 - -/* PMC Slave Module resources assignment */ -#define TPS80031_PREQ1_RES_ASS_A 0xD7 -#define TPS80031_PREQ1_RES_ASS_B 0xD8 -#define TPS80031_PREQ1_RES_ASS_C 0xD9 -#define TPS80031_PREQ2_RES_ASS_A 0xDA -#define TPS80031_PREQ2_RES_ASS_B 0xDB -#define TPS80031_PREQ2_RES_ASS_C 0xDC -#define TPS80031_PREQ3_RES_ASS_A 0xDD -#define TPS80031_PREQ3_RES_ASS_B 0xDE -#define TPS80031_PREQ3_RES_ASS_C 0xDF - -/* PMC Slave Module Miscellaneous */ -#define TPS80031_SMPS_OFFSET 0xE0 -#define TPS80031_SMPS_MULT 0xE3 -#define TPS80031_MISC1 0xE4 -#define TPS80031_MISC2 0xE5 -#define TPS80031_BBSPOR_CFG 0xE6 -#define TPS80031_TMP_CFG 0xE7 - -/* Battery Charging Controller and Indicator LED */ -#define TPS80031_CONTROLLER_CTRL2 0xDA -#define TPS80031_CONTROLLER_VSEL_COMP 0xDB -#define TPS80031_CHARGERUSB_VSYSREG 0xDC -#define TPS80031_CHARGERUSB_VICHRG_PC 0xDD -#define TPS80031_LINEAR_CHRG_STS 0xDE -#define TPS80031_CONTROLLER_INT_MASK 0xE0 -#define TPS80031_CONTROLLER_CTRL1 0xE1 -#define TPS80031_CONTROLLER_WDG 0xE2 -#define TPS80031_CONTROLLER_STAT1 0xE3 -#define TPS80031_CHARGERUSB_INT_STATUS 0xE4 -#define TPS80031_CHARGERUSB_INT_MASK 0xE5 -#define TPS80031_CHARGERUSB_STATUS_INT1 0xE6 -#define TPS80031_CHARGERUSB_STATUS_INT2 0xE7 -#define TPS80031_CHARGERUSB_CTRL1 0xE8 -#define TPS80031_CHARGERUSB_CTRL2 0xE9 -#define TPS80031_CHARGERUSB_CTRL3 0xEA -#define TPS80031_CHARGERUSB_STAT1 0xEB -#define TPS80031_CHARGERUSB_VOREG 0xEC -#define TPS80031_CHARGERUSB_VICHRG 0xED -#define TPS80031_CHARGERUSB_CINLIMIT 0xEE -#define TPS80031_CHARGERUSB_CTRLLIMIT1 0xEF -#define TPS80031_CHARGERUSB_CTRLLIMIT2 0xF0 -#define TPS80031_LED_PWM_CTRL1 0xF4 -#define TPS80031_LED_PWM_CTRL2 0xF5 - -/* USB On-The-Go */ -#define TPS80031_BACKUP_REG 0xFA -#define TPS80031_USB_VENDOR_ID_LSB 0x00 -#define TPS80031_USB_VENDOR_ID_MSB 0x01 -#define TPS80031_USB_PRODUCT_ID_LSB 0x02 -#define TPS80031_USB_PRODUCT_ID_MSB 0x03 -#define TPS80031_USB_VBUS_CTRL_SET 0x04 -#define TPS80031_USB_VBUS_CTRL_CLR 0x05 -#define TPS80031_USB_ID_CTRL_SET 0x06 -#define TPS80031_USB_ID_CTRL_CLR 0x07 -#define TPS80031_USB_VBUS_INT_SRC 0x08 -#define TPS80031_USB_VBUS_INT_LATCH_SET 0x09 -#define TPS80031_USB_VBUS_INT_LATCH_CLR 0x0A -#define TPS80031_USB_VBUS_INT_EN_LO_SET 0x0B -#define TPS80031_USB_VBUS_INT_EN_LO_CLR 0x0C -#define TPS80031_USB_VBUS_INT_EN_HI_SET 0x0D -#define TPS80031_USB_VBUS_INT_EN_HI_CLR 0x0E -#define TPS80031_USB_ID_INT_SRC 0x0F -#define TPS80031_USB_ID_INT_LATCH_SET 0x10 -#define TPS80031_USB_ID_INT_LATCH_CLR 0x11 -#define TPS80031_USB_ID_INT_EN_LO_SET 0x12 -#define TPS80031_USB_ID_INT_EN_LO_CLR 0x13 -#define TPS80031_USB_ID_INT_EN_HI_SET 0x14 -#define TPS80031_USB_ID_INT_EN_HI_CLR 0x15 -#define TPS80031_USB_OTG_ADP_CTRL 0x16 -#define TPS80031_USB_OTG_ADP_HIGH 0x17 -#define TPS80031_USB_OTG_ADP_LOW 0x18 -#define TPS80031_USB_OTG_ADP_RISE 0x19 -#define TPS80031_USB_OTG_REVISION 0x1A - -/* Gas Gauge */ -#define TPS80031_FG_REG_00 0xC0 -#define TPS80031_FG_REG_01 0xC1 -#define TPS80031_FG_REG_02 0xC2 -#define TPS80031_FG_REG_03 0xC3 -#define TPS80031_FG_REG_04 0xC4 -#define TPS80031_FG_REG_05 0xC5 -#define TPS80031_FG_REG_06 0xC6 -#define TPS80031_FG_REG_07 0xC7 -#define TPS80031_FG_REG_08 0xC8 -#define TPS80031_FG_REG_09 0xC9 -#define TPS80031_FG_REG_10 0xCA -#define TPS80031_FG_REG_11 0xCB - -/* General Purpose ADC */ -#define TPS80031_GPADC_CTRL 0x2E -#define TPS80031_GPADC_CTRL2 0x2F -#define TPS80031_RTSELECT_LSB 0x32 -#define TPS80031_RTSELECT_ISB 0x33 -#define TPS80031_RTSELECT_MSB 0x34 -#define TPS80031_GPSELECT_ISB 0x35 -#define TPS80031_CTRL_P1 0x36 -#define TPS80031_RTCH0_LSB 0x37 -#define TPS80031_RTCH0_MSB 0x38 -#define TPS80031_RTCH1_LSB 0x39 -#define TPS80031_RTCH1_MSB 0x3A -#define TPS80031_GPCH0_LSB 0x3B -#define TPS80031_GPCH0_MSB 0x3C - -/* SIM, MMC and Battery Detection */ -#define TPS80031_SIMDEBOUNCING 0xEB -#define TPS80031_SIMCTRL 0xEC -#define TPS80031_MMCDEBOUNCING 0xED -#define TPS80031_MMCCTRL 0xEE -#define TPS80031_BATDEBOUNCING 0xEF - -/* Vibrator Driver and PWMs */ -#define TPS80031_VIBCTRL 0x9B -#define TPS80031_VIBMODE 0x9C -#define TPS80031_PWM1ON 0xBA -#define TPS80031_PWM1OFF 0xBB -#define TPS80031_PWM2ON 0xBD -#define TPS80031_PWM2OFF 0xBE - -/* Control Interface */ -#define TPS80031_INT_STS_A 0xD0 -#define TPS80031_INT_STS_B 0xD1 -#define TPS80031_INT_STS_C 0xD2 -#define TPS80031_INT_MSK_LINE_A 0xD3 -#define TPS80031_INT_MSK_LINE_B 0xD4 -#define TPS80031_INT_MSK_LINE_C 0xD5 -#define TPS80031_INT_MSK_STS_A 0xD6 -#define TPS80031_INT_MSK_STS_B 0xD7 -#define TPS80031_INT_MSK_STS_C 0xD8 -#define TPS80031_TOGGLE1 0x90 -#define TPS80031_TOGGLE2 0x91 -#define TPS80031_TOGGLE3 0x92 -#define TPS80031_PWDNSTATUS1 0x93 -#define TPS80031_PWDNSTATUS2 0x94 -#define TPS80031_VALIDITY0 0x17 -#define TPS80031_VALIDITY1 0x18 -#define TPS80031_VALIDITY2 0x19 -#define TPS80031_VALIDITY3 0x1A -#define TPS80031_VALIDITY4 0x1B -#define TPS80031_VALIDITY5 0x1C -#define TPS80031_VALIDITY6 0x1D -#define TPS80031_VALIDITY7 0x1E - -/* Version number related register */ -#define TPS80031_JTAGVERNUM 0x87 -#define TPS80031_EPROM_REV 0xDF - -/* GPADC Trimming Bits. */ -#define TPS80031_GPADC_TRIM0 0xCC -#define TPS80031_GPADC_TRIM1 0xCD -#define TPS80031_GPADC_TRIM2 0xCE -#define TPS80031_GPADC_TRIM3 0xCF -#define TPS80031_GPADC_TRIM4 0xD0 -#define TPS80031_GPADC_TRIM5 0xD1 -#define TPS80031_GPADC_TRIM6 0xD2 -#define TPS80031_GPADC_TRIM7 0xD3 -#define TPS80031_GPADC_TRIM8 0xD4 -#define TPS80031_GPADC_TRIM9 0xD5 -#define TPS80031_GPADC_TRIM10 0xD6 -#define TPS80031_GPADC_TRIM11 0xD7 -#define TPS80031_GPADC_TRIM12 0xD8 -#define TPS80031_GPADC_TRIM13 0xD9 -#define TPS80031_GPADC_TRIM14 0xDA -#define TPS80031_GPADC_TRIM15 0xDB -#define TPS80031_GPADC_TRIM16 0xDC -#define TPS80031_GPADC_TRIM17 0xDD -#define TPS80031_GPADC_TRIM18 0xDE - -/* TPS80031_CONTROLLER_STAT1 bit fields */ -#define TPS80031_CONTROLLER_STAT1_BAT_TEMP 0 -#define TPS80031_CONTROLLER_STAT1_BAT_REMOVED 1 -#define TPS80031_CONTROLLER_STAT1_VBUS_DET 2 -#define TPS80031_CONTROLLER_STAT1_VAC_DET 3 -#define TPS80031_CONTROLLER_STAT1_FAULT_WDG 4 -#define TPS80031_CONTROLLER_STAT1_LINCH_GATED 6 -/* TPS80031_CONTROLLER_INT_MASK bit filed */ -#define TPS80031_CONTROLLER_INT_MASK_MVAC_DET 0 -#define TPS80031_CONTROLLER_INT_MASK_MVBUS_DET 1 -#define TPS80031_CONTROLLER_INT_MASK_MBAT_TEMP 2 -#define TPS80031_CONTROLLER_INT_MASK_MFAULT_WDG 3 -#define TPS80031_CONTROLLER_INT_MASK_MBAT_REMOVED 4 -#define TPS80031_CONTROLLER_INT_MASK_MLINCH_GATED 5 - -#define TPS80031_CHARGE_CONTROL_SUB_INT_MASK 0x3F - -/* TPS80031_PHOENIX_DEV_ON bit field */ -#define TPS80031_DEVOFF 0x1 - -#define TPS80031_EXT_CONTROL_CFG_TRANS 0 -#define TPS80031_EXT_CONTROL_CFG_STATE 1 - -/* State register field */ -#define TPS80031_STATE_OFF 0x00 -#define TPS80031_STATE_ON 0x01 -#define TPS80031_STATE_MASK 0x03 - -/* Trans register field */ -#define TPS80031_TRANS_ACTIVE_OFF 0x00 -#define TPS80031_TRANS_ACTIVE_ON 0x01 -#define TPS80031_TRANS_ACTIVE_MASK 0x03 -#define TPS80031_TRANS_SLEEP_OFF 0x00 -#define TPS80031_TRANS_SLEEP_ON 0x04 -#define TPS80031_TRANS_SLEEP_MASK 0x0C -#define TPS80031_TRANS_OFF_OFF 0x00 -#define TPS80031_TRANS_OFF_ACTIVE 0x10 -#define TPS80031_TRANS_OFF_MASK 0x30 - -#define TPS80031_EXT_PWR_REQ (TPS80031_PWR_REQ_INPUT_PREQ1 | \ - TPS80031_PWR_REQ_INPUT_PREQ2 | \ - TPS80031_PWR_REQ_INPUT_PREQ3) - -/* TPS80031_BBSPOR_CFG bit field */ -#define TPS80031_BBSPOR_CHG_EN 0x8 -#define TPS80031_MAX_REGISTER 0xFF - -struct i2c_client; - -/* Supported chips */ -enum chips { - TPS80031 = 0x00000001, - TPS80032 = 0x00000002, -}; - -enum { - TPS80031_INT_PWRON, - TPS80031_INT_RPWRON, - TPS80031_INT_SYS_VLOW, - TPS80031_INT_RTC_ALARM, - TPS80031_INT_RTC_PERIOD, - TPS80031_INT_HOT_DIE, - TPS80031_INT_VXX_SHORT, - TPS80031_INT_SPDURATION, - TPS80031_INT_WATCHDOG, - TPS80031_INT_BAT, - TPS80031_INT_SIM, - TPS80031_INT_MMC, - TPS80031_INT_RES, - TPS80031_INT_GPADC_RT, - TPS80031_INT_GPADC_SW2_EOC, - TPS80031_INT_CC_AUTOCAL, - TPS80031_INT_ID_WKUP, - TPS80031_INT_VBUSS_WKUP, - TPS80031_INT_ID, - TPS80031_INT_VBUS, - TPS80031_INT_CHRG_CTRL, - TPS80031_INT_EXT_CHRG, - TPS80031_INT_INT_CHRG, - TPS80031_INT_RES2, - TPS80031_INT_BAT_TEMP_OVRANGE, - TPS80031_INT_BAT_REMOVED, - TPS80031_INT_VBUS_DET, - TPS80031_INT_VAC_DET, - TPS80031_INT_FAULT_WDG, - TPS80031_INT_LINCH_GATED, - - /* Last interrupt id to get the end number */ - TPS80031_INT_NR, -}; - -/* TPS80031 Slave IDs */ -#define TPS80031_NUM_SLAVES 4 -#define TPS80031_SLAVE_ID0 0 -#define TPS80031_SLAVE_ID1 1 -#define TPS80031_SLAVE_ID2 2 -#define TPS80031_SLAVE_ID3 3 - -/* TPS80031 I2C addresses */ -#define TPS80031_I2C_ID0_ADDR 0x12 -#define TPS80031_I2C_ID1_ADDR 0x48 -#define TPS80031_I2C_ID2_ADDR 0x49 -#define TPS80031_I2C_ID3_ADDR 0x4A - -enum { - TPS80031_REGULATOR_VIO, - TPS80031_REGULATOR_SMPS1, - TPS80031_REGULATOR_SMPS2, - TPS80031_REGULATOR_SMPS3, - TPS80031_REGULATOR_SMPS4, - TPS80031_REGULATOR_VANA, - TPS80031_REGULATOR_LDO1, - TPS80031_REGULATOR_LDO2, - TPS80031_REGULATOR_LDO3, - TPS80031_REGULATOR_LDO4, - TPS80031_REGULATOR_LDO5, - TPS80031_REGULATOR_LDO6, - TPS80031_REGULATOR_LDO7, - TPS80031_REGULATOR_LDOLN, - TPS80031_REGULATOR_LDOUSB, - TPS80031_REGULATOR_VBUS, - TPS80031_REGULATOR_REGEN1, - TPS80031_REGULATOR_REGEN2, - TPS80031_REGULATOR_SYSEN, - TPS80031_REGULATOR_MAX, -}; - -/* Different configurations for the rails */ -enum { - /* USBLDO input selection */ - TPS80031_USBLDO_INPUT_VSYS = 0x00000001, - TPS80031_USBLDO_INPUT_PMID = 0x00000002, - - /* LDO3 output mode */ - TPS80031_LDO3_OUTPUT_VIB = 0x00000004, - - /* VBUS configuration */ - TPS80031_VBUS_DISCHRG_EN_PDN = 0x00000004, - TPS80031_VBUS_SW_ONLY = 0x00000008, - TPS80031_VBUS_SW_N_ID = 0x00000010, -}; - -/* External controls requests */ -enum tps80031_ext_control { - TPS80031_PWR_REQ_INPUT_NONE = 0x00000000, - TPS80031_PWR_REQ_INPUT_PREQ1 = 0x00000001, - TPS80031_PWR_REQ_INPUT_PREQ2 = 0x00000002, - TPS80031_PWR_REQ_INPUT_PREQ3 = 0x00000004, - TPS80031_PWR_OFF_ON_SLEEP = 0x00000008, - TPS80031_PWR_ON_ON_SLEEP = 0x00000010, -}; - -enum tps80031_pupd_pins { - TPS80031_PREQ1 = 0, - TPS80031_PREQ2A, - TPS80031_PREQ2B, - TPS80031_PREQ2C, - TPS80031_PREQ3, - TPS80031_NRES_WARM, - TPS80031_PWM_FORCE, - TPS80031_CHRG_EXT_CHRG_STATZ, - TPS80031_SIM, - TPS80031_MMC, - TPS80031_GPADC_START, - TPS80031_DVSI2C_SCL, - TPS80031_DVSI2C_SDA, - TPS80031_CTLI2C_SCL, - TPS80031_CTLI2C_SDA, -}; - -enum tps80031_pupd_settings { - TPS80031_PUPD_NORMAL, - TPS80031_PUPD_PULLDOWN, - TPS80031_PUPD_PULLUP, -}; - -struct tps80031 { - struct device *dev; - unsigned long chip_info; - int es_version; - struct i2c_client *clients[TPS80031_NUM_SLAVES]; - struct regmap *regmap[TPS80031_NUM_SLAVES]; - struct regmap_irq_chip_data *irq_data; -}; - -struct tps80031_pupd_init_data { - int input_pin; - int setting; -}; - -/* - * struct tps80031_regulator_platform_data - tps80031 regulator platform data. - * - * @reg_init_data: The regulator init data. - * @ext_ctrl_flag: External control flag for sleep/power request control. - * @config_flags: Configuration flag to configure the rails. - * It should be ORed of config enums. - */ - -struct tps80031_regulator_platform_data { - struct regulator_init_data *reg_init_data; - unsigned int ext_ctrl_flag; - unsigned int config_flags; -}; - -struct tps80031_platform_data { - int irq_base; - bool use_power_off; - struct tps80031_pupd_init_data *pupd_init_data; - int pupd_init_data_size; - struct tps80031_regulator_platform_data - *regulator_pdata[TPS80031_REGULATOR_MAX]; -}; - -static inline int tps80031_write(struct device *dev, int sid, - int reg, uint8_t val) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_write(tps80031->regmap[sid], reg, val); -} - -static inline int tps80031_writes(struct device *dev, int sid, int reg, - int len, uint8_t *val) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_bulk_write(tps80031->regmap[sid], reg, val, len); -} - -static inline int tps80031_read(struct device *dev, int sid, - int reg, uint8_t *val) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - unsigned int ival; - int ret; - - ret = regmap_read(tps80031->regmap[sid], reg, &ival); - if (ret < 0) { - dev_err(dev, "failed reading from reg 0x%02x\n", reg); - return ret; - } - - *val = ival; - return ret; -} - -static inline int tps80031_reads(struct device *dev, int sid, - int reg, int len, uint8_t *val) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_bulk_read(tps80031->regmap[sid], reg, val, len); -} - -static inline int tps80031_set_bits(struct device *dev, int sid, - int reg, uint8_t bit_mask) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_update_bits(tps80031->regmap[sid], reg, - bit_mask, bit_mask); -} - -static inline int tps80031_clr_bits(struct device *dev, int sid, - int reg, uint8_t bit_mask) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_update_bits(tps80031->regmap[sid], reg, bit_mask, 0); -} - -static inline int tps80031_update(struct device *dev, int sid, - int reg, uint8_t val, uint8_t mask) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_update_bits(tps80031->regmap[sid], reg, mask, val); -} - -static inline unsigned long tps80031_get_chip_info(struct device *dev) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return tps80031->chip_info; -} - -static inline int tps80031_get_pmu_version(struct device *dev) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return tps80031->es_version; -} - -static inline int tps80031_irq_get_virq(struct device *dev, int irq) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_irq_get_virq(tps80031->irq_data, irq); -} - -extern int tps80031_ext_power_req_config(struct device *dev, - unsigned long ext_ctrl_flag, int preq_bit, - int state_reg_add, int trans_reg_add); -#endif /*__LINUX_MFD_TPS80031_H */ -- cgit v1.2.3 From d755ad8dc752d44545613ea04d660aed674e540d Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:00 -0400 Subject: NFS: Create a new nfs_alloc_fattr_with_label() function For creating fattrs with the label field already allocated for us. I also update nfs_free_fattr() to free the label in the end. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 739ca1ef934f..88c3aed8ad39 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -426,9 +426,22 @@ extern void nfs_fattr_set_barrier(struct nfs_fattr *fattr); extern unsigned long nfs_inc_attr_generation_counter(void); extern struct nfs_fattr *nfs_alloc_fattr(void); +extern struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server); + +static inline void nfs4_label_free(struct nfs4_label *label) +{ +#ifdef CONFIG_NFS_V4_SECURITY_LABEL + if (label) { + kfree(label->label); + kfree(label); + } +#endif +} static inline void nfs_free_fattr(const struct nfs_fattr *fattr) { + if (fattr) + nfs4_label_free(fattr->label); kfree(fattr); } -- cgit v1.2.3 From b1db9a401d464d526d5941f0544e7c9ea37fa731 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:01 -0400 Subject: NFS: Remove the nfs4_label from the nfs_entry struct And instead allocate the fattr using nfs_alloc_fattr_with_label() Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e9698b6278a5..9960f6628066 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -753,7 +753,6 @@ struct nfs_entry { int eof; struct nfs_fh * fh; struct nfs_fattr * fattr; - struct nfs4_label *label; unsigned char d_type; struct nfs_server * server; }; -- cgit v1.2.3 From 68be1742c22983558f0f148a4467eb9127d56b86 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:02 -0400 Subject: NFS: Remove the nfs4_label from the nfs4_create_res struct Instead, use the label embedded in the attached fattr. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9960f6628066..5aba81b74c98 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1040,7 +1040,6 @@ struct nfs4_create_res { const struct nfs_server * server; struct nfs_fh * fh; struct nfs_fattr * fattr; - struct nfs4_label *label; struct nfs4_change_info dir_cinfo; }; -- cgit v1.2.3 From aa7ca3b2de190675543d84adaa1ff74e7867c76f Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:03 -0400 Subject: NFS: Remove the nfs4_label from the nfs4_link_res struct Again, use the fattr's label field instead. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5aba81b74c98..d55bf3fd5167 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1079,7 +1079,6 @@ struct nfs4_link_res { struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fattr * fattr; - struct nfs4_label *label; struct nfs4_change_info cinfo; struct nfs_fattr * dir_attr; }; -- cgit v1.2.3 From 9558a007dbc383d48e7f5a123d0b5ff656c71068 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:04 -0400 Subject: NFS: Remove the label from the nfs4_lookup_res struct And usethe fattr's label field instead. I also adjust function calls to remove labels along the way. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d55bf3fd5167..95219d5a8668 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1095,7 +1095,6 @@ struct nfs4_lookup_res { const struct nfs_server * server; struct nfs_fattr * fattr; struct nfs_fh * fh; - struct nfs4_label *label; }; struct nfs4_lookupp_arg { @@ -1740,8 +1739,7 @@ struct nfs_rpc_ops { int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); int (*lookup) (struct inode *, struct dentry *, - struct nfs_fh *, struct nfs_fattr *, - struct nfs4_label *); + struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); int (*access) (struct inode *, struct nfs_access_entry *); -- cgit v1.2.3 From ba4bc8dc4d937df2b407393435a302550be0ad82 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:05 -0400 Subject: NFS: Remove the nfs4_label from the nfs4_lookupp_res struct Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 95219d5a8668..f0a685d9b8bd 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1108,7 +1108,6 @@ struct nfs4_lookupp_res { const struct nfs_server *server; struct nfs_fattr *fattr; struct nfs_fh *fh; - struct nfs4_label *label; }; struct nfs4_lookup_root_arg { @@ -1741,7 +1740,7 @@ struct nfs_rpc_ops { int (*lookup) (struct inode *, struct dentry *, struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *); + struct nfs_fattr *); int (*access) (struct inode *, struct nfs_access_entry *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); -- cgit v1.2.3 From 76baa2b29c7161bc65a3051d311297b7d7fc827a Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:06 -0400 Subject: NFS: Remove the f_label from the nfs4_opendata and nfs_openres Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index f0a685d9b8bd..cb28e01ea41e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -488,7 +488,6 @@ struct nfs_openres { struct nfs4_change_info cinfo; __u32 rflags; struct nfs_fattr * f_attr; - struct nfs4_label *f_label; struct nfs_seqid * seqid; const struct nfs_server *server; fmode_t delegation_type; -- cgit v1.2.3 From 2ef61e0eaa333e4e9c348c41a4b7abfb34b8736d Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:07 -0400 Subject: NFS: Remove the nfs4_label from the nfs4_getattr_res Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index cb28e01ea41e..817f1bf5f187 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1063,7 +1063,6 @@ struct nfs4_getattr_res { struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fattr * fattr; - struct nfs4_label *label; }; struct nfs4_link_arg { @@ -1732,8 +1731,7 @@ struct nfs_rpc_ops { int (*submount) (struct fs_context *, struct nfs_server *); int (*try_get_tree) (struct fs_context *); int (*getattr) (struct nfs_server *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *, - struct inode *); + struct nfs_fattr *, struct inode *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); int (*lookup) (struct inode *, struct dentry *, -- cgit v1.2.3 From 1b00ad657997c8984a9e627a3bd37ea14f20beb2 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:08 -0400 Subject: NFS: Remove the nfs4_label from the nfs_setattrres Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 817f1bf5f187..967a0098f0a9 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -832,7 +832,6 @@ struct nfs_getaclres { struct nfs_setattrres { struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; - struct nfs4_label *label; const struct nfs_server * server; }; -- cgit v1.2.3 From d91bfc46426d3d772fc0d9d165e3435fd0f0a79e Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:09 -0400 Subject: NFS: Remove the nfs4_label argument from nfs_instantiate() Pull the label from the fattr instead. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 88c3aed8ad39..a8a9b71aeea6 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -532,7 +532,7 @@ extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, - struct nfs_fattr *fattr, struct nfs4_label *label); + struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, -- cgit v1.2.3 From cc6f32989c3202349b90edde0c4702b098410fe8 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:10 -0400 Subject: NFS: Remove the nfs4_label argument from nfs_add_or_obtain() Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a8a9b71aeea6..6eda001b306b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -529,8 +529,7 @@ extern void nfs_set_verifier(struct dentry * dentry, unsigned long verf); extern void nfs_clear_verifier_delegated(struct inode *inode); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, - struct nfs_fh *fh, struct nfs_fattr *fattr, - struct nfs4_label *label); + struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); -- cgit v1.2.3 From cf7ab00aabbf9c8f1ec72edff15849ddc23aa6a7 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:11 -0400 Subject: NFS: Remove the nfs4_label argument from nfs_fhget() Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 6eda001b306b..c36c6a559fc9 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -388,7 +388,7 @@ extern void nfs_zap_caches(struct inode *); extern void nfs_set_inode_stale(struct inode *inode); extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *); + struct nfs_fattr *); struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); -- cgit v1.2.3 From dd225cb3b02b827271a2284f89102fc81efcbf6f Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:12 -0400 Subject: NFS: Remove the nfs4_label argument from nfs_setsecurity Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c36c6a559fc9..05f249f20f55 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -409,8 +409,7 @@ extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *map extern int nfs_revalidate_mapping_rcu(struct inode *inode); extern int nfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); -extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, - struct nfs4_label *label); +extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode); -- cgit v1.2.3 From 3990ed4c426652fcd469f8c9dc08156294b36c28 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 5 Nov 2021 18:40:14 -0700 Subject: bpf: Stop caching subprog index in the bpf_pseudo_func insn This patch is to fix an out-of-bound access issue when jit-ing the bpf_pseudo_func insn (i.e. ld_imm64 with src_reg == BPF_PSEUDO_FUNC) In jit_subprog(), it currently reuses the subprog index cached in insn[1].imm. This subprog index is an index into a few array related to subprogs. For example, in jit_subprog(), it is an index to the newly allocated 'struct bpf_prog **func' array. The subprog index was cached in insn[1].imm after add_subprog(). However, this could become outdated (and too big in this case) if some subprogs are completely removed during dead code elimination (in adjust_subprog_starts_after_remove). The cached index in insn[1].imm is not updated accordingly and causing out-of-bound issue in the later jit_subprog(). Unlike bpf_pseudo_'func' insn, the current bpf_pseudo_'call' insn is handling the DCE properly by calling find_subprog(insn->imm) to figure out the index instead of caching the subprog index. The existing bpf_adj_branches() will adjust the insn->imm whenever insn is added or removed. Instead of having two ways handling subprog index, this patch is to make bpf_pseudo_func works more like bpf_pseudo_call. First change is to stop caching the subprog index result in insn[1].imm after add_subprog(). The verification process will use find_subprog(insn->imm) to figure out the subprog index. Second change is in bpf_adj_branches() and have it to adjust the insn->imm for the bpf_pseudo_func insn also whenever insn is added or removed. Third change is in jit_subprog(). Like the bpf_pseudo_call handling, bpf_pseudo_func temporarily stores the find_subprog() result in insn->off. It is fine because the prog's insn has been finalized at this point. insn->off will be reset back to 0 later to avoid confusing the userspace prog dump tool. Fixes: 69c087ba6225 ("bpf: Add bpf_for_each_map_elem() helper") Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211106014014.651018-1-kafai@fb.com --- include/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2be6dfd68df9..f715e8863f4d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -484,6 +484,12 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +static inline bool bpf_pseudo_func(const struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && + insn->src_reg == BPF_PSEUDO_FUNC; +} + struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); -- cgit v1.2.3 From 8587ca6f34152ea650bad4b2db68456601159024 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 5 Nov 2021 13:35:07 -0700 Subject: mm: move kvmalloc-related functions to slab.h Not all files in the kernel should include mm.h. Migrating callers from kmalloc to kvmalloc is easier if the kvmalloc functions are in slab.h. [akpm@linux-foundation.org: move the new kvrealloc() also] [akpm@linux-foundation.org: drivers/hwmon/occ/p9_sbe.c needs slab.h] Link: https://lkml.kernel.org/r/20210622215757.3525604-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Pekka Enberg Cc: Christoph Lameter Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 34 ---------------------------------- include/linux/slab.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 73a52aba448f..32b2ecc47408 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -799,40 +799,6 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif -extern void *kvmalloc_node(size_t size, gfp_t flags, int node); -static inline void *kvmalloc(size_t size, gfp_t flags) -{ - return kvmalloc_node(size, flags, NUMA_NO_NODE); -} -static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) -{ - return kvmalloc_node(size, flags | __GFP_ZERO, node); -} -static inline void *kvzalloc(size_t size, gfp_t flags) -{ - return kvmalloc(size, flags | __GFP_ZERO); -} - -static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) -{ - size_t bytes; - - if (unlikely(check_mul_overflow(n, size, &bytes))) - return NULL; - - return kvmalloc(bytes, flags); -} - -static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) -{ - return kvmalloc_array(n, size, flags | __GFP_ZERO); -} - -extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, - gfp_t flags); -extern void kvfree(const void *addr); -extern void kvfree_sensitive(const void *addr, size_t len); - static inline int head_compound_mapcount(struct page *head) { return atomic_read(compound_mapcount_ptr(head)) + 1; diff --git a/include/linux/slab.h b/include/linux/slab.h index 083f3ce550bc..c0d46b6fa12a 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -732,6 +732,40 @@ static inline void *kzalloc_node(size_t size, gfp_t flags, int node) return kmalloc_node(size, flags | __GFP_ZERO, node); } +extern void *kvmalloc_node(size_t size, gfp_t flags, int node); +static inline void *kvmalloc(size_t size, gfp_t flags) +{ + return kvmalloc_node(size, flags, NUMA_NO_NODE); +} +static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) +{ + return kvmalloc_node(size, flags | __GFP_ZERO, node); +} +static inline void *kvzalloc(size_t size, gfp_t flags) +{ + return kvmalloc(size, flags | __GFP_ZERO); +} + +static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +{ + size_t bytes; + + if (unlikely(check_mul_overflow(n, size, &bytes))) + return NULL; + + return kvmalloc(bytes, flags); +} + +static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) +{ + return kvmalloc_array(n, size, flags | __GFP_ZERO); +} + +extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, + gfp_t flags); +extern void kvfree(const void *addr); +extern void kvfree_sensitive(const void *addr, size_t len); + unsigned int kmem_cache_size(struct kmem_cache *s); void __init kmem_cache_init_late(void); -- cgit v1.2.3 From b47291ef02b0bee85ffb7efd6c336060ad1fe1a4 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 5 Nov 2021 13:35:17 -0700 Subject: mm, slub: change percpu partial accounting from objects to pages With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of partial slabs that can be promoted to cpu slab when the previous one is depleted, without accessing the shared partial list. A slab can be added to this list by 1) refill of an empty list from get_partial_node() - once we really have to access the shared partial list, we acquire multiple slabs to amortize the cost of locking, and 2) first free to a previously full slab - instead of putting the slab on a shared partial list, we can more cheaply freeze it and put it on the per-cpu list. To control how large a percpu partial list can grow for a kmem cache, set_cpu_partial() calculates a target number of free objects on each cpu's percpu partial list, and this can be also set by the sysfs file cpu_partial. However, the tracking of actual number of objects is imprecise, in order to limit overhead from cpu X freeing an objects to a slab on percpu partial list of cpu Y. Basically, the percpu partial slabs form a single linked list, and when we add a new slab to the list with current head "oldpage", we set in the struct page of the slab we're adding: page->pages = oldpage->pages + 1; // this is precise page->pobjects = oldpage->pobjects + (page->objects - page->inuse); page->next = oldpage; Thus the real number of free objects in the slab (objects - inuse) is only determined at the moment of adding the slab to the percpu partial list, and further freeing doesn't update the pobjects counter nor propagate it to the current list head. As Jann reports [1], this can easily lead to large inaccuracies, where the target number of objects (up to 30 by default) can translate to the same number of (empty) slab pages on the list. In case 2) above, we put a slab with 1 free object on the list, thus only increase page->pobjects by 1, even if there are subsequent frees on the same slab. Jann has noticed this in practice and so did we [2] when investigating significant increase of kmemcg usage after switching from SLAB to SLUB. While this is no longer a problem in kmemcg context thanks to the accounting rewrite in 5.9, the memory waste is still not ideal and it's questionable whether it makes sense to perform free object count based control when object counts can easily become so much inaccurate. So this patch converts the accounting to be based on number of pages only (which is precise) and removes the page->pobjects field completely. This is also ultimately simpler. To retain the existing set_cpu_partial() heuristic, first calculate the target number of objects as previously, but then convert it to target number of pages by assuming the pages will be half-filled on average. This assumption might obviously also be inaccurate in practice, but cannot degrade to actual number of pages being equal to the target number of objects. We could also skip the intermediate step with target number of objects and rewrite the heuristic in terms of pages. However we still have the sysfs file cpu_partial which uses number of objects and could break existing users if it suddenly becomes number of pages, so this patch doesn't do that. In practice, after this patch the heuristics limit the size of percpu partial list up to 2 pages. In case of a reported regression (which would mean some workload has benefited from the previous imprecise object based counting), we can tune the heuristics to get a better compromise within the new scheme, while still avoid the unexpectedly long percpu partial lists. [1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/ [2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/ ========== Evaluation ========== Mel was kind enough to run v1 through mmtests machinery for netperf (localhost) and hackbench and, for most significant results see below. So there are some apparent regressions, especially with hackbench, which I think ultimately boils down to having shorter percpu partial lists on average and some benchmarks benefiting from longer ones. Monitoring slab usage also indicated less memory usage by slab. Based on that, the following patch will bump the defaults to allow longer percpu partial lists than after this patch. However the goal is certainly not such that we would limit the percpu partial lists to 30 pages just because previously a specific alloc/free pattern could lead to the limit of 30 objects translate to a limit to 30 pages - that would make little sense. This is a correctness patch, and if a workload benefits from larger lists, the sysfs tuning knobs are still there to allow that. Netperf 2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM TCP-RR: hmean before 127045.79 after 121092.94 (-4.69%, worse) stddev before 2634.37 after 1254.08 UDP-RR: hmean before 166985.45 after 160668.94 ( -3.78%, worse) stddev before 4059.69 after 1943.63 2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM TCP-RR: hmean before 84173.25 after 76914.72 ( -8.62%, worse) UDP-RR: hmean before 93571.12 after 96428.69 ( 3.05%, better) stddev before 23118.54 after 16828.14 2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM TCP-RR: hmean before 49984.92 after 48922.27 ( -2.13%, worse) stddev before 6248.15 after 4740.51 UDP-RR: hmean before 61854.31 after 68761.81 ( 11.17%, better) stddev before 4093.54 after 5898.91 other machines - within 2% Hackbench (results before and after the patch, negative % means worse) 2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM hackbench-process-sockets Amean 1 0.5380 0.5583 ( -3.78%) Amean 4 0.7510 0.8150 ( -8.52%) Amean 7 0.7930 0.9533 ( -20.22%) Amean 12 0.7853 1.1313 ( -44.06%) Amean 21 1.1520 1.4993 ( -30.15%) Amean 30 1.6223 1.9237 ( -18.57%) Amean 48 2.6767 2.9903 ( -11.72%) Amean 79 4.0257 5.1150 ( -27.06%) Amean 110 5.5193 7.4720 ( -35.38%) Amean 141 7.2207 9.9840 ( -38.27%) Amean 172 8.4770 12.1963 ( -43.88%) Amean 203 9.6473 14.3137 ( -48.37%) Amean 234 11.3960 18.7917 ( -64.90%) Amean 265 13.9627 22.4607 ( -60.86%) Amean 296 14.9163 26.0483 ( -74.63%) hackbench-thread-sockets Amean 1 0.5597 0.5877 ( -5.00%) Amean 4 0.7913 0.8960 ( -13.23%) Amean 7 0.8190 1.0017 ( -22.30%) Amean 12 0.9560 1.1727 ( -22.66%) Amean 21 1.7587 1.5660 ( 10.96%) Amean 30 2.4477 1.9807 ( 19.08%) Amean 48 3.4573 3.0630 ( 11.41%) Amean 79 4.7903 5.1733 ( -8.00%) Amean 110 6.1370 7.4220 ( -20.94%) Amean 141 7.5777 9.2617 ( -22.22%) Amean 172 9.2280 11.0907 ( -20.18%) Amean 203 10.2793 13.3470 ( -29.84%) Amean 234 11.2410 17.1070 ( -52.18%) Amean 265 12.5970 23.3323 ( -85.22%) Amean 296 17.1540 24.2857 ( -41.57%) 2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM hackbench-process-sockets Amean 1 0.5760 0.4793 ( 16.78%) Amean 4 0.9430 0.9707 ( -2.93%) Amean 7 1.5517 1.8843 ( -21.44%) Amean 12 2.4903 2.7267 ( -9.49%) Amean 21 3.9560 4.2877 ( -8.38%) Amean 30 5.4613 5.8343 ( -6.83%) Amean 48 8.5337 9.2937 ( -8.91%) Amean 79 14.0670 15.2630 ( -8.50%) Amean 110 19.2253 21.2467 ( -10.51%) Amean 141 23.7557 25.8550 ( -8.84%) Amean 172 28.4407 29.7603 ( -4.64%) Amean 203 33.3407 33.9927 ( -1.96%) Amean 234 38.3633 39.1150 ( -1.96%) Amean 265 43.4420 43.8470 ( -0.93%) Amean 296 48.3680 48.9300 ( -1.16%) hackbench-thread-sockets Amean 1 0.6080 0.6493 ( -6.80%) Amean 4 1.0000 1.0513 ( -5.13%) Amean 7 1.6607 2.0260 ( -22.00%) Amean 12 2.7637 2.9273 ( -5.92%) Amean 21 5.0613 4.5153 ( 10.79%) Amean 30 6.3340 6.1140 ( 3.47%) Amean 48 9.0567 9.5577 ( -5.53%) Amean 79 14.5657 15.7983 ( -8.46%) Amean 110 19.6213 21.6333 ( -10.25%) Amean 141 24.1563 26.2697 ( -8.75%) Amean 172 28.9687 30.2187 ( -4.32%) Amean 203 33.9763 34.6970 ( -2.12%) Amean 234 38.8647 39.3207 ( -1.17%) Amean 265 44.0813 44.1507 ( -0.16%) Amean 296 49.2040 49.4330 ( -0.47%) 2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM hackbench-process-sockets Amean 1 0.5027 0.5017 ( 0.20%) Amean 4 1.1053 1.2033 ( -8.87%) Amean 7 1.8760 2.1820 ( -16.31%) Amean 12 2.9053 3.1810 ( -9.49%) Amean 21 4.6777 4.9920 ( -6.72%) Amean 30 6.5180 6.7827 ( -4.06%) Amean 48 10.0710 10.5227 ( -4.48%) Amean 79 16.4250 17.5053 ( -6.58%) Amean 110 22.6203 24.4617 ( -8.14%) Amean 141 28.0967 31.0363 ( -10.46%) Amean 172 34.4030 36.9233 ( -7.33%) Amean 203 40.5933 43.0850 ( -6.14%) Amean 234 46.6477 48.7220 ( -4.45%) Amean 265 53.0530 53.9597 ( -1.71%) Amean 296 59.2760 59.9213 ( -1.09%) hackbench-thread-sockets Amean 1 0.5363 0.5330 ( 0.62%) Amean 4 1.1647 1.2157 ( -4.38%) Amean 7 1.9237 2.2833 ( -18.70%) Amean 12 2.9943 3.3110 ( -10.58%) Amean 21 4.9987 5.1880 ( -3.79%) Amean 30 6.7583 7.0043 ( -3.64%) Amean 48 10.4547 10.8353 ( -3.64%) Amean 79 16.6707 17.6790 ( -6.05%) Amean 110 22.8207 24.4403 ( -7.10%) Amean 141 28.7090 31.0533 ( -8.17%) Amean 172 34.9387 36.8260 ( -5.40%) Amean 203 41.1567 43.0450 ( -4.59%) Amean 234 47.3790 48.5307 ( -2.43%) Amean 265 53.9543 54.6987 ( -1.38%) Amean 296 60.0820 60.2163 ( -0.22%) 1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads), 32 GB RAM hackbench-process-sockets Amean 1 1.4760 1.5773 ( -6.87%) Amean 3 3.9370 4.0910 ( -3.91%) Amean 5 6.6797 6.9357 ( -3.83%) Amean 7 9.3367 9.7150 ( -4.05%) Amean 12 15.7627 16.1400 ( -2.39%) Amean 18 23.5360 23.6890 ( -0.65%) Amean 24 31.0663 31.3137 ( -0.80%) Amean 30 38.7283 39.0037 ( -0.71%) Amean 32 41.3417 41.6097 ( -0.65%) hackbench-thread-sockets Amean 1 1.5250 1.6043 ( -5.20%) Amean 3 4.0897 4.2603 ( -4.17%) Amean 5 6.7760 7.0933 ( -4.68%) Amean 7 9.4817 9.9157 ( -4.58%) Amean 12 15.9610 16.3937 ( -2.71%) Amean 18 23.9543 24.3417 ( -1.62%) Amean 24 31.4400 31.7217 ( -0.90%) Amean 30 39.2457 39.5467 ( -0.77%) Amean 32 41.8267 42.1230 ( -0.71%) 2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM hackbench-process-sockets Amean 1 1.0347 1.0880 ( -5.15%) Amean 4 1.7267 1.8527 ( -7.30%) Amean 7 2.6707 2.8110 ( -5.25%) Amean 12 4.1617 4.3383 ( -4.25%) Amean 21 7.0070 7.2600 ( -3.61%) Amean 30 9.9187 10.2397 ( -3.24%) Amean 48 15.6710 16.3923 ( -4.60%) Amean 79 24.7743 26.1247 ( -5.45%) Amean 110 34.3000 35.9307 ( -4.75%) Amean 141 44.2043 44.8010 ( -1.35%) Amean 172 54.2430 54.7260 ( -0.89%) Amean 192 60.6557 60.9777 ( -0.53%) hackbench-thread-sockets Amean 1 1.0610 1.1353 ( -7.01%) Amean 4 1.7543 1.9140 ( -9.10%) Amean 7 2.7840 2.9573 ( -6.23%) Amean 12 4.3813 4.4937 ( -2.56%) Amean 21 7.3460 7.5350 ( -2.57%) Amean 30 10.2313 10.5190 ( -2.81%) Amean 48 15.9700 16.5940 ( -3.91%) Amean 79 25.3973 26.6637 ( -4.99%) Amean 110 35.1087 36.4797 ( -3.91%) Amean 141 45.8220 46.3053 ( -1.05%) Amean 172 55.4917 55.7320 ( -0.43%) Amean 192 62.7490 62.5410 ( 0.33%) Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reported-by: Jann Horn Cc: Roman Gushchin Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 -- include/linux/slub_def.h | 13 ++----------- 2 files changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f8ee09c711f..68ffa064b7a8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -124,10 +124,8 @@ struct page { struct page *next; #ifdef CONFIG_64BIT int pages; /* Nr of pages left */ - int pobjects; /* Approximate count */ #else short int pages; - short int pobjects; #endif }; }; diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 85499f0586b0..0fa751b946fa 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -99,6 +99,8 @@ struct kmem_cache { #ifdef CONFIG_SLUB_CPU_PARTIAL /* Number of per cpu partial objects to keep around */ unsigned int cpu_partial; + /* Number of per cpu partial pages to keep around */ + unsigned int cpu_partial_pages; #endif struct kmem_cache_order_objects oo; @@ -141,17 +143,6 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -#ifdef CONFIG_SLUB_CPU_PARTIAL -#define slub_cpu_partial(s) ((s)->cpu_partial) -#define slub_set_cpu_partial(s, n) \ -({ \ - slub_cpu_partial(s) = (n); \ -}) -#else -#define slub_cpu_partial(s) (0) -#define slub_set_cpu_partial(s, n) -#endif /* CONFIG_SLUB_CPU_PARTIAL */ - #ifdef CONFIG_SYSFS #define SLAB_SUPPORTS_SYSFS void sysfs_slab_unlink(struct kmem_cache *); -- cgit v1.2.3 From 96c84dde362a3e4ff67a12eaac2ea6e88e963c07 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Nov 2021 13:35:30 -0700 Subject: mm: don't include in Not required at all, and having this causes a huge kernel rebuild as soon as something in dax.h changes. Link: https://lkml.kernel.org/r/20210921082253.1859794-1-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Naoya Horiguchi Reviewed-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 4091692bed8c..097bbbb37493 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -8,7 +8,6 @@ #include #include -#include #include #include #include -- cgit v1.2.3 From 7857ccdf94e94f1dd56496b90084fdcaa5e655a4 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:35:33 -0700 Subject: lib/stackdepot: include gfp.h Patch series "stackdepot, kasan, workqueue: Avoid expanding stackdepot slabs when holding raw_spin_lock", v2. Shuah Khan reported [1]: | When CONFIG_PROVE_RAW_LOCK_NESTING=y and CONFIG_KASAN are enabled, | kasan_record_aux_stack() runs into "BUG: Invalid wait context" when | it tries to allocate memory attempting to acquire spinlock in page | allocation code while holding workqueue pool raw_spinlock. | | There are several instances of this problem when block layer tries | to __queue_work(). Call trace from one of these instances is below: | | kblockd_mod_delayed_work_on() | mod_delayed_work_on() | __queue_delayed_work() | __queue_work() (rcu_read_lock, raw_spin_lock pool->lock held) | insert_work() | kasan_record_aux_stack() | kasan_save_stack() | stack_depot_save() | alloc_pages() | __alloc_pages() | get_page_from_freelist() | rm_queue() | rm_queue_pcplist() | local_lock_irqsave(&pagesets.lock, flags); | [ BUG: Invalid wait context triggered ] PROVE_RAW_LOCK_NESTING is pointing out that (on RT kernels) the locking rules are being violated. More generally, memory is being allocated from a non-preemptive context (raw_spin_lock'd c-s) where it is not allowed. To properly fix this, we must prevent stackdepot from replenishing its "stack slab" pool if memory allocations cannot be done in the current context: it's a bug to use either GFP_ATOMIC nor GFP_NOWAIT in certain non-preemptive contexts, including raw_spin_locks (see gfp.h and commit ab00db216c9c7). The only downside is that saving a stack trace may fail if: stackdepot runs out of space AND the same stack trace has not been recorded before. I expect this to be unlikely, and a simple experiment (boot the kernel) didn't result in any failure to record stack trace from insert_work(). The series includes a few minor fixes to stackdepot that I noticed in preparing the series. It then introduces __stack_depot_save(), which exposes the option to force stackdepot to not allocate any memory. Finally, KASAN is changed to use the new stackdepot interface and provide kasan_record_aux_stack_noalloc(), which is then used by workqueue code. [1] https://lkml.kernel.org/r/20210902200134.25603-1-skhan@linuxfoundation.org This patch (of 6): refers to gfp_t, but doesn't include gfp.h. Fix it by including . Link: https://lkml.kernel.org/r/20210913112609.2651084-1-elver@google.com Link: https://lkml.kernel.org/r/20210913112609.2651084-2-elver@google.com Signed-off-by: Marco Elver Tested-by: Shuah Khan Acked-by: Sebastian Andrzej Siewior Reviewed-by: Andrey Konovalov Cc: Tejun Heo Cc: Lai Jiangshan Cc: Walter Wu Cc: Thomas Gleixner Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Vijayanand Jitta Cc: Vinayak Menon Cc: "Gustavo A. R. Silva" Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 6bb4bc1a5f54..97b36dc53301 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -11,6 +11,8 @@ #ifndef _LINUX_STACKDEPOT_H #define _LINUX_STACKDEPOT_H +#include + typedef u32 depot_stack_handle_t; depot_stack_handle_t stack_depot_save(unsigned long *entries, -- cgit v1.2.3 From 11ac25c62cd2f3bb8da9e1df2e71afdebe76f093 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:35:39 -0700 Subject: lib/stackdepot: introduce __stack_depot_save() Add __stack_depot_save(), which provides more fine-grained control over stackdepot's memory allocation behaviour, in case stackdepot runs out of "stack slabs". Normally stackdepot uses alloc_pages() in case it runs out of space; passing can_alloc==false to __stack_depot_save() prohibits this, at the cost of more likely failure to record a stack trace. Link: https://lkml.kernel.org/r/20210913112609.2651084-4-elver@google.com Signed-off-by: Marco Elver Tested-by: Shuah Khan Acked-by: Sebastian Andrzej Siewior Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: "Gustavo A. R. Silva" Cc: Lai Jiangshan Cc: Taras Madan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Vijayanand Jitta Cc: Vinayak Menon Cc: Walter Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 97b36dc53301..b2f7e7c6ba54 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -15,6 +15,10 @@ typedef u32 depot_stack_handle_t; +depot_stack_handle_t __stack_depot_save(unsigned long *entries, + unsigned int nr_entries, + gfp_t gfp_flags, bool can_alloc); + depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); -- cgit v1.2.3 From 7cb3007ce2da27ec02a1a3211941e7fe6875b642 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:35:46 -0700 Subject: kasan: generic: introduce kasan_record_aux_stack_noalloc() Introduce a variant of kasan_record_aux_stack() that does not do any memory allocation through stackdepot. This will permit using it in contexts that cannot allocate any memory. Link: https://lkml.kernel.org/r/20210913112609.2651084-6-elver@google.com Signed-off-by: Marco Elver Tested-by: Shuah Khan Acked-by: Sebastian Andrzej Siewior Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: "Gustavo A. R. Silva" Cc: Lai Jiangshan Cc: Taras Madan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Vijayanand Jitta Cc: Vinayak Menon Cc: Walter Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index dd874a1ee862..736d7b458996 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -370,12 +370,14 @@ static inline void kasan_unpoison_task_stack(struct task_struct *task) {} void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_record_aux_stack(void *ptr); +void kasan_record_aux_stack_noalloc(void *ptr); #else /* CONFIG_KASAN_GENERIC */ static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_record_aux_stack(void *ptr) {} +static inline void kasan_record_aux_stack_noalloc(void *ptr) {} #endif /* CONFIG_KASAN_GENERIC */ -- cgit v1.2.3 From 86cffecdeaa278444870c8745ab166a65865dbf0 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:19 -0700 Subject: Compiler Attributes: add __alloc_size() for better bounds checking GCC and Clang can use the "alloc_size" attribute to better inform the results of __builtin_object_size() (for compile-time constant values). Clang can additionally use alloc_size to inform the results of __builtin_dynamic_object_size() (for run-time values). Because GCC sees the frequent use of struct_size() as an allocator size argument, and notices it can return SIZE_MAX (the overflow indication), it complains about these call sites overflowing (since SIZE_MAX is greater than the default -Walloc-size-larger-than=PTRDIFF_MAX). This isn't helpful since we already know a SIZE_MAX will be caught at run-time (this was an intentional design). To deal with this, we must disable this check as it is both a false positive and redundant. (Clang does not have this warning option.) Unfortunately, just checking the -Wno-alloc-size-larger-than is not sufficient to make the __alloc_size attribute behave correctly under older GCC versions. The attribute itself must be disabled in those situations too, as there appears to be no way to reliably silence the SIZE_MAX constant expression cases for GCC versions less than 9.1: In file included from ./include/linux/resource_ext.h:11, from ./include/linux/pci.h:40, from drivers/net/ethernet/intel/ixgbe/ixgbe.h:9, from drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c:4: In function 'kmalloc_node', inlined from 'ixgbe_alloc_q_vector' at ./include/linux/slab.h:743:9: ./include/linux/slab.h:618:9: error: argument 1 value '18446744073709551615' exceeds maximum object size 9223372036854775807 [-Werror=alloc-size-larger-than=] return __kmalloc_node(size, flags, node); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/slab.h: In function 'ixgbe_alloc_q_vector': ./include/linux/slab.h:455:7: note: in a call to allocation function '__kmalloc_node' declared here void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_slab_alignment __malloc; ^~~~~~~~~~~~~~ Specifically: '-Wno-alloc-size-larger-than' is not correctly handled by GCC < 9.1 https://godbolt.org/z/hqsfG7q84 (doesn't disable) https://godbolt.org/z/P9jdrPTYh (doesn't admit to not knowing about option) https://godbolt.org/z/465TPMWKb (only warns when other warnings appear) '-Walloc-size-larger-than=18446744073709551615' is not handled by GCC < 8.2 https://godbolt.org/z/73hh1EPxz (ignores numeric value) Since anything marked with __alloc_size would also qualify for marking with __malloc, just include __malloc along with it to avoid redundant markings. (Suggested by Linus Torvalds.) Finally, make sure checkpatch.pl doesn't get confused about finding the __alloc_size attribute on functions. (Thanks to Joe Perches.) Link: https://lkml.kernel.org/r/20210930222704.2631604-3-keescook@chromium.org Signed-off-by: Kees Cook Tested-by: Randy Dunlap Cc: Andy Whitcroft Cc: Christoph Lameter Cc: Daniel Micay Cc: David Rientjes Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Pekka Enberg Cc: Tejun Heo Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 8 ++++++++ include/linux/compiler_attributes.h | 10 ++++++++++ include/linux/compiler_types.h | 12 ++++++++++++ 3 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index bd2b881c6b63..b9d5f9c373a0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -144,3 +144,11 @@ #else #define __diag_GCC_8(s) #endif + +/* + * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size" + * attribute) do not work, and must be disabled. + */ +#if GCC_VERSION < 90100 +#undef __alloc_size__ +#endif diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index e6ec63403965..3de06a8fae73 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -33,6 +33,15 @@ #define __aligned(x) __attribute__((__aligned__(x))) #define __aligned_largest __attribute__((__aligned__)) +/* + * Note: do not use this directly. Instead, use __alloc_size() since it is conditionally + * available and includes other attributes. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alloc_005fsize-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#alloc-size + */ +#define __alloc_size__(x, ...) __attribute__((__alloc_size__(x, ## __VA_ARGS__))) + /* * Note: users of __always_inline currently do not write "inline" themselves, * which seems to be required by gcc to apply the attribute according @@ -153,6 +162,7 @@ /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-malloc-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#malloc */ #define __malloc __attribute__((__malloc__)) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index b6ff83a714ca..4f2203c4a257 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -250,6 +250,18 @@ struct ftrace_likely_data { # define __cficanonical #endif +/* + * Any place that could be marked with the "alloc_size" attribute is also + * a place to be marked with the "malloc" attribute. Do this as part of the + * __alloc_size macro to avoid redundant attributes and to avoid missing a + * __malloc marking. + */ +#ifdef __alloc_size__ +# define __alloc_size(x, ...) __alloc_size__(x, ## __VA_ARGS__) __malloc +#else +# define __alloc_size(x, ...) __malloc +#endif + #ifndef asm_volatile_goto #define asm_volatile_goto(x...) asm goto(x) #endif -- cgit v1.2.3 From 72d67229f522e3331d1eabd9f58d36ae080eb228 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:23 -0700 Subject: slab: clean up function prototypes Based on feedback from Joe Perches and Linus Torvalds, regularize the slab function prototypes before making attribute changes. Link: https://lkml.kernel.org/r/20210930222704.2631604-4-keescook@chromium.org Signed-off-by: Kees Cook Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Andy Whitcroft Cc: Daniel Micay Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: Joe Perches Cc: John Hubbard Cc: kernel test robot Cc: Lukas Bulwahn Cc: Matt Porter Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Randy Dunlap Cc: Souptick Joarder Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 68 ++++++++++++++++++++++++++-------------------------- 1 file changed, 34 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index c0d46b6fa12a..d05de03bdcdd 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -152,8 +152,8 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); -void kmem_cache_destroy(struct kmem_cache *); -int kmem_cache_shrink(struct kmem_cache *); +void kmem_cache_destroy(struct kmem_cache *s); +int kmem_cache_shrink(struct kmem_cache *s); /* * Please use this macro to create slab caches. Simply specify the @@ -181,11 +181,11 @@ int kmem_cache_shrink(struct kmem_cache *); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *, size_t, gfp_t); -void kfree(const void *); -void kfree_sensitive(const void *); -size_t __ksize(const void *); -size_t ksize(const void *); +void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags); +void kfree(const void *objp); +void kfree_sensitive(const void *objp); +size_t __ksize(const void *objp); +size_t ksize(const void *objp); #ifdef CONFIG_PRINTK bool kmem_valid_obj(void *object); void kmem_dump_obj(void *object); @@ -426,8 +426,8 @@ static __always_inline unsigned int __kmalloc_index(size_t size, #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; -void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment __malloc; -void kmem_cache_free(struct kmem_cache *, void *); +void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc; +void kmem_cache_free(struct kmem_cache *s, void *objp); /* * Bulk allocation and freeing operations. These are accelerated in an @@ -436,8 +436,8 @@ void kmem_cache_free(struct kmem_cache *, void *); * * Note that interrupts must be enabled when calling these functions. */ -void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); -int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); +void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); +int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p); /* * Caller must not use kfree_bulk() on memory not originally allocated @@ -450,7 +450,8 @@ static __always_inline void kfree_bulk(size_t size, void **p) #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; -void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc; +void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment + __malloc; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { @@ -464,25 +465,24 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f #endif #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc; +extern void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) + __assume_slab_alignment __malloc; #ifdef CONFIG_NUMA -extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size) __assume_slab_alignment __malloc; +extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) __assume_slab_alignment __malloc; #else -static __always_inline void * -kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size) +static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, + gfp_t gfpflags, int node, + size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ -static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, - gfp_t flags, size_t size) +static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, + size_t size) { void *ret = kmem_cache_alloc(s, flags); @@ -490,10 +490,8 @@ static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, return ret; } -static __always_inline void * -kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size) +static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) { void *ret = kmem_cache_alloc_node(s, gfpflags, node); @@ -502,13 +500,14 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, } #endif /* CONFIG_TRACING */ -extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; +extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment + __malloc; #ifdef CONFIG_TRACING -extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; +extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) + __assume_page_alignment __malloc; #else -static __always_inline void * -kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +static __always_inline void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { return kmalloc_order(size, flags, order); } @@ -638,8 +637,8 @@ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -static __must_check inline void * -krealloc_array(void *p, size_t new_n, size_t new_size, gfp_t flags) +static inline void * __must_check krealloc_array(void *p, size_t new_n, size_t new_size, + gfp_t flags) { size_t bytes; @@ -668,7 +667,7 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) * allocator where we care about the real place the memory allocation * request comes from. */ -extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); +extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) @@ -691,7 +690,8 @@ static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) #ifdef CONFIG_NUMA -extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long); +extern void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, + unsigned long caller); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) -- cgit v1.2.3 From c37495d6254c237578db3121dcf79857e033f8ff Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:27 -0700 Subject: slab: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for regular kmalloc interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-5-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Reviewed-by: Nick Desaulniers Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Andy Whitcroft Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Tejun Heo Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 61 ++++++++++++++++++++++++++++------------------------ 1 file changed, 33 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index d05de03bdcdd..b5bf0537975b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -181,7 +181,7 @@ int kmem_cache_shrink(struct kmem_cache *s); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags); +void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __alloc_size(2); void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); @@ -425,7 +425,7 @@ static __always_inline unsigned int __kmalloc_index(size_t size, #define kmalloc_index(s) __kmalloc_index(s, true) #endif /* !CONFIG_SLOB */ -void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; +void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *s, void *objp); @@ -449,11 +449,12 @@ static __always_inline void kfree_bulk(size_t size, void **p) } #ifdef CONFIG_NUMA -void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; +void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment + __alloc_size(1); void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; #else -static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) +static __always_inline __alloc_size(1) void *__kmalloc_node(size_t size, gfp_t flags, int node) { return __kmalloc(size, flags); } @@ -466,23 +467,23 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f #ifdef CONFIG_TRACING extern void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) - __assume_slab_alignment __malloc; + __assume_slab_alignment __alloc_size(3); #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) __assume_slab_alignment __malloc; + int node, size_t size) __assume_slab_alignment + __alloc_size(4); #else -static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, int node, - size_t size) +static __always_inline __alloc_size(4) void *kmem_cache_alloc_node_trace(struct kmem_cache *s, + gfp_t gfpflags, int node, size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ -static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, - size_t size) +static __always_inline __alloc_size(3) void *kmem_cache_alloc_trace(struct kmem_cache *s, + gfp_t flags, size_t size) { void *ret = kmem_cache_alloc(s, flags); @@ -501,19 +502,20 @@ static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, g #endif /* CONFIG_TRACING */ extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment - __malloc; + __alloc_size(1); #ifdef CONFIG_TRACING extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) - __assume_page_alignment __malloc; + __assume_page_alignment __alloc_size(1); #else -static __always_inline void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +static __always_inline __alloc_size(1) void *kmalloc_order_trace(size_t size, gfp_t flags, + unsigned int order) { return kmalloc_order(size, flags, order); } #endif -static __always_inline void *kmalloc_large(size_t size, gfp_t flags) +static __always_inline __alloc_size(1) void *kmalloc_large(size_t size, gfp_t flags) { unsigned int order = get_order(size); return kmalloc_order_trace(size, flags, order); @@ -573,7 +575,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * Try really hard to succeed the allocation but fail * eventually. */ -static __always_inline void *kmalloc(size_t size, gfp_t flags) +static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { #ifndef CONFIG_SLOB @@ -595,7 +597,7 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) return __kmalloc(size, flags); } -static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) +static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && @@ -619,7 +621,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; @@ -637,8 +639,10 @@ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -static inline void * __must_check krealloc_array(void *p, size_t new_n, size_t new_size, - gfp_t flags) +static inline __alloc_size(2, 3) void * __must_check krealloc_array(void *p, + size_t new_n, + size_t new_size, + gfp_t flags) { size_t bytes; @@ -654,7 +658,7 @@ static inline void * __must_check krealloc_array(void *p, size_t new_n, size_t n * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline void *kcalloc(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flags) { return kmalloc_array(n, size, flags | __GFP_ZERO); } @@ -667,12 +671,13 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) * allocator where we care about the real place the memory allocation * request comes from. */ -extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller); +extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller) + __alloc_size(1); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) -static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, - int node) +static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, + int node) { size_t bytes; @@ -683,7 +688,7 @@ static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, return __kmalloc_node(bytes, flags, node); } -static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) +static inline __alloc_size(1, 2) void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) { return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); } @@ -691,7 +696,7 @@ static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) #ifdef CONFIG_NUMA extern void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, - unsigned long caller); + unsigned long caller) __alloc_size(1); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) @@ -716,7 +721,7 @@ static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ -static inline void *kzalloc(size_t size, gfp_t flags) +static inline __alloc_size(1) void *kzalloc(size_t size, gfp_t flags) { return kmalloc(size, flags | __GFP_ZERO); } @@ -727,7 +732,7 @@ static inline void *kzalloc(size_t size, gfp_t flags) * @flags: the type of memory to allocate (see kmalloc). * @node: memory node from which to allocate */ -static inline void *kzalloc_node(size_t size, gfp_t flags, int node) +static inline __alloc_size(1) void *kzalloc_node(size_t size, gfp_t flags, int node) { return kmalloc_node(size, flags | __GFP_ZERO, node); } -- cgit v1.2.3 From 56bcf40f91c7d7f53b77abe161a7d18ef9f981ba Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:31 -0700 Subject: mm/kvmalloc: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for regular kvmalloc interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-6-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Reviewed-by: Nick Desaulniers Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Andy Whitcroft Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Tejun Heo Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index b5bf0537975b..837cb16232ef 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -737,21 +737,21 @@ static inline __alloc_size(1) void *kzalloc_node(size_t size, gfp_t flags, int n return kmalloc_node(size, flags | __GFP_ZERO, node); } -extern void *kvmalloc_node(size_t size, gfp_t flags, int node); -static inline void *kvmalloc(size_t size, gfp_t flags) +extern void *kvmalloc_node(size_t size, gfp_t flags, int node) __alloc_size(1); +static inline __alloc_size(1) void *kvmalloc(size_t size, gfp_t flags) { return kvmalloc_node(size, flags, NUMA_NO_NODE); } -static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) +static inline __alloc_size(1) void *kvzalloc_node(size_t size, gfp_t flags, int node) { return kvmalloc_node(size, flags | __GFP_ZERO, node); } -static inline void *kvzalloc(size_t size, gfp_t flags) +static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags) { return kvmalloc(size, flags | __GFP_ZERO); } -static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; @@ -761,13 +761,13 @@ static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) return kvmalloc(bytes, flags); } -static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t flags) { return kvmalloc_array(n, size, flags | __GFP_ZERO); } -extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, - gfp_t flags); +extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) + __alloc_size(3); extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); -- cgit v1.2.3 From 894f24bb569afd4fe4a874c636f82d47f1c9beed Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:34 -0700 Subject: mm/vmalloc: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for appropriate vmalloc allocator interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-7-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Cc: Andy Whitcroft Cc: Christoph Lameter Cc: David Rientjes Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pekka Enberg Cc: Tejun Heo Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 671d402c3778..0ed56fc10c11 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -136,21 +136,21 @@ static inline void vmalloc_init(void) static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif -extern void *vmalloc(unsigned long size); -extern void *vzalloc(unsigned long size); -extern void *vmalloc_user(unsigned long size); -extern void *vmalloc_node(unsigned long size, int node); -extern void *vzalloc_node(unsigned long size, int node); -extern void *vmalloc_32(unsigned long size); -extern void *vmalloc_32_user(unsigned long size); -extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); +extern void *vmalloc(unsigned long size) __alloc_size(1); +extern void *vzalloc(unsigned long size) __alloc_size(1); +extern void *vmalloc_user(unsigned long size) __alloc_size(1); +extern void *vmalloc_node(unsigned long size, int node) __alloc_size(1); +extern void *vzalloc_node(unsigned long size, int node) __alloc_size(1); +extern void *vmalloc_32(unsigned long size) __alloc_size(1); +extern void *vmalloc_32_user(unsigned long size) __alloc_size(1); +extern void *__vmalloc(unsigned long size, gfp_t gfp_mask) __alloc_size(1); extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, - const void *caller); + const void *caller) __alloc_size(1); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, - int node, const void *caller); -void *vmalloc_no_huge(unsigned long size); + int node, const void *caller) __alloc_size(1); +void *vmalloc_no_huge(unsigned long size) __alloc_size(1); extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); -- cgit v1.2.3 From abd58f38dfb4771ef06e25d71a84aa0932c52f1a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:38 -0700 Subject: mm/page_alloc: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for appropriate page allocator interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-8-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Cc: Andy Whitcroft Cc: Christoph Lameter Cc: David Rientjes Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pekka Enberg Cc: Tejun Heo Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 55b2ec1f965a..fbd4abc33f24 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -608,9 +608,9 @@ static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); -void *alloc_pages_exact(size_t size, gfp_t gfp_mask); +void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1); void free_pages_exact(void *virt, size_t size); -void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); +__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(1); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) -- cgit v1.2.3 From 17197dd460469c6fca66e274f5cd51ee43bb6ddd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:42 -0700 Subject: percpu: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for appropriate percpu allocator interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Note that due to the implementation of the percpu API, this is unlikely to ever actually provide compile-time checking beyond very simple non-SMP builds. But, since they are technically allocators, mark them as such. Link: https://lkml.kernel.org/r/20210930222704.2631604-9-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Acked-by: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Cc: Andy Whitcroft Cc: David Rientjes Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pekka Enberg Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 5e76af742c80..98a9371133f8 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -123,7 +123,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_populate_pte_fn_t populate_pte_fn); #endif -extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); +extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1); extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr); extern bool is_kernel_percpu_address(unsigned long addr); @@ -131,8 +131,8 @@ extern bool is_kernel_percpu_address(unsigned long addr); extern void __init setup_per_cpu_areas(void); #endif -extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp); -extern void __percpu *__alloc_percpu(size_t size, size_t align); +extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); +extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); extern void free_percpu(void __percpu *__pdata); extern phys_addr_t per_cpu_ptr_to_phys(void *addr); -- cgit v1.2.3 From 0b3ea0926afb8dde70cfab00316ae0a70b93a7cc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Nov 2021 13:36:58 -0700 Subject: fs: explicitly unregister per-superblock BDIs Add a new SB_I_ flag to mark superblocks that have an ephemeral bdi associated with them, and unregister it when the superblock is shut down. Link: https://lkml.kernel.org/r/20211021124441.668816-4-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e7a633353fd2..226de651f52e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1443,6 +1443,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ +#define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ /* Possible states of 'frozen' field */ enum { -- cgit v1.2.3 From efee17134ca464639a2f5b4d036ce40caf1b247a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Nov 2021 13:37:04 -0700 Subject: mm: simplify bdi refcounting Move grabbing and releasing the bdi refcount out of the common wb_init/wb_exit helpers into code that is only used for the non-default memcg driven bdi_writeback structures. [hch@lst.de: add comment] Link: https://lkml.kernel.org/r/20211027074207.GA12793@lst.de [akpm@linux-foundation.org: fix typo] Link: https://lkml.kernel.org/r/20211021124441.668816-6-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 33207004cfde..993c5628a726 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -103,6 +103,9 @@ struct wb_completion { * change as blkcg is disabled and enabled higher up in the hierarchy, a wb * is tested for blkcg after lookup and removed from index on mismatch so * that a new wb for the combination can be created. + * + * Each bdi_writeback that is not embedded into the backing_dev_info must hold + * a reference to the parent backing_dev_info. See cgwb_create() for details. */ struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ -- cgit v1.2.3 From e80216d9f1f5c90b3cab834cd4fb492d731f70aa Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 5 Nov 2021 13:37:56 -0700 Subject: mm: memcontrol: remove the kmem states Now the kmem states is only used to indicate whether the kmem is offline. However, we can set ->kmemcg_id to -1 to indicate whether the kmem is offline. Finally, we can remove the kmem states to simplify the code. Link: https://lkml.kernel.org/r/20211025125259.56624-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Roman Gushchin Cc: Michal Hocko Cc: Shakeel Butt Cc: Matthew Wilcox (Oracle) Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3096c9a0ee01..f207f98bdb76 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -180,12 +180,6 @@ struct mem_cgroup_thresholds { struct mem_cgroup_threshold_ary *spare; }; -enum memcg_kmem_state { - KMEM_NONE, - KMEM_ALLOCATED, - KMEM_ONLINE, -}; - #if defined(CONFIG_SMP) struct memcg_padding { char x[0]; @@ -318,7 +312,6 @@ struct mem_cgroup { #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; - enum memcg_kmem_state kmem_state; struct obj_cgroup __rcu *objcg; struct list_head objcg_list; /* list of inherited objcgs */ #endif -- cgit v1.2.3 From f1dc0db296bd25960273649fc6ef2ecbf5aaa0e0 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Fri, 5 Nov 2021 13:38:15 -0700 Subject: mm: use __pfn_to_section() instead of open coding it It is defined in the same file just a few lines above. Link: https://lkml.kernel.org/r/4598487.Rc0NezkW7i@mobilepool36.emlix.com Signed-off-by: Rolf Eike Beer Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6a1d79d84675..832aa49d0d8e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1481,7 +1481,7 @@ static inline int pfn_valid(unsigned long pfn) if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - ms = __nr_to_section(pfn_to_section_nr(pfn)); + ms = __pfn_to_section(pfn); if (!valid_section(ms)) return 0; /* @@ -1496,7 +1496,7 @@ static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - return present_section(__nr_to_section(pfn_to_section_nr(pfn))); + return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) -- cgit v1.2.3 From 232a6a1c0619d1b4d9cd8d21949b2f13821be0af Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 5 Nov 2021 13:38:31 -0700 Subject: mm: drop first_index/last_index in zap_details The first_index/last_index parameters in zap_details are actually only used in unmap_mapping_range_tree(). At the meantime, this function is only called by unmap_mapping_pages() once. Instead of passing these two variables through the whole stack of page zapping code, remove them from zap_details and let them simply be parameters of unmap_mapping_range_tree(), which is inlined. Link: https://lkml.kernel.org/r/20210915181535.11238-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Alistair Popple Reviewed-by: David Hildenbrand Reviewed-by: Liam Howlett Acked-by: Hugh Dickins Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mike Rapoport Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 32b2ecc47408..c5b600d7f85b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1688,8 +1688,6 @@ extern void user_shm_unlock(size_t, struct ucounts *); */ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ - pgoff_t first_index; /* Lowest page->index to unmap */ - pgoff_t last_index; /* Highest page->index to unmap */ struct page *single_page; /* Locked page to be unmapped */ }; -- cgit v1.2.3 From 91b61ef333cf43f96b3522a086c9ac925763d6e5 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 5 Nov 2021 13:38:34 -0700 Subject: mm: add zap_skip_check_mapping() helper Use the helper for the checks. Rename "check_mapping" into "zap_mapping" because "check_mapping" looks like a bool but in fact it stores the mapping itself. When it's set, we check the mapping (it must be non-NULL). When it's cleared we skip the check, which works like the old way. Move the duplicated comments to the helper too. Link: https://lkml.kernel.org/r/20210915181538.11288-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Liam Howlett Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mike Rapoport Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c5b600d7f85b..6e29deb1e0d4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1687,10 +1687,24 @@ extern void user_shm_unlock(size_t, struct ucounts *); * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { - struct address_space *check_mapping; /* Check page->mapping if set */ + struct address_space *zap_mapping; /* Check page->mapping if set */ struct page *single_page; /* Locked page to be unmapped */ }; +/* + * We set details->zap_mappings when we want to unmap shared but keep private + * pages. Return true if skip zapping this page, false otherwise. + */ +static inline bool +zap_skip_check_mapping(struct zap_details *details, struct page *page) +{ + if (!details || !page) + return false; + + return details->zap_mapping && + (details->zap_mapping != page_rmapping(page)); +} + struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, -- cgit v1.2.3 From e26e0cc30b48cad5f2704f6a22fa5cac9fdaaece Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 5 Nov 2021 13:39:00 -0700 Subject: memory: remove unused CONFIG_MEM_BLOCK_SIZE Commit 3947be1969a9 ("[PATCH] memory hotplug: sysfs and add/remove functions") defines CONFIG_MEM_BLOCK_SIZE, but this has never been utilized anywhere. It is a good practice to keep the CONFIG_* defines exclusively for the Kbuild system. So, drop this unused definition. This issue was noticed due to running ./scripts/checkkconfigsymbols.py. Link: https://lkml.kernel.org/r/20211006120354.7468-1-lukas.bulwahn@gmail.com Signed-off-by: Lukas Bulwahn Reviewed-by: David Hildenbrand Cc: Michal Hocko Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 182c606adb06..053a530c7bdd 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -140,7 +140,6 @@ typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); extern int walk_memory_blocks(unsigned long start, unsigned long size, void *arg, walk_memory_blocks_func_t func); extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func); -#define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION< Date: Fri, 5 Nov 2021 13:39:10 -0700 Subject: include/linux/io-mapping.h: remove fallback for writecombine The fallback was introduced in commit 80c33624e472 ("io-mapping: Fixup for different names of writecombine") to fix the build on microblaze. 5 years later, it seems all archs now provide a pgprot_writecombine(), so just remove the other possible fallbacks. For microblaze, pgprot_writecombine() is available since commit 97ccedd793ac ("microblaze: Provide pgprot_device/writecombine macros for nommu"). This is build-tested on microblaze with a hack to always build mm/io-mapping.o and without DIYing on an x86-only macro (_PAGE_CACHE_MASK) Link: https://lkml.kernel.org/r/20211020204838.1142908-1-lucas.demarchi@intel.com Signed-off-by: Lucas De Marchi Cc: Chris Wilson Cc: Daniel Vetter Cc: Joonas Lahtinen Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/io-mapping.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index e9743cfd8585..66a774d2710e 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -132,13 +132,7 @@ io_mapping_init_wc(struct io_mapping *iomap, iomap->base = base; iomap->size = size; -#if defined(pgprot_noncached_wc) /* archs can't agree on a name ... */ - iomap->prot = pgprot_noncached_wc(PAGE_KERNEL); -#elif defined(pgprot_writecombine) iomap->prot = pgprot_writecombine(PAGE_KERNEL); -#else - iomap->prot = pgprot_noncached(PAGE_KERNEL); -#endif return iomap; } -- cgit v1.2.3 From bd1a8fb2d43f7c293383f76691d7a55f7f89d9da Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 5 Nov 2021 13:39:22 -0700 Subject: mm/vmalloc: don't allow VM_NO_GUARD on vmap() The vmalloc guard pages are added on top of each allocation, thereby isolating any two allocations from one another. The top guard of the lower allocation is the bottom guard guard of the higher allocation etc. Therefore VM_NO_GUARD is dangerous; it breaks the basic premise of isolating separate allocations. There are only two in-tree users of this flag, neither of which use it through the exported interface. Ensure it stays this way. Link: https://lkml.kernel.org/r/YUMfdA36fuyZ+/xt@hirez.programming.kicks-ass.net Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Christoph Hellwig Reviewed-by: David Hildenbrand Acked-by: Will Deacon Acked-by: Kees Cook Cc: Andrey Konovalov Cc: Mel Gorman Cc: Uladzislau Rezki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0ed56fc10c11..6e022cc712e6 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -22,7 +22,7 @@ struct notifier_block; /* in notifier.h */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_DMA_COHERENT 0x00000010 /* dma_alloc_coherent */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ -#define VM_NO_GUARD 0x00000040 /* don't add guard page */ +#define VM_NO_GUARD 0x00000040 /* ***DANGEROUS*** don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ -- cgit v1.2.3 From 3252b1d8309ea42bc6329d9341072ecf1c9505c0 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 5 Nov 2021 13:39:47 -0700 Subject: kasan: arm64: fix pcpu_page_first_chunk crash with KASAN_VMALLOC With KASAN_VMALLOC and NEED_PER_CPU_PAGE_FIRST_CHUNK the kernel crashes: Unable to handle kernel paging request at virtual address ffff7000028f2000 ... swapper pgtable: 64k pages, 48-bit VAs, pgdp=0000000042440000 [ffff7000028f2000] pgd=000000063e7c0003, p4d=000000063e7c0003, pud=000000063e7c0003, pmd=000000063e7b0003, pte=0000000000000000 Internal error: Oops: 96000007 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 5.13.0-rc4-00003-gc6e6e28f3f30-dirty #62 Hardware name: linux,dummy-virt (DT) pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO BTYPE=--) pc : kasan_check_range+0x90/0x1a0 lr : memcpy+0x88/0xf4 sp : ffff80001378fe20 ... Call trace: kasan_check_range+0x90/0x1a0 pcpu_page_first_chunk+0x3f0/0x568 setup_per_cpu_areas+0xb8/0x184 start_kernel+0x8c/0x328 The vm area used in vm_area_register_early() has no kasan shadow memory, Let's add a new kasan_populate_early_vm_area_shadow() function to populate the vm area shadow memory to fix the issue. [wangkefeng.wang@huawei.com: fix redefinition of 'kasan_populate_early_vm_area_shadow'] Link: https://lkml.kernel.org/r/20211011123211.3936196-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20210910053354.26721-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: Marco Elver [KASAN] Acked-by: Andrey Konovalov [KASAN] Acked-by: Catalin Marinas Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 736d7b458996..65487a3b2a71 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -436,6 +436,8 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); +void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); + #else /* CONFIG_KASAN_VMALLOC */ static inline int kasan_populate_vmalloc(unsigned long start, @@ -453,6 +455,10 @@ static inline void kasan_release_vmalloc(unsigned long start, unsigned long free_region_start, unsigned long free_region_end) {} +static inline void kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) +{ } + #endif /* CONFIG_KASAN_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ -- cgit v1.2.3 From c00b6b9610991c042ff4c3153daaa3ea8522c210 Mon Sep 17 00:00:00 2001 From: Chen Wandun Date: Fri, 5 Nov 2021 13:39:53 -0700 Subject: mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation Commit ffb29b1c255a ("mm/vmalloc: fix numa spreading for large hash tables") can cause significant performance regressions in some situations as Andrew mentioned in [1]. The main situation is vmalloc, vmalloc will allocate pages with NUMA_NO_NODE by default, that will result in alloc page one by one; In order to solve this, __alloc_pages_bulk and mempolicy should be considered at the same time. 1) If node is specified in memory allocation request, it will alloc all pages by __alloc_pages_bulk. 2) If interleaving allocate memory, it will cauculate how many pages should be allocated in each node, and use __alloc_pages_bulk to alloc pages in each node. [1]: https://lore.kernel.org/lkml/CALvZod4G3SzP3kWxQYn0fj+VgG-G3yWXz=gz17+3N57ru1iajw@mail.gmail.com/t/#m750c8e3231206134293b089feaa090590afa0f60 [akpm@linux-foundation.org: coding style fixes] [akpm@linux-foundation.org: make two functions static] [akpm@linux-foundation.org: fix CONFIG_NUMA=n build] Link: https://lkml.kernel.org/r/20211021080744.874701-3-chenwandun@huawei.com Signed-off-by: Chen Wandun Reviewed-by: Uladzislau Rezki (Sony) Cc: Eric Dumazet Cc: Shakeel Butt Cc: Nicholas Piggin Cc: Kefeng Wang Cc: Hanjun Guo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fbd4abc33f24..c1b262725dca 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -535,6 +535,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, struct list_head *page_list, struct page **page_array); +unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, + unsigned long nr_pages, + struct page **page_array); + /* Bulk allocate order-0 pages */ static inline unsigned long alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list) -- cgit v1.2.3 From 8ca1b5a49885f0c0c486544da46a9e0ac790831d Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Fri, 5 Nov 2021 13:40:34 -0700 Subject: mm/page_alloc: detect allocation forbidden by cpuset and bail out early There was a report that starting an Ubuntu in docker while using cpuset to bind it to movable nodes (a node only has movable zone, like a node for hotplug or a Persistent Memory node in normal usage) will fail due to memory allocation failure, and then OOM is involved and many other innocent processes got killed. It can be reproduced with command: $ docker run -it --rm --cpuset-mems 4 ubuntu:latest bash -c "grep Mems_allowed /proc/self/status" (where node 4 is a movable node) runc:[2:INIT] invoked oom-killer: gfp_mask=0x500cc2(GFP_HIGHUSER|__GFP_ACCOUNT), order=0, oom_score_adj=0 CPU: 8 PID: 8291 Comm: runc:[2:INIT] Tainted: G W I E 5.8.2-0.g71b519a-default #1 openSUSE Tumbleweed (unreleased) Hardware name: Dell Inc. PowerEdge R640/0PHYDR, BIOS 2.6.4 04/09/2020 Call Trace: dump_stack+0x6b/0x88 dump_header+0x4a/0x1e2 oom_kill_process.cold+0xb/0x10 out_of_memory.part.0+0xaf/0x230 out_of_memory+0x3d/0x80 __alloc_pages_slowpath.constprop.0+0x954/0xa20 __alloc_pages_nodemask+0x2d3/0x300 pipe_write+0x322/0x590 new_sync_write+0x196/0x1b0 vfs_write+0x1c3/0x1f0 ksys_write+0xa7/0xe0 do_syscall_64+0x52/0xd0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Mem-Info: active_anon:392832 inactive_anon:182 isolated_anon:0 active_file:68130 inactive_file:151527 isolated_file:0 unevictable:2701 dirty:0 writeback:7 slab_reclaimable:51418 slab_unreclaimable:116300 mapped:45825 shmem:735 pagetables:2540 bounce:0 free:159849484 free_pcp:73 free_cma:0 Node 4 active_anon:1448kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:0kB dirty:0kB writeback:0kB shmem:0kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 0kB writeback_tmp:0kB all_unreclaimable? no Node 4 Movable free:130021408kB min:9140kB low:139160kB high:269180kB reserved_highatomic:0KB active_anon:1448kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB writepending:0kB present:130023424kB managed:130023424kB mlocked:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:292kB local_pcp:84kB free_cma:0kB lowmem_reserve[]: 0 0 0 0 0 Node 4 Movable: 1*4kB (M) 0*8kB 0*16kB 1*32kB (M) 0*64kB 0*128kB 1*256kB (M) 1*512kB (M) 1*1024kB (M) 0*2048kB 31743*4096kB (M) = 130021156kB oom-kill:constraint=CONSTRAINT_CPUSET,nodemask=(null),cpuset=docker-9976a269caec812c134fa317f27487ee36e1129beba7278a463dd53e5fb9997b.scope,mems_allowed=4,global_oom,task_memcg=/system.slice/containerd.service,task=containerd,pid=4100,uid=0 Out of memory: Killed process 4100 (containerd) total-vm:4077036kB, anon-rss:51184kB, file-rss:26016kB, shmem-rss:0kB, UID:0 pgtables:676kB oom_score_adj:0 oom_reaper: reaped process 8248 (docker), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 2054 (node_exporter), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 1452 (systemd-journal), now anon-rss:0kB, file-rss:8564kB, shmem-rss:4kB oom_reaper: reaped process 2146 (munin-node), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 8291 (runc:[2:INIT]), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB The reason is that in this case, the target cpuset nodes only have movable zone, while the creation of an OS in docker sometimes needs to allocate memory in non-movable zones (dma/dma32/normal) like GFP_HIGHUSER, and the cpuset limit forbids the allocation, then out-of-memory killing is involved even when normal nodes and movable nodes both have many free memory. The OOM killer cannot help to resolve the situation as there is no usable memory for the request in the cpuset scope. The only reasonable measure to take is to fail the allocation right away and have the caller to deal with it. So add a check for cases like this in the slowpath of allocation, and bail out early returning NULL for the allocation. As page allocation is one of the hottest path in kernel, this check will hurt all users with sane cpuset configuration, add a static branch check and detect the abnormal config in cpuset memory binding setup so that the extra check cost in page allocation is not paid by everyone. [thanks to Micho Hocko and David Rientjes for suggesting not handling it inside OOM code, adding cpuset check, refining comments] Link: https://lkml.kernel.org/r/1632481657-68112-1-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Suggested-by: Michal Hocko Acked-by: Michal Hocko Cc: David Rientjes Cc: Tejun Heo Cc: Zefan Li Cc: Johannes Weiner Cc: Mel Gorman Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 17 +++++++++++++++++ include/linux/mmzone.h | 22 ++++++++++++++++++++++ 2 files changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d2b9c41c8edf..d58e0476ee8e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -34,6 +34,8 @@ */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; +extern struct static_key_false cpusets_insane_config_key; + static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); @@ -51,6 +53,19 @@ static inline void cpuset_dec(void) static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } +/* + * This will get enabled whenever a cpuset configuration is considered + * unsupportable in general. E.g. movable only node which cannot satisfy + * any non movable allocations (see update_nodemask). Page allocator + * needs to make additional checks for those configurations and this + * check is meant to guard those checks without any overhead for sane + * configurations. + */ +static inline bool cpusets_insane_config(void) +{ + return static_branch_unlikely(&cpusets_insane_config_key); +} + extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); @@ -167,6 +182,8 @@ static inline void set_mems_allowed(nodemask_t nodemask) static inline bool cpusets_enabled(void) { return false; } +static inline bool cpusets_insane_config(void) { return false; } + static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 832aa49d0d8e..fb36a29e3aae 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1220,6 +1220,28 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) +/* Whether the 'nodes' are all movable nodes */ +static inline bool movable_only_nodes(nodemask_t *nodes) +{ + struct zonelist *zonelist; + struct zoneref *z; + int nid; + + if (nodes_empty(*nodes)) + return false; + + /* + * We can chose arbitrary node from the nodemask to get a + * zonelist as they are interlinked. We just need to find + * at least one zone that can satisfy kernel allocations. + */ + nid = first_node(*nodes); + zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; + z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); + return (!z->zone) ? true : false; +} + + #ifdef CONFIG_SPARSEMEM #include #endif -- cgit v1.2.3 From d2635f2012a44e3d469ab9a4022162dbe0e53f21 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 5 Nov 2021 13:40:40 -0700 Subject: mm: create a new system state and fix core_kernel_text() core_kernel_text() considers that until system_state in at least SYSTEM_RUNNING, init memory is valid. But init memory is freed a few lines before setting SYSTEM_RUNNING, so we have a small period of time when core_kernel_text() is wrong. Create an intermediate system state called SYSTEM_FREEING_INIT that is set before starting freeing init memory, and use it in core_kernel_text() to report init memory invalid earlier. Link: https://lkml.kernel.org/r/9ecfdee7dd4d741d172cb93ff1d87f1c58127c9a.1633001016.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Gerald Schaefer Cc: Kefeng Wang Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2776423a587e..471bc0593679 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -248,6 +248,7 @@ extern bool early_boot_irqs_disabled; extern enum system_states { SYSTEM_BOOTING, SYSTEM_SCHEDULING, + SYSTEM_FREEING_INITMEM, SYSTEM_RUNNING, SYSTEM_HALT, SYSTEM_POWER_OFF, -- cgit v1.2.3 From 477d01fce8dacb41cae9363136ea56812e8baa59 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:40:58 -0700 Subject: mm: fix data race in PagePoisoned() PagePoisoned() accesses page->flags which can be updated concurrently: | BUG: KCSAN: data-race in next_uptodate_page / unlock_page | | write (marked) to 0xffffea00050f37c0 of 8 bytes by task 1872 on cpu 1: | instrument_atomic_write include/linux/instrumented.h:87 [inline] | clear_bit_unlock_is_negative_byte include/asm-generic/bitops/instrumented-lock.h:74 [inline] | unlock_page+0x102/0x1b0 mm/filemap.c:1465 | filemap_map_pages+0x6c6/0x890 mm/filemap.c:3057 | ... | read to 0xffffea00050f37c0 of 8 bytes by task 1873 on cpu 0: | PagePoisoned include/linux/page-flags.h:204 [inline] | PageReadahead include/linux/page-flags.h:382 [inline] | next_uptodate_page+0x456/0x830 mm/filemap.c:2975 | ... | CPU: 0 PID: 1873 Comm: systemd-udevd Not tainted 5.11.0-rc4-00001-gf9ce0be71d1f #1 To avoid the compiler tearing or otherwise optimizing the access, use READ_ONCE() to access flags. Link: https://lore.kernel.org/all/20210826144157.GA26950@xsang-OptiPlex-9020/ Link: https://lkml.kernel.org/r/20210913113542.2658064-1-elver@google.com Reported-by: kernel test robot Signed-off-by: Marco Elver Acked-by: Kirill A. Shutemov Acked-by: Will Deacon Cc: Marco Elver Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index fbfd3fad48f2..dd80cf0bb579 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -215,7 +215,7 @@ static __always_inline int PageCompound(struct page *page) #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { - return page->flags == PAGE_POISON_PATTERN; + return READ_ONCE(page->flags) == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM -- cgit v1.2.3 From 73c54763482b841d9c14bad87eec98f80f700e0b Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 5 Nov 2021 13:41:17 -0700 Subject: mm/hugetlb: drop __unmap_hugepage_range definition from hugetlb.h Remove __unmap_hugepage_range() from the header file, because it is only used in hugetlb.c. Link: https://lkml.kernel.org/r/20210917165108.9341-1-peterx@redhat.com Signed-off-by: Peter Xu Suggested-by: Mike Kravetz Reviewed-by: Mike Kravetz Reviewed-by: John Hubbard Reviewed-by: Muchun Song Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 1faebe1cd0ed..3cbf60464398 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -143,9 +143,6 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page); -void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct page *ref_page); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo(void); @@ -385,13 +382,6 @@ static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, BUG(); } -static inline void __unmap_hugepage_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) -{ - BUG(); -} - static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) -- cgit v1.2.3 From 79dfc695525f60c8410015362b8aa4eb5c57210c Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:20 -0700 Subject: hugetlb: add demote hugetlb page sysfs interfaces Patch series "hugetlb: add demote/split page functionality", v4. The concurrent use of multiple hugetlb page sizes on a single system is becoming more common. One of the reasons is better TLB support for gigantic page sizes on x86 hardware. In addition, hugetlb pages are being used to back VMs in hosting environments. When using hugetlb pages to back VMs, it is often desirable to preallocate hugetlb pools. This avoids the delay and uncertainty of allocating hugetlb pages at VM startup. In addition, preallocating huge pages minimizes the issue of memory fragmentation that increases the longer the system is up and running. In such environments, a combination of larger and smaller hugetlb pages are preallocated in anticipation of backing VMs of various sizes. Over time, the preallocated pool of smaller hugetlb pages may become depleted while larger hugetlb pages still remain. In such situations, it is desirable to convert larger hugetlb pages to smaller hugetlb pages. Converting larger to smaller hugetlb pages can be accomplished today by first freeing the larger page to the buddy allocator and then allocating the smaller pages. For example, to convert 50 GB pages on x86: gb_pages=`cat .../hugepages-1048576kB/nr_hugepages` m2_pages=`cat .../hugepages-2048kB/nr_hugepages` echo $(($gb_pages - 50)) > .../hugepages-1048576kB/nr_hugepages echo $(($m2_pages + 25600)) > .../hugepages-2048kB/nr_hugepages On an idle system this operation is fairly reliable and results are as expected. The number of 2MB pages is increased as expected and the time of the operation is a second or two. However, when there is activity on the system the following issues arise: 1) This process can take quite some time, especially if allocation of the smaller pages is not immediate and requires migration/compaction. 2) There is no guarantee that the total size of smaller pages allocated will match the size of the larger page which was freed. This is because the area freed by the larger page could quickly be fragmented. In a test environment with a load that continually fills the page cache with clean pages, results such as the following can be observed: Unexpected number of 2MB pages allocated: Expected 25600, have 19944 real 0m42.092s user 0m0.008s sys 0m41.467s To address these issues, introduce the concept of hugetlb page demotion. Demotion provides a means of 'in place' splitting of a hugetlb page to pages of a smaller size. This avoids freeing pages to buddy and then trying to allocate from buddy. Page demotion is controlled via sysfs files that reside in the per-hugetlb page size and per node directories. - demote_size Target page size for demotion, a smaller huge page size. File can be written to chose a smaller huge page size if multiple are available. - demote Writable number of hugetlb pages to be demoted To demote 50 GB huge pages, one would: cat .../hugepages-1048576kB/free_hugepages /* optional, verify free pages */ cat .../hugepages-1048576kB/demote_size /* optional, verify target size */ echo 50 > .../hugepages-1048576kB/demote Only hugetlb pages which are free at the time of the request can be demoted. Demotion does not add to the complexity of surplus pages and honors reserved huge pages. Therefore, when a value is written to the sysfs demote file, that value is only the maximum number of pages which will be demoted. It is possible fewer will actually be demoted. The recently introduced per-hstate mutex is used to synchronize demote operations with other operations that modify hugetlb pools. Real world use cases -------------------- The above scenario describes a real world use case where hugetlb pages are used to back VMs on x86. Both issues of long allocation times and not necessarily getting the expected number of smaller huge pages after a free and allocate cycle have been experienced. The occurrence of these issues is dependent on other activity within the host and can not be predicted. This patch (of 5): Two new sysfs files are added to demote hugtlb pages. These files are both per-hugetlb page size and per node. Files are: demote_size - The size in Kb that pages are demoted to. (read-write) demote - The number of huge pages to demote. (write-only) By default, demote_size is the next smallest huge page size. Valid huge page sizes less than huge page size may be written to this file. When huge pages are demoted, they are demoted to this size. Writing a value to demote will result in an attempt to demote that number of hugetlb pages to an appropriate number of demote_size pages. NOTE: Demote interfaces are only provided for huge page sizes if there is a smaller target demote huge page size. For example, on x86 1GB huge pages will have demote interfaces. 2MB huge pages will not have demote interfaces. This patch does not provide full demote functionality. It only provides the sysfs interfaces. It also provides documentation for the new interfaces. [mike.kravetz@oracle.com: n_mask initialization does not need to be protected by the mutex] Link: https://lkml.kernel.org/r/0530e4ef-2492-5186-f919-5db68edea654@oracle.com Link: https://lkml.kernel.org/r/20211007181918.136982-2-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Cc: David Hildenbrand Cc: Michal Hocko Cc: Zi Yan Cc: Muchun Song Cc: Naoya Horiguchi Cc: David Rientjes Cc: "Aneesh Kumar K . V" Cc: Nghia Le Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3cbf60464398..2bddd6c38204 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -586,6 +586,7 @@ struct hstate { int next_nid_to_alloc; int next_nid_to_free; unsigned int order; + unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; -- cgit v1.2.3 From 9871e2ded6c1ff61a59988d7a0e975f012105d52 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:23 -0700 Subject: mm/cma: add cma_pages_valid to determine if pages are in CMA Add new interface cma_pages_valid() which indicates if the specified pages are part of a CMA region. This interface will be used in a subsequent patch by hugetlb code. In order to keep the same amount of DEBUG information, a pr_debug() call was added to cma_pages_valid(). In the case where the page passed to cma_release is not in cma region, the debug message will be printed from cma_pages_valid as opposed to cma_release. Link: https://lkml.kernel.org/r/20211007181918.136982-3-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: "Aneesh Kumar K . V" Cc: David Rientjes Cc: Michal Hocko Cc: Muchun Song Cc: Naoya Horiguchi Cc: Nghia Le Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cma.h b/include/linux/cma.h index 53fd8c3cdbd0..bd801023504b 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -46,6 +46,7 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, struct cma **res_cma); extern struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align, bool no_warn); +extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned long count); extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); -- cgit v1.2.3 From bd3400ea173fb611cdf2030d03620185ff6c0b0e Mon Sep 17 00:00:00 2001 From: Liangcai Fan Date: Fri, 5 Nov 2021 13:41:36 -0700 Subject: mm: khugepaged: recalculate min_free_kbytes after stopping khugepaged When initializing transparent huge pages, min_free_kbytes would be calculated according to what khugepaged expected. So when transparent huge pages get disabled, min_free_kbytes should be recalculated instead of the higher value set by khugepaged. Link: https://lkml.kernel.org/r/1633937809-16558-1-git-send-email-liangcaifan19@gmail.com Signed-off-by: Liangcai Fan Signed-off-by: Chunyan Zhang Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6e29deb1e0d4..7e37c726b9db 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2453,6 +2453,7 @@ extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); extern void setup_per_zone_wmarks(void); +extern void calculate_min_free_kbytes(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); -- cgit v1.2.3 From 550a7d60bd5e35a56942dba6d8a26752beb26c9f Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Fri, 5 Nov 2021 13:41:40 -0700 Subject: mm, hugepages: add mremap() support for hugepage backed vma Support mremap() for hugepage backed vma segment by simply repositioning page table entries. The page table entries are repositioned to the new virtual address on mremap(). Hugetlb mremap() support is of course generic; my motivating use case is a library (hugepage_text), which reloads the ELF text of executables in hugepages. This significantly increases the execution performance of said executables. Restrict the mremap operation on hugepages to up to the size of the original mapping as the underlying hugetlb reservation is not yet capable of handling remapping to a larger size. During the mremap() operation we detect pmd_share'd mappings and we unshare those during the mremap(). On access and fault the sharing is established again. Link: https://lkml.kernel.org/r/20211013195825.3058275-1-almasrymina@google.com Signed-off-by: Mina Almasry Reviewed-by: Mike Kravetz Cc: Ken Chen Cc: Chris Kennelly Cc: Michal Hocko Cc: Vlastimil Babka Cc: Kirill Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2bddd6c38204..c0a20781b28e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -124,6 +124,7 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, void hugepage_put_subpool(struct hugepage_subpool *spool); void reset_vma_resv_huge_pages(struct vm_area_struct *vma); +void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, loff_t *); @@ -132,6 +133,10 @@ int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, unsigned long new_addr, + unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, @@ -215,6 +220,10 @@ static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { } +static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) +{ +} + static inline unsigned long hugetlb_total_pages(void) { return 0; @@ -262,6 +271,16 @@ static inline int copy_hugetlb_page_range(struct mm_struct *dst, return 0; } +static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, + unsigned long new_addr, + unsigned long len) +{ + BUG(); + return 0; +} + static inline void hugetlb_report_meminfo(struct seq_file *m) { } -- cgit v1.2.3 From 8cd7c588decf470bf7e14f2be93b709f839a965e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:25 -0700 Subject: mm/vmscan: throttle reclaim until some writeback completes if congested Patch series "Remove dependency on congestion_wait in mm/", v5. This series that removes all calls to congestion_wait in mm/ and deletes wait_iff_congested. It's not a clever implementation but congestion_wait has been broken for a long time [1]. Even if congestion throttling worked, it was never a great idea. While excessive dirty/writeback pages at the tail of the LRU is one possibility that reclaim may be slow, there is also the problem of too many pages being isolated and reclaim failing for other reasons (elevated references, too many pages isolated, excessive LRU contention etc). This series replaces the "congestion" throttling with 3 different types. - If there are too many dirty/writeback pages, sleep until a timeout or enough pages get cleaned - If too many pages are isolated, sleep until enough isolated pages are either reclaimed or put back on the LRU - If no progress is being made, direct reclaim tasks sleep until another task makes progress with acceptable efficiency. This was initially tested with a mix of workloads that used to trigger corner cases that no longer work. A new test case was created called "stutterp" (pagereclaim-stutterp-noreaders in mmtests) using a freshly created XFS filesystem. Note that it may be necessary to increase the timeout of ssh if executing remotely as ssh itself can get throttled and the connection may timeout. stutterp varies the number of "worker" processes from 4 up to NR_CPUS*4 to check the impact as the number of direct reclaimers increase. It has four types of worker. - One "anon latency" worker creates small mappings with mmap() and times how long it takes to fault the mapping reading it 4K at a time - X file writers which is fio randomly writing X files where the total size of the files add up to the allowed dirty_ratio. fio is allowed to run for a warmup period to allow some file-backed pages to accumulate. The duration of the warmup is based on the best-case linear write speed of the storage. - Y file readers which is fio randomly reading small files - Z anon memory hogs which continually map (100-dirty_ratio)% of memory - Total estimated WSS = (100+dirty_ration) percentage of memory X+Y+Z+1 == NR_WORKERS varying from 4 up to NR_CPUS*4 The intent is to maximise the total WSS with a mix of file and anon memory where some anonymous memory must be swapped and there is a high likelihood of dirty/writeback pages reaching the end of the LRU. The test can be configured to have no background readers to stress dirty/writeback pages. The results below are based on having zero readers. The short summary of the results is that the series works and stalls until some event occurs but the timeouts may need adjustment. The test results are not broken down by patch as the series should be treated as one block that replaces a broken throttling mechanism with a working one. Finally, three machines were tested but I'm reporting the worst set of results. The other two machines had much better latencies for example. First the results of the "anon latency" latency stutterp 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r4 Amean mmap-4 31.4003 ( 0.00%) 2661.0198 (-8374.52%) Amean mmap-7 38.1641 ( 0.00%) 149.2891 (-291.18%) Amean mmap-12 60.0981 ( 0.00%) 187.8105 (-212.51%) Amean mmap-21 161.2699 ( 0.00%) 213.9107 ( -32.64%) Amean mmap-30 174.5589 ( 0.00%) 377.7548 (-116.41%) Amean mmap-48 8106.8160 ( 0.00%) 1070.5616 ( 86.79%) Stddev mmap-4 41.3455 ( 0.00%) 27573.9676 (-66591.66%) Stddev mmap-7 53.5556 ( 0.00%) 4608.5860 (-8505.23%) Stddev mmap-12 171.3897 ( 0.00%) 5559.4542 (-3143.75%) Stddev mmap-21 1506.6752 ( 0.00%) 5746.2507 (-281.39%) Stddev mmap-30 557.5806 ( 0.00%) 7678.1624 (-1277.05%) Stddev mmap-48 61681.5718 ( 0.00%) 14507.2830 ( 76.48%) Max-90 mmap-4 31.4243 ( 0.00%) 83.1457 (-164.59%) Max-90 mmap-7 41.0410 ( 0.00%) 41.0720 ( -0.08%) Max-90 mmap-12 66.5255 ( 0.00%) 53.9073 ( 18.97%) Max-90 mmap-21 146.7479 ( 0.00%) 105.9540 ( 27.80%) Max-90 mmap-30 193.9513 ( 0.00%) 64.3067 ( 66.84%) Max-90 mmap-48 277.9137 ( 0.00%) 591.0594 (-112.68%) Max mmap-4 1913.8009 ( 0.00%) 299623.9695 (-15555.96%) Max mmap-7 2423.9665 ( 0.00%) 204453.1708 (-8334.65%) Max mmap-12 6845.6573 ( 0.00%) 221090.3366 (-3129.64%) Max mmap-21 56278.6508 ( 0.00%) 213877.3496 (-280.03%) Max mmap-30 19716.2990 ( 0.00%) 216287.6229 (-997.00%) Max mmap-48 477923.9400 ( 0.00%) 245414.8238 ( 48.65%) For most thread counts, the time to mmap() is unfortunately increased. In earlier versions of the series, this was lower but a large number of throttling events were reaching their timeout increasing the amount of inefficient scanning of the LRU. There is no prioritisation of reclaim tasks making progress based on each tasks rate of page allocation versus progress of reclaim. The variance is also impacted for high worker counts but in all cases, the differences in latency are not statistically significant due to very large maximum outliers. Max-90 shows that 90% of the stalls are comparable but the Max results show the massive outliers which are increased to to stalling. It is expected that this will be very machine dependant. Due to the test design, reclaim is difficult so allocations stall and there are variances depending on whether THPs can be allocated or not. The amount of memory will affect exactly how bad the corner cases are and how often they trigger. The warmup period calculation is not ideal as it's based on linear writes where as fio is randomly writing multiple files from multiple tasks so the start state of the test is variable. For example, these are the latencies on a single-socket machine that had more memory Amean mmap-4 42.2287 ( 0.00%) 49.6838 * -17.65%* Amean mmap-7 216.4326 ( 0.00%) 47.4451 * 78.08%* Amean mmap-12 2412.0588 ( 0.00%) 51.7497 ( 97.85%) Amean mmap-21 5546.2548 ( 0.00%) 51.8862 ( 99.06%) Amean mmap-30 1085.3121 ( 0.00%) 72.1004 ( 93.36%) The overall system CPU usage and elapsed time is as follows 5.15.0-rc3 5.15.0-rc3 vanilla mm-reclaimcongest-v5r4 Duration User 6989.03 983.42 Duration System 7308.12 799.68 Duration Elapsed 2277.67 2092.98 The patches reduce system CPU usage by 89% as the vanilla kernel is rarely stalling. The high-level /proc/vmstats show 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r2 Ops Direct pages scanned 1056608451.00 503594991.00 Ops Kswapd pages scanned 109795048.00 147289810.00 Ops Kswapd pages reclaimed 63269243.00 31036005.00 Ops Direct pages reclaimed 10803973.00 6328887.00 Ops Kswapd efficiency % 57.62 21.07 Ops Kswapd velocity 48204.98 57572.86 Ops Direct efficiency % 1.02 1.26 Ops Direct velocity 463898.83 196845.97 Kswapd scanned less pages but the detailed pattern is different. The vanilla kernel scans slowly over time where as the patches exhibits burst patterns of scan activity. Direct reclaim scanning is reduced by 52% due to stalling. The pattern for stealing pages is also slightly different. Both kernels exhibit spikes but the vanilla kernel when reclaiming shows pages being reclaimed over a period of time where as the patches tend to reclaim in spikes. The difference is that vanilla is not throttling and instead scanning constantly finding some pages over time where as the patched kernel throttles and reclaims in spikes. Ops Percentage direct scans 90.59 77.37 For direct reclaim, vanilla scanned 90.59% of pages where as with the patches, 77.37% were direct reclaim due to throttling Ops Page writes by reclaim 2613590.00 1687131.00 Page writes from reclaim context are reduced. Ops Page writes anon 2932752.00 1917048.00 And there is less swapping. Ops Page reclaim immediate 996248528.00 107664764.00 The number of pages encountered at the tail of the LRU tagged for immediate reclaim but still dirty/writeback is reduced by 89%. Ops Slabs scanned 164284.00 153608.00 Slab scan activity is similar. ftrace was used to gather stall activity Vanilla ------- 1 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=16000 2 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=12000 8 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=8000 29 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=4000 82394 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=0 The fast majority of wait_iff_congested calls do not stall at all. What is likely happening is that cond_resched() reschedules the task for a short period when the BDI is not registering congestion (which it never will in this test setup). 1 writeback_congestion_wait: usec_timeout=100000 usec_delayed=120000 2 writeback_congestion_wait: usec_timeout=100000 usec_delayed=132000 4 writeback_congestion_wait: usec_timeout=100000 usec_delayed=112000 380 writeback_congestion_wait: usec_timeout=100000 usec_delayed=108000 778 writeback_congestion_wait: usec_timeout=100000 usec_delayed=104000 congestion_wait if called always exceeds the timeout as there is no trigger to wake it up. Bottom line: Vanilla will throttle but it's not effective. Patch series ------------ Kswapd throttle activity was always due to scanning pages tagged for immediate reclaim at the tail of the LRU 1 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 4 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 94 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 112 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK The majority of events did not stall or stalled for a short period. Roughly 16% of stalls reached the timeout before expiry. For direct reclaim, the number of times stalled for each reason were 6624 reason=VMSCAN_THROTTLE_ISOLATED 93246 reason=VMSCAN_THROTTLE_NOPROGRESS 96934 reason=VMSCAN_THROTTLE_WRITEBACK The most common reason to stall was due to excessive pages tagged for immediate reclaim at the tail of the LRU followed by a failure to make forward. A relatively small number were due to too many pages isolated from the LRU by parallel threads For VMSCAN_THROTTLE_ISOLATED, the breakdown of delays was 9 usec_timeout=20000 usect_delayed=4000 reason=VMSCAN_THROTTLE_ISOLATED 12 usec_timeout=20000 usect_delayed=16000 reason=VMSCAN_THROTTLE_ISOLATED 83 usec_timeout=20000 usect_delayed=20000 reason=VMSCAN_THROTTLE_ISOLATED 6520 usec_timeout=20000 usect_delayed=0 reason=VMSCAN_THROTTLE_ISOLATED Most did not stall at all. A small number reached the timeout. For VMSCAN_THROTTLE_NOPROGRESS, the breakdown of stalls were all over the map 1 usec_timeout=500000 usect_delayed=324000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=332000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=348000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=360000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=228000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=260000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=340000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=364000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=372000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=428000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=460000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=464000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=244000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=252000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=272000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=188000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=268000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=328000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=380000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=392000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=432000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=204000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=220000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=412000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=436000 reason=VMSCAN_THROTTLE_NOPROGRESS 6 usec_timeout=500000 usect_delayed=488000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=212000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=300000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=316000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=472000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=248000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=356000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=456000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=124000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=376000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=484000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=172000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=420000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=452000 reason=VMSCAN_THROTTLE_NOPROGRESS 11 usec_timeout=500000 usect_delayed=256000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=112000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=116000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=144000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=152000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=264000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=384000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=424000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=492000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=184000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=444000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=308000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=440000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=476000 reason=VMSCAN_THROTTLE_NOPROGRESS 16 usec_timeout=500000 usect_delayed=140000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=232000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=240000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=280000 reason=VMSCAN_THROTTLE_NOPROGRESS 18 usec_timeout=500000 usect_delayed=404000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=148000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=216000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=468000 reason=VMSCAN_THROTTLE_NOPROGRESS 21 usec_timeout=500000 usect_delayed=448000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=168000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=296000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=132000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=352000 reason=VMSCAN_THROTTLE_NOPROGRESS 26 usec_timeout=500000 usect_delayed=180000 reason=VMSCAN_THROTTLE_NOPROGRESS 27 usec_timeout=500000 usect_delayed=284000 reason=VMSCAN_THROTTLE_NOPROGRESS 28 usec_timeout=500000 usect_delayed=164000 reason=VMSCAN_THROTTLE_NOPROGRESS 29 usec_timeout=500000 usect_delayed=136000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=200000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=400000 reason=VMSCAN_THROTTLE_NOPROGRESS 31 usec_timeout=500000 usect_delayed=196000 reason=VMSCAN_THROTTLE_NOPROGRESS 32 usec_timeout=500000 usect_delayed=156000 reason=VMSCAN_THROTTLE_NOPROGRESS 33 usec_timeout=500000 usect_delayed=224000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=128000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=176000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=368000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=496000 reason=VMSCAN_THROTTLE_NOPROGRESS 37 usec_timeout=500000 usect_delayed=312000 reason=VMSCAN_THROTTLE_NOPROGRESS 38 usec_timeout=500000 usect_delayed=304000 reason=VMSCAN_THROTTLE_NOPROGRESS 40 usec_timeout=500000 usect_delayed=288000 reason=VMSCAN_THROTTLE_NOPROGRESS 43 usec_timeout=500000 usect_delayed=408000 reason=VMSCAN_THROTTLE_NOPROGRESS 55 usec_timeout=500000 usect_delayed=416000 reason=VMSCAN_THROTTLE_NOPROGRESS 56 usec_timeout=500000 usect_delayed=76000 reason=VMSCAN_THROTTLE_NOPROGRESS 58 usec_timeout=500000 usect_delayed=120000 reason=VMSCAN_THROTTLE_NOPROGRESS 59 usec_timeout=500000 usect_delayed=208000 reason=VMSCAN_THROTTLE_NOPROGRESS 61 usec_timeout=500000 usect_delayed=68000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=192000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=480000 reason=VMSCAN_THROTTLE_NOPROGRESS 79 usec_timeout=500000 usect_delayed=60000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=320000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=92000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=64000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=80000 reason=VMSCAN_THROTTLE_NOPROGRESS 88 usec_timeout=500000 usect_delayed=84000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=160000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=292000 reason=VMSCAN_THROTTLE_NOPROGRESS 94 usec_timeout=500000 usect_delayed=56000 reason=VMSCAN_THROTTLE_NOPROGRESS 118 usec_timeout=500000 usect_delayed=88000 reason=VMSCAN_THROTTLE_NOPROGRESS 119 usec_timeout=500000 usect_delayed=72000 reason=VMSCAN_THROTTLE_NOPROGRESS 126 usec_timeout=500000 usect_delayed=108000 reason=VMSCAN_THROTTLE_NOPROGRESS 146 usec_timeout=500000 usect_delayed=52000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=36000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=48000 reason=VMSCAN_THROTTLE_NOPROGRESS 159 usec_timeout=500000 usect_delayed=28000 reason=VMSCAN_THROTTLE_NOPROGRESS 178 usec_timeout=500000 usect_delayed=44000 reason=VMSCAN_THROTTLE_NOPROGRESS 183 usec_timeout=500000 usect_delayed=40000 reason=VMSCAN_THROTTLE_NOPROGRESS 237 usec_timeout=500000 usect_delayed=100000 reason=VMSCAN_THROTTLE_NOPROGRESS 266 usec_timeout=500000 usect_delayed=32000 reason=VMSCAN_THROTTLE_NOPROGRESS 313 usec_timeout=500000 usect_delayed=24000 reason=VMSCAN_THROTTLE_NOPROGRESS 347 usec_timeout=500000 usect_delayed=96000 reason=VMSCAN_THROTTLE_NOPROGRESS 470 usec_timeout=500000 usect_delayed=20000 reason=VMSCAN_THROTTLE_NOPROGRESS 559 usec_timeout=500000 usect_delayed=16000 reason=VMSCAN_THROTTLE_NOPROGRESS 964 usec_timeout=500000 usect_delayed=12000 reason=VMSCAN_THROTTLE_NOPROGRESS 2001 usec_timeout=500000 usect_delayed=104000 reason=VMSCAN_THROTTLE_NOPROGRESS 2447 usec_timeout=500000 usect_delayed=8000 reason=VMSCAN_THROTTLE_NOPROGRESS 7888 usec_timeout=500000 usect_delayed=4000 reason=VMSCAN_THROTTLE_NOPROGRESS 22727 usec_timeout=500000 usect_delayed=0 reason=VMSCAN_THROTTLE_NOPROGRESS 51305 usec_timeout=500000 usect_delayed=500000 reason=VMSCAN_THROTTLE_NOPROGRESS The full timeout is often hit but a large number also do not stall at all. The remainder slept a little allowing other reclaim tasks to make progress. While this timeout could be further increased, it could also negatively impact worst-case behaviour when there is no prioritisation of what task should make progress. For VMSCAN_THROTTLE_WRITEBACK, the breakdown was 1 usec_timeout=100000 usect_delayed=44000 reason=VMSCAN_THROTTLE_WRITEBACK 2 usec_timeout=100000 usect_delayed=76000 reason=VMSCAN_THROTTLE_WRITEBACK 3 usec_timeout=100000 usect_delayed=80000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=48000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=84000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 7 usec_timeout=100000 usect_delayed=88000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=56000 reason=VMSCAN_THROTTLE_WRITEBACK 12 usec_timeout=100000 usect_delayed=64000 reason=VMSCAN_THROTTLE_WRITEBACK 16 usec_timeout=100000 usect_delayed=92000 reason=VMSCAN_THROTTLE_WRITEBACK 24 usec_timeout=100000 usect_delayed=68000 reason=VMSCAN_THROTTLE_WRITEBACK 28 usec_timeout=100000 usect_delayed=32000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=60000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=96000 reason=VMSCAN_THROTTLE_WRITEBACK 32 usec_timeout=100000 usect_delayed=52000 reason=VMSCAN_THROTTLE_WRITEBACK 42 usec_timeout=100000 usect_delayed=40000 reason=VMSCAN_THROTTLE_WRITEBACK 77 usec_timeout=100000 usect_delayed=28000 reason=VMSCAN_THROTTLE_WRITEBACK 99 usec_timeout=100000 usect_delayed=36000 reason=VMSCAN_THROTTLE_WRITEBACK 137 usec_timeout=100000 usect_delayed=24000 reason=VMSCAN_THROTTLE_WRITEBACK 190 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 339 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 518 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 852 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 3359 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK 7147 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 83962 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK The majority hit the timeout in direct reclaim context although a sizable number did not stall at all. This is very different to kswapd where only a tiny percentage of stalls due to writeback reached the timeout. Bottom line, the throttling appears to work and the wakeup events may limit worst case stalls. There might be some grounds for adjusting timeouts but it's likely futile as the worst-case scenarios depend on the workload, memory size and the speed of the storage. A better approach to improve the series further would be to prioritise tasks based on their rate of allocation with the caveat that it may be very expensive to track. This patch (of 5): Page reclaim throttles on wait_iff_congested under the following conditions: - kswapd is encountering pages under writeback and marked for immediate reclaim implying that pages are cycling through the LRU faster than pages can be cleaned. - Direct reclaim will stall if all dirty pages are backed by congested inodes. wait_iff_congested is almost completely broken with few exceptions. This patch adds a new node-based workqueue and tracks the number of throttled tasks and pages written back since throttling started. If enough pages belonging to the node are written back then the throttled tasks will wake early. If not, the throttled tasks sleeps until the timeout expires. [neilb@suse.de: Uninterruptible sleep and simpler wakeups] [hdanton@sina.com: Avoid race when reclaim starts] [vbabka@suse.cz: vmstat irq-safe api, clarifications] Link: https://lore.kernel.org/linux-mm/45d8b7a6-8548-65f5-cccf-9f451d4ae3d4@kernel.dk/ [1] Link: https://lkml.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20211022144651.19914-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: NeilBrown Cc: "Theodore Ts'o" Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Matthew Wilcox Cc: Michal Hocko Cc: Dave Chinner Cc: Rik van Riel Cc: Johannes Weiner Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 1 - include/linux/mmzone.h | 13 +++++++++++++ 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ac7f231b8825..9fb1f0ae273c 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -154,7 +154,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) } long congestion_wait(int sync, long timeout); -long wait_iff_congested(int sync, long timeout); static inline bool mapping_can_writeback(struct address_space *mapping) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fb36a29e3aae..5a5e19b90dab 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -199,6 +199,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ @@ -272,6 +273,11 @@ enum lru_list { NR_LRU_LISTS }; +enum vmscan_throttle_state { + VMSCAN_THROTTLE_WRITEBACK, + NR_VMSCAN_THROTTLE, +}; + #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) @@ -841,6 +847,13 @@ typedef struct pglist_data { int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; + + /* workqueues for throttling reclaim for different reasons. */ + wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; + + atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ + unsigned long nr_reclaim_start; /* nr pages written while throttled + * when throttling started. */ struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; -- cgit v1.2.3 From d818fca1cac31b1fc9301bda83e195a46fb4ebaa Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:29 -0700 Subject: mm/vmscan: throttle reclaim and compaction when too may pages are isolated Page reclaim throttles on congestion if too many parallel reclaim instances have isolated too many pages. This makes no sense, excessive parallelisation has nothing to do with writeback or congestion. This patch creates an additional workqueue to sleep on when too many pages are isolated. The throttled tasks are woken when the number of isolated pages is reduced or a timeout occurs. There may be some false positive wakeups for GFP_NOIO/GFP_NOFS callers but the tasks will throttle again if necessary. [shy828301@gmail.com: Wake up from compaction context] [vbabka@suse.cz: Account number of throttled tasks only for writeback] Link: https://lkml.kernel.org/r/20211022144651.19914-3-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5a5e19b90dab..312c1ea9aafa 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -275,6 +275,7 @@ enum lru_list { enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, + VMSCAN_THROTTLE_ISOLATED, NR_VMSCAN_THROTTLE, }; -- cgit v1.2.3 From 69392a403f49e6e33f9dfb1d6edb87c8006f83c2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:32 -0700 Subject: mm/vmscan: throttle reclaim when no progress is being made Memcg reclaim throttles on congestion if no reclaim progress is made. This makes little sense, it might be due to writeback or a host of other factors. For !memcg reclaim, it's messy. Direct reclaim primarily is throttled in the page allocator if it is failing to make progress. Kswapd throttles if too many pages are under writeback and marked for immediate reclaim. This patch explicitly throttles if reclaim is failing to make progress. [vbabka@suse.cz: Remove redundant code] Link: https://lkml.kernel.org/r/20211022144651.19914-4-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 312c1ea9aafa..58e744b78c2c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -276,6 +276,7 @@ enum lru_list { enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, + VMSCAN_THROTTLE_NOPROGRESS, NR_VMSCAN_THROTTLE, }; -- cgit v1.2.3 From 7e6ec49c18988f1b8dab0677271dafde5f8d9a43 Mon Sep 17 00:00:00 2001 From: Yuanzheng Song Date: Fri, 5 Nov 2021 13:42:52 -0700 Subject: mm/vmpressure: fix data-race with memcg->socket_pressure When reading memcg->socket_pressure in mem_cgroup_under_socket_pressure() and writing memcg->socket_pressure in vmpressure() at the same time, the following data-race occurs: BUG: KCSAN: data-race in __sk_mem_reduce_allocated / vmpressure write to 0xffff8881286f4938 of 8 bytes by task 24550 on cpu 3: vmpressure+0x218/0x230 mm/vmpressure.c:307 shrink_node_memcgs+0x2b9/0x410 mm/vmscan.c:2658 shrink_node+0x9d2/0x11d0 mm/vmscan.c:2769 shrink_zones+0x29f/0x470 mm/vmscan.c:2972 do_try_to_free_pages+0x193/0x6e0 mm/vmscan.c:3027 try_to_free_mem_cgroup_pages+0x1c0/0x3f0 mm/vmscan.c:3345 reclaim_high mm/memcontrol.c:2440 [inline] mem_cgroup_handle_over_high+0x18b/0x4d0 mm/memcontrol.c:2624 tracehook_notify_resume include/linux/tracehook.h:197 [inline] exit_to_user_mode_loop kernel/entry/common.c:164 [inline] exit_to_user_mode_prepare+0x110/0x170 kernel/entry/common.c:191 syscall_exit_to_user_mode+0x16/0x30 kernel/entry/common.c:266 ret_from_fork+0x15/0x30 arch/x86/entry/entry_64.S:289 read to 0xffff8881286f4938 of 8 bytes by interrupt on cpu 1: mem_cgroup_under_socket_pressure include/linux/memcontrol.h:1483 [inline] sk_under_memory_pressure include/net/sock.h:1314 [inline] __sk_mem_reduce_allocated+0x1d2/0x270 net/core/sock.c:2696 __sk_mem_reclaim+0x44/0x50 net/core/sock.c:2711 sk_mem_reclaim include/net/sock.h:1490 [inline] ...... net_rx_action+0x17a/0x480 net/core/dev.c:6864 __do_softirq+0x12c/0x2af kernel/softirq.c:298 run_ksoftirqd+0x13/0x20 kernel/softirq.c:653 smpboot_thread_fn+0x33f/0x510 kernel/smpboot.c:165 kthread+0x1fc/0x220 kernel/kthread.c:292 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:296 Fix it by using READ_ONCE() and WRITE_ONCE() to read and write memcg->socket_pressure. Link: https://lkml.kernel.org/r/20211025082843.671690-1-songyuanzheng@huawei.com Signed-off-by: Yuanzheng Song Reviewed-by: Muchun Song Cc: Shakeel Butt Cc: Roman Gushchin Cc: Johannes Weiner Cc: Michal Hocko Cc: Matthew Wilcox (Oracle) Cc: Alex Shi Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f207f98bdb76..9d96238d9c21 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1606,7 +1606,7 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) return true; do { - if (time_before(jiffies, memcg->socket_pressure)) + if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; -- cgit v1.2.3 From fa27717110ae51b9b9013ced0b5143888257bb79 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:13 -0700 Subject: memblock: drop memblock_free_early_nid() and memblock_free_early() memblock_free_early_nid() is unused and memblock_free_early() is an alias for memblock_free(). Replace calls to memblock_free_early() with calls to memblock_free() and remove memblock_free_early() and memblock_free_early_nid(). Link: https://lkml.kernel.org/r/20210930185031.18648-4-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 34de69b3b8ba..fc8183be340c 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -441,18 +441,6 @@ static inline void *memblock_alloc_node(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } -static inline void memblock_free_early(phys_addr_t base, - phys_addr_t size) -{ - memblock_free(base, size); -} - -static inline void memblock_free_early_nid(phys_addr_t base, - phys_addr_t size, int nid) -{ - memblock_free(base, size); -} - static inline void memblock_free_late(phys_addr_t base, phys_addr_t size) { __memblock_free_late(base, size); -- cgit v1.2.3 From 621d973901cf9fa6c6e31b31bdd36c5c5f3c9c9e Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:16 -0700 Subject: memblock: stop aliasing __memblock_free_late with memblock_free_late memblock_free_late() is a NOP wrapper for __memblock_free_late(), there is no point to keep this indirection. Drop the wrapper and rename __memblock_free_late() to memblock_free_late(). Link: https://lkml.kernel.org/r/20210930185031.18648-5-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index fc8183be340c..e25f964fdd60 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -133,7 +133,7 @@ void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); -void __memblock_free_late(phys_addr_t base, phys_addr_t size); +void memblock_free_late(phys_addr_t base, phys_addr_t size); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, @@ -441,11 +441,6 @@ static inline void *memblock_alloc_node(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } -static inline void memblock_free_late(phys_addr_t base, phys_addr_t size) -{ - __memblock_free_late(base, size); -} - /* * Set the allocation direction to bottom-up or top-down. */ -- cgit v1.2.3 From 3ecc68349bbab6bff1d12cbc7951ca6019b2faf6 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:19 -0700 Subject: memblock: rename memblock_free to memblock_phys_free Since memblock_free() operates on a physical range, make its name reflect it and rename it to memblock_phys_free(), so it will be a logical counterpart to memblock_phys_alloc(). The callers are updated with the below semantic patch: @@ expression addr; expression size; @@ - memblock_free(addr, size); + memblock_phys_free(addr, size); Link: https://lkml.kernel.org/r/20210930185031.18648-6-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e25f964fdd60..d32d41709513 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -103,7 +103,7 @@ void memblock_allow_resize(void); int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); -int memblock_free(phys_addr_t base, phys_addr_t size); +int memblock_phys_free(phys_addr_t base, phys_addr_t size); int memblock_reserve(phys_addr_t base, phys_addr_t size); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP int memblock_physmem_add(phys_addr_t base, phys_addr_t size); -- cgit v1.2.3 From 4421cca0a3e4833b3bf0f20de98eb580ab8c7290 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:22 -0700 Subject: memblock: use memblock_free for freeing virtual pointers Rename memblock_free_ptr() to memblock_free() and use memblock_free() when freeing a virtual pointer so that memblock_free() will be a counterpart of memblock_alloc() The callers are updated with the below semantic patch and manual addition of (void *) casting to pointers that are represented by unsigned long variables. @@ identifier vaddr; expression size; @@ ( - memblock_phys_free(__pa(vaddr), size); + memblock_free(vaddr, size); | - memblock_free_ptr(vaddr, size); + memblock_free(vaddr, size); ) [sfr@canb.auug.org.au: fixup] Link: https://lkml.kernel.org/r/20211018192940.3d1d532f@canb.auug.org.au Link: https://lkml.kernel.org/r/20210930185031.18648-7-rppt@kernel.org Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index d32d41709513..484650681bee 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,7 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); -void memblock_free_ptr(void *ptr, size_t size); +void memblock_free(void *ptr, size_t size); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); -- cgit v1.2.3 From b5389086ad7be0453c55e0069a89856d1fbdf605 Mon Sep 17 00:00:00 2001 From: Zhenguo Yao Date: Fri, 5 Nov 2021 13:43:28 -0700 Subject: hugetlbfs: extend the definition of hugepages parameter to support node allocation We can specify the number of hugepages to allocate at boot. But the hugepages is balanced in all nodes at present. In some scenarios, we only need hugepages in one node. For example: DPDK needs hugepages which are in the same node as NIC. If DPDK needs four hugepages of 1G size in node1 and system has 16 numa nodes we must reserve 64 hugepages on the kernel cmdline. But only four hugepages are used. The others should be free after boot. If the system memory is low(for example: 64G), it will be an impossible task. So extend the hugepages parameter to support specifying hugepages on a specific node. For example add following parameter: hugepagesz=1G hugepages=0:1,1:3 It will allocate 1 hugepage in node0 and 3 hugepages in node1. Link: https://lkml.kernel.org/r/20211005054729.86457-1-yaozhenguo1@gmail.com Signed-off-by: Zhenguo Yao Reviewed-by: Mike Kravetz Cc: Zhenguo Yao Cc: Dan Carpenter Cc: Nathan Chancellor Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c0a20781b28e..44c2ab0dfa59 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -615,6 +615,7 @@ struct hstate { unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; + unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; @@ -647,8 +648,9 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page); /* arch callback */ -int __init __alloc_bootmem_huge_page(struct hstate *h); -int __init alloc_bootmem_huge_page(struct hstate *h); +int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); +int __init alloc_bootmem_huge_page(struct hstate *h, int nid); +bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); -- cgit v1.2.3 From 8eb42beac8d369f5443addd469879d152422a28d Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Fri, 5 Nov 2021 13:43:32 -0700 Subject: mm/migrate: de-duplicate migrate_reason strings In order to remove the need to manually keep three different files in synch, provide a common definition of the mapping between enum migrate_reason, and the associated strings for each enum item. 1. Use the tracing system's mapping of enums to strings, by redefining and reusing the MIGRATE_REASON and supporting macros, and using that to populate the string array in mm/debug.c. 2. Move enum migrate_reason to migrate_mode.h. This is not strictly necessary for this patch, but migrate mode and migrate reason go together, so this will slightly clarify things. Link: https://lkml.kernel.org/r/20210922041755.141817-2-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Weizhao Ouyang Cc: "Huang, Ying" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 19 +------------------ include/linux/migrate_mode.h | 13 +++++++++++++ 2 files changed, 14 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index c8077e936691..3d154fe03c96 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -19,24 +19,7 @@ struct migration_target_control; */ #define MIGRATEPAGE_SUCCESS 0 -/* - * Keep sync with: - * - macro MIGRATE_REASON in include/trace/events/migrate.h - * - migrate_reason_names[MR_TYPES] in mm/debug.c - */ -enum migrate_reason { - MR_COMPACTION, - MR_MEMORY_FAILURE, - MR_MEMORY_HOTPLUG, - MR_SYSCALL, /* also applies to cpusets */ - MR_MEMPOLICY_MBIND, - MR_NUMA_MISPLACED, - MR_CONTIG_RANGE, - MR_LONGTERM_PIN, - MR_DEMOTION, - MR_TYPES -}; - +/* Defined in mm/debug.c: */ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h index 883c99249033..f37cc03f9369 100644 --- a/include/linux/migrate_mode.h +++ b/include/linux/migrate_mode.h @@ -19,4 +19,17 @@ enum migrate_mode { MIGRATE_SYNC_NO_COPY, }; +enum migrate_reason { + MR_COMPACTION, + MR_MEMORY_FAILURE, + MR_MEMORY_HOTPLUG, + MR_SYSCALL, /* also applies to cpusets */ + MR_MEMPOLICY_MBIND, + MR_NUMA_MISPLACED, + MR_CONTIG_RANGE, + MR_LONGTERM_PIN, + MR_DEMOTION, + MR_TYPES +}; + #endif /* MIGRATE_MODE_H_INCLUDED */ -- cgit v1.2.3 From 20f9ba4f995247bb79e243741b8fdddbd76dd923 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 5 Nov 2021 13:43:35 -0700 Subject: mm: migrate: make demotion knob depend on migration The memory demotion needs to call migrate_pages() to do the jobs. And it is controlled by a knob, however, the knob doesn't depend on CONFIG_MIGRATION. The knob could be truned on even though MIGRATION is disabled, this will not cause any crash since migrate_pages() would just return -ENOSYS. But it is definitely not optimal to go through demotion path then retry regular swap every time. And it doesn't make too much sense to have the knob visible to the users when !MIGRATION. Move the related code from mempolicy.[h|c] to migrate.[h|c]. Link: https://lkml.kernel.org/r/20211015005559.246709-1-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: "Huang, Ying" Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 4 ---- include/linux/migrate.h | 4 ++++ 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 097bbbb37493..3c7595e81150 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -183,8 +183,6 @@ extern bool vma_migratable(struct vm_area_struct *vma); extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); -extern bool numa_demotion_enabled; - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); @@ -300,8 +298,6 @@ static inline nodemask_t *policy_nodemask_current(gfp_t gfp) return NULL; } -#define numa_demotion_enabled false - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 3d154fe03c96..2d8130e05dc0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -40,6 +40,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); + +extern bool numa_demotion_enabled; #else static inline void putback_movable_pages(struct list_head *l) {} @@ -65,6 +67,8 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, { return -ENOSYS; } + +#define numa_demotion_enabled false #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION -- cgit v1.2.3 From 50f9481ed9fb8a2d2a06a155634c7f9eeff9fa61 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:24 -0700 Subject: mm/memory_hotplug: remove CONFIG_MEMORY_HOTPLUG_SPARSE CONFIG_MEMORY_HOTPLUG depends on CONFIG_SPARSEMEM, so there is no need for CONFIG_MEMORY_HOTPLUG_SPARSE anymore; adjust all instances to use CONFIG_MEMORY_HOTPLUG and remove CONFIG_MEMORY_HOTPLUG_SPARSE. Link: https://lkml.kernel.org/r/20210929143600.49379-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Shuah Khan [kselftest] Acked-by: Greg Kroah-Hartman Acked-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 24 ++++++++++-------------- include/linux/node.h | 4 ++-- 2 files changed, 12 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 053a530c7bdd..0328ec039c38 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -110,7 +110,7 @@ struct mem_section; #define SLAB_CALLBACK_PRI 1 #define IPC_CALLBACK_PRI 10 -#ifndef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifndef CONFIG_MEMORY_HOTPLUG static inline void memory_dev_init(void) { return; @@ -126,7 +126,14 @@ static inline int memory_notify(unsigned long val, void *v) { return 0; } -#else +static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) +{ + return 0; +} +/* These aren't inline functions due to a GCC bug. */ +#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) +#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) +#else /* CONFIG_MEMORY_HOTPLUG */ extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); int create_memory_block_devices(unsigned long start, unsigned long size, @@ -148,9 +155,6 @@ struct memory_group *memory_group_find_by_id(int mgid); typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *); int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, struct memory_group *excluded, void *arg); -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ - -#ifdef CONFIG_MEMORY_HOTPLUG #define hotplug_memory_notifier(fn, pri) ({ \ static __meminitdata struct notifier_block fn##_mem_nb =\ { .notifier_call = fn, .priority = pri };\ @@ -158,15 +162,7 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, }) #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) -#else -static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) -{ - return 0; -} -/* These aren't inline functions due to a GCC bug. */ -#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) -#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) -#endif +#endif /* CONFIG_MEMORY_HOTPLUG */ /* * Kernel text modification mutex, used for code patching. Users of this lock diff --git a/include/linux/node.h b/include/linux/node.h index 8e5a29897936..bb21fd631b16 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -85,7 +85,7 @@ struct node { struct device dev; struct list_head access_list; -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) struct work_struct node_work; #endif #ifdef CONFIG_HMEM_REPORTING @@ -98,7 +98,7 @@ struct memory_block; extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA) void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn, enum meminit_context context); -- cgit v1.2.3 From 6b740c6c3aa371cd70ac07f8d071f2a8af28c51c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:31 -0700 Subject: mm/memory_hotplug: remove HIGHMEM leftovers We don't support CONFIG_MEMORY_HOTPLUG on 32 bit and consequently not HIGHMEM. Let's remove any leftover code -- including the unused "status_change_nid_high" field part of the memory notifier. Link: https://lkml.kernel.org/r/20210929143600.49379-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 0328ec039c38..88eb587b5143 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -96,7 +96,6 @@ struct memory_notify { unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; }; -- cgit v1.2.3 From 43e3aa2a3247c9ca348884866a9846d788ec5ed6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:35 -0700 Subject: mm/memory_hotplug: remove stale function declarations These functions no longer exist. Link: https://lkml.kernel.org/r/20210929143600.49379-6-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e5a867c950b2..be48e003a518 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -98,9 +98,6 @@ static inline void zone_seqlock_init(struct zone *zone) { seqlock_init(&zone->span_seqlock); } -extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); -extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); -extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); extern void adjust_present_page_count(struct page *page, struct memory_group *group, long nr_pages); -- cgit v1.2.3 From e14b41556d9ec20af60a9f672ac6f64dd450763c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:46 -0700 Subject: memblock: improve MEMBLOCK_HOTPLUG documentation The description of MEMBLOCK_HOTPLUG is currently short and consequently misleading: we're actually dealing with a memory region that might get hotunplugged later (i.e., the platform+firmware supports it), yet it is indicated in the firmware-provided memory map as system ram that will just get used by the system for any purpose when not taking special care. The firmware marked this memory region as a hot(un)plugged (e.g., hotplugged before reboot), implying that it might get hotunplugged again later. Whether we consider this information depends on the "movable_node" kernel commandline parameter: only with "movable_node" set, we'll try keeping this memory hotunpluggable, for example, by not serving early allocations from this memory region and by letting the buddy manage it using the ZONE_MOVABLE. Let's make this clearer by extending the documentation. Note: kexec *has to* indicate this memory to the second kernel. With "movable_node" set, we don't want to place kexec-images on this memory. Without "movable_node" set, we don't care and can place kexec-images on this memory. In both cases, after successful memory hotunplug, kexec has to be re-armed to update the memory map for the second kernel and to place the kexec-images somewhere else. Link: https://lkml.kernel.org/r/20211004093605.5830-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Shahab Vahedi Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 484650681bee..1d2b3e902a84 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -28,7 +28,11 @@ extern unsigned long long max_possible_pfn; /** * enum memblock_flags - definition of memory region attributes * @MEMBLOCK_NONE: no special request - * @MEMBLOCK_HOTPLUG: hotpluggable region + * @MEMBLOCK_HOTPLUG: memory region indicated in the firmware-provided memory + * map during early boot as hot(un)pluggable system RAM (e.g., memory range + * that might get hotunplugged later). With "movable_node" set on the kernel + * commandline, try keeping this memory region hotunpluggable. Does not apply + * to memblocks added ("hotplugged") after early boot. * @MEMBLOCK_MIRROR: mirrored region * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as * reserved in the memory map; refer to memblock_mark_nomap() description -- cgit v1.2.3 From 952eea9b01e4bbb7011329f1b7240844e61e5128 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:49 -0700 Subject: memblock: allow to specify flags with memblock_add_node() We want to specify flags when hotplugging memory. Let's prepare to pass flags to memblock_add_node() by adjusting all existing users. Note that when hotplugging memory the system is already up and running and we might have concurrent memblock users: for example, while we're hotplugging memory, kexec_file code might search for suitable memory regions to place kexec images. It's important to add the memory directly to memblock via a single call with the right flags, instead of adding the memory first and apply flags later: otherwise, concurrent memblock users might temporarily stumble over memblocks with wrong flags, which will be important in a follow-up patch that introduces a new flag to properly handle add_memory_driver_managed(). Link: https://lkml.kernel.org/r/20211004093605.5830-4-david@redhat.com Acked-by: Geert Uytterhoeven Acked-by: Heiko Carstens Signed-off-by: David Hildenbrand Acked-by: Shahab Vahedi [arch/arc] Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 3 ++- include/linux/mm.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1d2b3e902a84..8b6560dc7a9e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -104,7 +104,8 @@ static inline void memblock_discard(void) {} #endif void memblock_allow_resize(void); -int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); +int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, + enum memblock_flags flags); int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); int memblock_phys_free(phys_addr_t base, phys_addr_t size); diff --git a/include/linux/mm.h b/include/linux/mm.h index 7e37c726b9db..15058d9cec99 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2425,7 +2425,7 @@ static inline unsigned long get_num_physpages(void) * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() - * memblock_add_node(base, size, nid) + * memblock_add_node(base, size, nid, MEMBLOCK_NONE) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); -- cgit v1.2.3 From f7892d8e288d4b090176f26d9bf7943dbbb639a6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:53 -0700 Subject: memblock: add MEMBLOCK_DRIVER_MANAGED to mimic IORESOURCE_SYSRAM_DRIVER_MANAGED Let's add a flag that corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED, indicating that we're dealing with a memory region that is never indicated in the firmware-provided memory map, but always detected and added by a driver. Similar to MEMBLOCK_HOTPLUG, most infrastructure has to treat such memory regions like ordinary MEMBLOCK_NONE memory regions -- for example, when selecting memory regions to add to the vmcore for dumping in the crashkernel via for_each_mem_range(). However, especially kexec_file is not supposed to select such memblocks via for_each_free_mem_range() / for_each_free_mem_range_reverse() to place kexec images, similar to how we handle IORESOURCE_SYSRAM_DRIVER_MANAGED without CONFIG_ARCH_KEEP_MEMBLOCK. We'll make sure that memory hotplug code sets the flag where applicable (IORESOURCE_SYSRAM_DRIVER_MANAGED) next. This prepares architectures that need CONFIG_ARCH_KEEP_MEMBLOCK, such as arm64, for virtio-mem support. Note that kexec *must not* indicate this memory to the second kernel and *must not* place kexec-images on this memory. Let's add a comment to kexec_walk_memblock(), documenting how we handle MEMBLOCK_DRIVER_MANAGED now just like using IORESOURCE_SYSRAM_DRIVER_MANAGED in locate_mem_hole_callback() for kexec_walk_resources(). Also note that MEMBLOCK_HOTPLUG cannot be reused due to different semantics: MEMBLOCK_HOTPLUG: memory is indicated as "System RAM" in the firmware-provided memory map and added to the system early during boot; kexec *has to* indicate this memory to the second kernel and can place kexec-images on this memory. After memory hotunplug, kexec has to be re-armed. We mostly ignore this flag when "movable_node" is not set on the kernel command line, because then we're told to not care about hotunpluggability of such memory regions. MEMBLOCK_DRIVER_MANAGED: memory is not indicated as "System RAM" in the firmware-provided memory map; this memory is always detected and added to the system by a driver; memory might not actually be physically hotunpluggable. kexec *must not* indicate this memory to the second kernel and *must not* place kexec-images on this memory. Link: https://lkml.kernel.org/r/20211004093605.5830-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Shahab Vahedi Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8b6560dc7a9e..7df557b16c1e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -37,12 +37,17 @@ extern unsigned long long max_possible_pfn; * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as * reserved in the memory map; refer to memblock_mark_nomap() description * for further details + * @MEMBLOCK_DRIVER_MANAGED: memory region that is always detected and added + * via a driver, and never indicated in the firmware-provided memory map as + * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the + * kernel resource tree. */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ MEMBLOCK_MIRROR = 0x2, /* mirrored region */ MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ + MEMBLOCK_DRIVER_MANAGED = 0x8, /* always detected via a driver */ }; /** @@ -213,7 +218,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range(i, p_start, p_end) \ __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_HOTPLUG, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED, \ + p_start, p_end, NULL) /** * for_each_mem_range_rev - reverse iterate through memblock areas from @@ -224,7 +230,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range_rev(i, p_start, p_end) \ __for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_HOTPLUG, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED,\ + p_start, p_end, NULL) /** * for_each_reserved_mem_range - iterate over all reserved memblock areas @@ -254,6 +261,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m) return m->flags & MEMBLOCK_NOMAP; } +static inline bool memblock_is_driver_managed(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_DRIVER_MANAGED; +} + int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, -- cgit v1.2.3 From d2c20e51e3966bc668ef1ef21fbe90704286c8d0 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Fri, 5 Nov 2021 13:45:06 -0700 Subject: mm/highmem: remove deprecated kmap_atomic kmap_atomic() is being deprecated in favor of kmap_local_page(). Replace the uses of kmap_atomic() within the highmem code. On profiling clear_huge_page() using ftrace an improvement of 62% was observed on the below setup. Setup:- Below data has been collected on Qualcomm's SM7250 SoC THP enabled (kernel v4.19.113) with only CPU-0(Cortex-A55) and CPU-7(Cortex-A76) switched on and set to max frequency, also DDR set to perf governor. FTRACE Data:- Base data:- Number of iterations: 48 Mean of allocation time: 349.5 us std deviation: 74.5 us v4 data:- Number of iterations: 48 Mean of allocation time: 131 us std deviation: 32.7 us The following simple userspace experiment to allocate 100MB(BUF_SZ) of pages and writing to it gave us a good insight, we observed an improvement of 42% in allocation and writing timings. ------------------------------------------------------------- Test code snippet ------------------------------------------------------------- clock_start(); buf = malloc(BUF_SZ); /* Allocate 100 MB of memory */ for(i=0; i < BUF_SZ_PAGES; i++) { *((int *)(buf + (i*PAGE_SIZE))) = 1; } clock_end(); ------------------------------------------------------------- Malloc test timings for 100MB anon allocation:- Base data:- Number of iterations: 100 Mean of allocation time: 31831 us std deviation: 4286 us v4 data:- Number of iterations: 100 Mean of allocation time: 18193 us std deviation: 4915 us [willy@infradead.org: fix zero_user_segments()] Link: https://lkml.kernel.org/r/YYVhHCJcm2DM2G9u@casper.infradead.org Link: https://lkml.kernel.org/r/20210204073255.20769-2-prathu.baronia@oneplus.com Signed-off-by: Ira Weiny Signed-off-by: Prathu Baronia Cc: Thomas Gleixner Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index b4c49f9cc379..31ebee36f26c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -143,9 +143,9 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { - void *addr = kmap_atomic(page); + void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); - kunmap_atomic(addr); + kunmap_local(addr); } #endif @@ -177,9 +177,9 @@ alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, static inline void clear_highpage(struct page *page) { - void *kaddr = kmap_atomic(page); + void *kaddr = kmap_local_page(page); clear_page(kaddr); - kunmap_atomic(kaddr); + kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE @@ -202,7 +202,7 @@ static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { - void *kaddr = kmap_atomic(page); + void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); @@ -213,7 +213,7 @@ static inline void zero_user_segments(struct page *page, if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); - kunmap_atomic(kaddr); + kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } @@ -238,11 +238,11 @@ static inline void copy_user_highpage(struct page *to, struct page *from, { char *vfrom, *vto; - vfrom = kmap_atomic(from); - vto = kmap_atomic(to); + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); - kunmap_atomic(vto); - kunmap_atomic(vfrom); + kunmap_local(vto); + kunmap_local(vfrom); } #endif @@ -253,11 +253,11 @@ static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; - vfrom = kmap_atomic(from); - vto = kmap_atomic(to); + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); copy_page(vto, vfrom); - kunmap_atomic(vto); - kunmap_atomic(vfrom); + kunmap_local(vto); + kunmap_local(vfrom); } #endif -- cgit v1.2.3 From 53944f171a89dff4e2a3d76f42e6eedb551bb861 Mon Sep 17 00:00:00 2001 From: Stephen Kitt Date: Fri, 5 Nov 2021 13:45:18 -0700 Subject: mm: remove HARDENED_USERCOPY_FALLBACK This has served its purpose and is no longer used. All usercopy violations appear to have been handled by now, any remaining instances (or new bugs) will cause copies to be rejected. This isn't a direct revert of commit 2d891fbc3bb6 ("usercopy: Allow strict enforcement of whitelists"); since usercopy_fallback is effectively 0, the fallback handling is removed too. This also removes the usercopy_fallback module parameter on slab_common. Link: https://github.com/KSPP/linux/issues/153 Link: https://lkml.kernel.org/r/20210921061149.1091163-1-steve@sk2.org Signed-off-by: Stephen Kitt Suggested-by: Kees Cook Acked-by: Kees Cook Reviewed-by: Joel Stanley [defconfig change] Acked-by: David Rientjes Cc: Christoph Lameter Cc: Pekka Enberg Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: James Morris Cc: "Serge E . Hallyn" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 837cb16232ef..181045148b06 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -142,8 +142,6 @@ struct mem_cgroup; void __init kmem_cache_init(void); bool slab_is_available(void); -extern bool usercopy_fallback; - struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); -- cgit v1.2.3 From a1554c002699cbc9ced2e9f44f9c1357181bead3 Mon Sep 17 00:00:00 2001 From: Mianhan Liu Date: Fri, 5 Nov 2021 13:45:21 -0700 Subject: include/linux/mm.h: move nr_free_buffer_pages from swap.h to mm.h nr_free_buffer_pages could be exposed through mm.h instead of swap.h. The advantage of this change is that it can reduce the obsolete includes. For example, net/ipv4/tcp.c wouldn't need swap.h any more since it has already included mm.h. Similarly, after checking all the other files, it comes that tcp.c, udp.c meter.c ,... follow the same rule, so these files can have swap.h removed too. Moreover, after preprocessing all the files that use nr_free_buffer_pages, it turns out that those files have already included mm.h.Thus, we can move nr_free_buffer_pages from swap.h to mm.h safely. This change will not affect the compilation of other files. Link: https://lkml.kernel.org/r/20210912133640.1624-1-liumh1@shanghaitech.edu.cn Signed-off-by: Mianhan Liu Cc: Jakub Kicinski CC: Ulf Hansson Cc: "David S . Miller" Cc: Simon Horman Cc: Pravin B Shelar Cc: Vlad Yasevich Cc: Marcelo Ricardo Leitner Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ include/linux/swap.h | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 15058d9cec99..b1720aa63727 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -875,6 +875,8 @@ void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); void copy_huge_page(struct page *dst, struct page *src); +unsigned long nr_free_buffer_pages(void); + /* * Compound pages have a destructor function. Provide a * prototype for that function and accessor functions. diff --git a/include/linux/swap.h b/include/linux/swap.h index ba52f3a3478e..53f759a59996 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,7 +335,6 @@ void workingset_update_node(struct xa_node *node); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; -extern unsigned long nr_free_buffer_pages(void); /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) -- cgit v1.2.3 From f39f21b3ddc7fc0f87eb6dc75ddc81b5bbfb7672 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:25 -0700 Subject: stacktrace: move filter_irq_stacks() to kernel/stacktrace.c filter_irq_stacks() has little to do with the stackdepot implementation, except that it is usually used by users (such as KASAN) of stackdepot to reduce the stack trace. However, filter_irq_stacks() itself is not useful without a stack trace as obtained by stack_trace_save() and friends. Therefore, move filter_irq_stacks() to kernel/stacktrace.c, so that new users of filter_irq_stacks() do not have to start depending on STACKDEPOT only for filter_irq_stacks(). Link: https://lkml.kernel.org/r/20210923104803.2620285-1-elver@google.com Signed-off-by: Marco Elver Acked-by: Dmitry Vyukov Cc: Alexander Potapenko Cc: Jann Horn Cc: Aleksandr Nogikh Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 2 -- include/linux/stacktrace.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index b2f7e7c6ba54..d29860966bc9 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -25,8 +25,6 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); -unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); - #ifdef CONFIG_STACKDEPOT int stack_depot_init(void); #else diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 9edecb494e9e..bef158815e83 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -21,6 +21,7 @@ unsigned int stack_trace_save_tsk(struct task_struct *task, unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, unsigned int size, unsigned int skipnr); unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); +unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); /* Internal interfaces. Do not use in generic code */ #ifdef CONFIG_ARCH_STACKWALK -- cgit v1.2.3 From 07e8481d3c38f461d7b79c1d5c9afe013b162b0c Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:46 -0700 Subject: kfence: always use static branches to guard kfence_alloc() Regardless of KFENCE mode (CONFIG_KFENCE_STATIC_KEYS: either using static keys to gate allocations, or using a simple dynamic branch), always use a static branch to avoid the dynamic branch in kfence_alloc() if KFENCE was disabled at boot. For CONFIG_KFENCE_STATIC_KEYS=n, this now avoids the dynamic branch if KFENCE was disabled at boot. To simplify, also unifies the location where kfence_allocation_gate is read-checked to just be inline in kfence_alloc(). Link: https://lkml.kernel.org/r/20211019102524.2807208-1-elver@google.com Signed-off-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jann Horn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 3fe6dd8a18c1..4b5e3679a72c 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -14,6 +14,9 @@ #ifdef CONFIG_KFENCE +#include +#include + /* * We allocate an even number of pages, as it simplifies calculations to map * address to metadata indices; effectively, the very first page serves as an @@ -22,13 +25,8 @@ #define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE) extern char *__kfence_pool; -#ifdef CONFIG_KFENCE_STATIC_KEYS -#include DECLARE_STATIC_KEY_FALSE(kfence_allocation_key); -#else -#include extern atomic_t kfence_allocation_gate; -#endif /** * is_kfence_address() - check if an address belongs to KFENCE pool @@ -116,13 +114,16 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags); */ static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { -#ifdef CONFIG_KFENCE_STATIC_KEYS - if (static_branch_unlikely(&kfence_allocation_key)) +#if defined(CONFIG_KFENCE_STATIC_KEYS) || CONFIG_KFENCE_SAMPLE_INTERVAL == 0 + if (!static_branch_unlikely(&kfence_allocation_key)) + return NULL; #else - if (unlikely(!atomic_read(&kfence_allocation_gate))) + if (!static_branch_likely(&kfence_allocation_key)) + return NULL; #endif - return __kfence_alloc(s, size, flags); - return NULL; + if (likely(atomic_read(&kfence_allocation_gate))) + return NULL; + return __kfence_alloc(s, size, flags); } /** -- cgit v1.2.3 From d2f272b35a84ace2ef04334a9822fd726a7f061b Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:04 -0700 Subject: include/linux/damon.h: fix kernel-doc comments for 'damon_callback' A few Kernel-doc comments in 'damon.h' are broken. This fixes them. Link: https://lkml.kernel.org/r/20210917123958.3819-5-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index d68b67b8d458..755d70804705 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -62,7 +62,7 @@ struct damon_target { struct damon_ctx; /** - * struct damon_primitive Monitoring primitives for given use cases. + * struct damon_primitive - Monitoring primitives for given use cases. * * @init: Initialize primitive-internal data structures. * @update: Update primitive-internal data structures. @@ -108,8 +108,8 @@ struct damon_primitive { void (*cleanup)(struct damon_ctx *context); }; -/* - * struct damon_callback Monitoring events notification callbacks. +/** + * struct damon_callback - Monitoring events notification callbacks. * * @before_start: Called before starting the monitoring. * @after_sampling: Called after each sampling. -- cgit v1.2.3 From fda504fade7f124858d7022341dc46ff35b45274 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:18 -0700 Subject: mm/damon/core: account age of target regions Patch series "Implement Data Access Monitoring-based Memory Operation Schemes". Introduction ============ DAMON[1] can be used as a primitive for data access aware memory management optimizations. For that, users who want such optimizations should run DAMON, read the monitoring results, analyze it, plan a new memory management scheme, and apply the new scheme by themselves. Such efforts will be inevitable for some complicated optimizations. However, in many other cases, the users would simply want the system to apply a memory management action to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB keeping only rare accesses more than 2 minutes", or "Do not use THP for a memory region larger than 2 MiB rarely accessed for more than 1 seconds". To make the works easier and non-redundant, this patchset implements a new feature of DAMON, which is called Data Access Monitoring-based Operation Schemes (DAMOS). Using the feature, users can describe the normal schemes in a simple way and ask DAMON to execute those on its own. [1] https://damonitor.github.io Evaluations =========== DAMOS is accurate and useful for memory management optimizations. An experimental DAMON-based operation scheme for THP, 'ethp', removes 76.15% of THP memory overheads while preserving 51.25% of THP speedup. Another experimental DAMON-based 'proactive reclamation' implementation, 'prcl', reduces 93.38% of residential sets and 23.63% of system memory footprint while incurring only 1.22% runtime overhead in the best case (parsec3/freqmine). NOTE that the experimental THP optimization and proactive reclamation are not for production but only for proof of concepts. Please refer to the showcase web site's evaluation document[1] for detailed evaluation setup and results. [1] https://damonitor.github.io/doc/html/v34/vm/damon/eval.html Long-term Support Trees ----------------------- For people who want to test DAMON but using LTS kernels, there are another couple of trees based on two latest LTS kernels respectively and containing the 'damon/master' backports. - For v5.4.y: https://git.kernel.org/sj/h/damon/for-v5.4.y - For v5.10.y: https://git.kernel.org/sj/h/damon/for-v5.10.y Sequence Of Patches =================== The 1st patch accounts age of each region. The 2nd patch implements the core of the DAMON-based operation schemes feature. The 3rd patch makes the default monitoring primitives for virtual address spaces to support the schemes. From this point, the kernel space users can use DAMOS. The 4th patch exports the feature to the user space via the debugfs interface. The 5th patch implements schemes statistics feature for easier tuning of the schemes and runtime access pattern analysis, and the 6th patch adds selftests for these changes. Finally, the 7th patch documents this new feature. This patch (of 7): DAMON can be used for data access pattern aware memory management optimizations. For that, users should run DAMON, read the monitoring results, analyze it, plan a new memory management scheme, and apply the new scheme by themselves. It would not be too hard, but still require some level of effort. For complicated cases, this effort is inevitable. That said, in many cases, users would simply want to apply an actions to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB but having a low access frequency more than 10 minutes", or "Use THP for a memory region larger than 2 MiB having a high access frequency for more than 2 seconds". For such optimizations, users will need to first account the age of each region themselves. To reduce such efforts, this implements a simple age account of each region in DAMON. For each aggregation step, DAMON compares the access frequency with that from last aggregation and reset the age of the region if the change is significant. Else, the age is incremented. Also, in case of the merge of regions, the region size-weighted average of the ages is set as the age of merged new region. Link: https://lkml.kernel.org/r/20211001125604.29660-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211001125604.29660-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Cameron Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Leonard Foerster Cc: Greg Thelen Cc: Markus Boehme Cc: David Rienjes Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 755d70804705..3e8215debbd4 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -31,12 +31,22 @@ struct damon_addr_range { * @sampling_addr: Address of the sample for the next access check. * @nr_accesses: Access frequency of this region. * @list: List head for siblings. + * @age: Age of this region. + * + * @age is initially zero, increased for each aggregation interval, and reset + * to zero again if the access frequency is significantly changed. If two + * regions are merged into a new region, both @nr_accesses and @age of the new + * region are set as region size-weighted average of those of the two regions. */ struct damon_region { struct damon_addr_range ar; unsigned long sampling_addr; unsigned int nr_accesses; struct list_head list; + + unsigned int age; +/* private: Internal value for age calculation. */ + unsigned int last_nr_accesses; }; /** -- cgit v1.2.3 From 1f366e421c8f69583ed37b56d86e3747331869c3 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:22 -0700 Subject: mm/damon/core: implement DAMON-based Operation Schemes (DAMOS) In many cases, users might use DAMON for simple data access aware memory management optimizations such as applying an operation scheme to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB but having a low access frequency more than 10 minutes", or "Use THP for a memory region larger than 2 MiB having a high access frequency for more than 2 seconds". Most simple form of the solution would be doing offline data access pattern profiling using DAMON and modifying the application source code or system configuration based on the profiling results. Or, developing a daemon constructed with two modules (one for access monitoring and the other for applying memory management actions via mlock(), madvise(), sysctl, etc) is imaginable. To avoid users spending their time for implementation of such simple data access monitoring-based operation schemes, this makes DAMON to handle such schemes directly. With this change, users can simply specify their desired schemes to DAMON. Then, DAMON will automatically apply the schemes to the user-specified target processes. Each of the schemes is composed with conditions for filtering of the target memory regions and desired memory management action for the target. Specifically, the format is:: The filtering conditions are size of memory region, number of accesses to the region monitored by DAMON, and the age of the region. The age of region is incremented periodically but reset when its addresses or access frequency has significantly changed or the action of a scheme was applied. For the action, current implementation supports a few of madvise()-like hints, ``WILLNEED``, ``COLD``, ``PAGEOUT``, ``HUGEPAGE``, and ``NOHUGEPAGE``. Because DAMON supports various address spaces and application of the actions to a monitoring target region is dependent to the type of the target address space, the application code should be implemented by each primitives and registered to the framework. Note that this only implements the framework part. Following commit will implement the action applications for virtual address spaces primitives. Link: https://lkml.kernel.org/r/20211001125604.29660-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 66 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 3e8215debbd4..dbe18b0fb795 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -69,6 +69,48 @@ struct damon_target { struct list_head list; }; +/** + * enum damos_action - Represents an action of a Data Access Monitoring-based + * Operation Scheme. + * + * @DAMOS_WILLNEED: Call ``madvise()`` for the region with MADV_WILLNEED. + * @DAMOS_COLD: Call ``madvise()`` for the region with MADV_COLD. + * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. + * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. + * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. + */ +enum damos_action { + DAMOS_WILLNEED, + DAMOS_COLD, + DAMOS_PAGEOUT, + DAMOS_HUGEPAGE, + DAMOS_NOHUGEPAGE, +}; + +/** + * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * @min_sz_region: Minimum size of target regions. + * @max_sz_region: Maximum size of target regions. + * @min_nr_accesses: Minimum ``->nr_accesses`` of target regions. + * @max_nr_accesses: Maximum ``->nr_accesses`` of target regions. + * @min_age_region: Minimum age of target regions. + * @max_age_region: Maximum age of target regions. + * @action: &damo_action to be applied to the target regions. + * @list: List head for siblings. + * + * Note that both the minimums and the maximums are inclusive. + */ +struct damos { + unsigned long min_sz_region; + unsigned long max_sz_region; + unsigned int min_nr_accesses; + unsigned int max_nr_accesses; + unsigned int min_age_region; + unsigned int max_age_region; + enum damos_action action; + struct list_head list; +}; + struct damon_ctx; /** @@ -79,6 +121,7 @@ struct damon_ctx; * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. + * @apply_scheme: Apply a DAMON-based operation scheme. * @target_valid: Determine if the target is valid. * @cleanup: Clean up the context. * @@ -104,6 +147,9 @@ struct damon_ctx; * of its update. The value will be used for regions adjustment threshold. * @reset_aggregated should reset the access monitoring results that aggregated * by @check_accesses. + * @apply_scheme is called from @kdamond when a region for user provided + * DAMON-based operation scheme is found. It should apply the scheme's action + * to the region. This is not used for &DAMON_ARBITRARY_TARGET case. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. @@ -114,6 +160,8 @@ struct damon_primitive { void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); void (*reset_aggregated)(struct damon_ctx *context); + int (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); bool (*target_valid)(void *target); void (*cleanup)(struct damon_ctx *context); }; @@ -192,6 +240,7 @@ struct damon_callback { * @min_nr_regions: The minimum number of adaptive monitoring regions. * @max_nr_regions: The maximum number of adaptive monitoring regions. * @adaptive_targets: Head of monitoring targets (&damon_target) list. + * @schemes: Head of schemes (&damos) list. */ struct damon_ctx { unsigned long sample_interval; @@ -213,6 +262,7 @@ struct damon_ctx { unsigned long min_nr_regions; unsigned long max_nr_regions; struct list_head adaptive_targets; + struct list_head schemes; }; #define damon_next_region(r) \ @@ -233,6 +283,12 @@ struct damon_ctx { #define damon_for_each_target_safe(t, next, ctx) \ list_for_each_entry_safe(t, next, &(ctx)->adaptive_targets, list) +#define damon_for_each_scheme(s, ctx) \ + list_for_each_entry(s, &(ctx)->schemes, list) + +#define damon_for_each_scheme_safe(s, next, ctx) \ + list_for_each_entry_safe(s, next, &(ctx)->schemes, list) + #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); @@ -242,6 +298,14 @@ inline void damon_insert_region(struct damon_region *r, void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); +struct damos *damon_new_scheme( + unsigned long min_sz_region, unsigned long max_sz_region, + unsigned int min_nr_accesses, unsigned int max_nr_accesses, + unsigned int min_age_region, unsigned int max_age_region, + enum damos_action action); +void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); +void damon_destroy_scheme(struct damos *s); + struct damon_target *damon_new_target(unsigned long id); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); void damon_free_target(struct damon_target *t); @@ -255,6 +319,8 @@ int damon_set_targets(struct damon_ctx *ctx, int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, unsigned long aggr_int, unsigned long primitive_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg); +int damon_set_schemes(struct damon_ctx *ctx, + struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); int damon_start(struct damon_ctx **ctxs, int nr_ctxs); -- cgit v1.2.3 From 6dea8add4d2875b80843e4a4c8acd334a4db8c8f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:25 -0700 Subject: mm/damon/vaddr: support DAMON-based Operation Schemes This makes DAMON's default primitives for virtual address spaces to support DAMON-based Operation Schemes (DAMOS) by implementing actions application functions and registering it to the monitoring context. The implementation simply links 'madvise()' for related DAMOS actions. That is, 'madvise(MADV_WILLNEED)' is called for 'WILLNEED' DAMOS action and similar for other actions ('COLD', 'PAGEOUT', 'HUGEPAGE', 'NOHUGEPAGE'). So, the kernel space DAMON users can now use the DAMON-based optimizations with only small amount of code. Link: https://lkml.kernel.org/r/20211001125604.29660-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index dbe18b0fb795..be6b6e81e8ee 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -337,6 +337,8 @@ void damon_va_prepare_access_checks(struct damon_ctx *ctx); unsigned int damon_va_check_accesses(struct damon_ctx *ctx); bool damon_va_target_valid(void *t); void damon_va_cleanup(struct damon_ctx *ctx); +int damon_va_apply_scheme(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_va_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ -- cgit v1.2.3 From 2f0b548c9f03a78f4ce6ab48986e3108028936a6 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:32 -0700 Subject: mm/damon/schemes: implement statistics feature To tune the DAMON-based operation schemes, knowing how many and how large regions are affected by each of the schemes will be helful. Those stats could be used for not only the tuning, but also monitoring of the working set size and the number of regions, if the scheme does not change the program behavior too much. For the reason, this implements the statistics for the schemes. The total number and size of the regions that each scheme is applied are exported to users via '->stat_count' and '->stat_sz' of 'struct damos'. Admins can also check the number by reading 'schemes' debugfs file. The last two integers now represents the stats. To allow collecting the stats without changing the program behavior, this also adds new scheme action, 'DAMOS_STAT'. Note that 'DAMOS_STAT' is not only making no memory operation actions, but also does not reset the age of regions. Link: https://lkml.kernel.org/r/20211001125604.29660-6-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index be6b6e81e8ee..f301bb53381c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -78,6 +78,7 @@ struct damon_target { * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. + * @DAMOS_STAT: Do nothing but count the stat. */ enum damos_action { DAMOS_WILLNEED, @@ -85,6 +86,7 @@ enum damos_action { DAMOS_PAGEOUT, DAMOS_HUGEPAGE, DAMOS_NOHUGEPAGE, + DAMOS_STAT, /* Do nothing but only record the stat */ }; /** @@ -96,9 +98,13 @@ enum damos_action { * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. + * @stat_count: Total number of regions that this scheme is applied. + * @stat_sz: Total size of regions that this scheme is applied. * @list: List head for siblings. * - * Note that both the minimums and the maximums are inclusive. + * For each aggregation interval, DAMON applies @action to monitoring target + * regions fit in the condition and updates the statistics. Note that both + * the minimums and the maximums are inclusive. */ struct damos { unsigned long min_sz_region; @@ -108,6 +114,8 @@ struct damos { unsigned int min_age_region; unsigned int max_age_region; enum damos_action action; + unsigned long stat_count; + unsigned long stat_sz; struct list_head list; }; -- cgit v1.2.3 From a28397beb55b68bd0f15c6778540e8ae1bc26d21 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:56 -0700 Subject: mm/damon: implement primitives for physical address space monitoring This implements the monitoring primitives for the physical memory address space. Internally, it uses the PTE Accessed bit, similar to that of the virtual address spaces monitoring primitives. It supports only user memory pages, as idle pages tracking does. If the monitoring target physical memory address range contains non-user memory pages, access check of the pages will do nothing but simply treat the pages as not accessed. Link: https://lkml.kernel.org/r/20211012205711.29216-6-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index f301bb53381c..715dadd21f7c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -351,4 +351,14 @@ void damon_va_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ +#ifdef CONFIG_DAMON_PADDR + +/* Monitoring primitives for the physical memory address space */ +void damon_pa_prepare_access_checks(struct damon_ctx *ctx); +unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); +bool damon_pa_target_valid(void *t); +void damon_pa_set_primitives(struct damon_ctx *ctx); + +#endif /* CONFIG_DAMON_PADDR */ + #endif /* _DAMON_H */ -- cgit v1.2.3 From 57223ac295845b1d72ec1bd02b5fab992b77a021 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:13 -0700 Subject: mm/damon/paddr: support the pageout scheme Introduction ============ This patchset 1) makes the engine for general data access pattern-oriented memory management (DAMOS) be more useful for production environments, and 2) implements a static kernel module for lightweight proactive reclamation using the engine. Proactive Reclamation --------------------- On general memory over-committed systems, proactively reclaiming cold pages helps saving memory and reducing latency spikes that incurred by the direct reclaim or the CPU consumption of kswapd, while incurring only minimal performance degradation[2]. A Free Pages Reporting[8] based memory over-commit virtualization system would be one more specific use case. In the system, the guest VMs reports their free memory to host, and the host reallocates the reported memory to other guests. As a result, the system's memory utilization can be maximized. However, the guests could be not so memory-frugal, because some kernel subsystems and user-space applications are designed to use as much memory as available. Then, guests would report only small amount of free memory to host, results in poor memory utilization. Running the proactive reclamation in such guests could help mitigating this problem. Google has also implemented this idea and using it in their data center. They further proposed upstreaming it in LSFMM'19, and "the general consensus was that, while this sort of proactive reclaim would be useful for a number of users, the cost of this particular solution was too high to consider merging it upstream"[3]. The cost mainly comes from the coldness tracking. Roughly speaking, the implementation periodically scans the 'Accessed' bit of each page. For the reason, the overhead linearly increases as the size of the memory and the scanning frequency grows. As a result, Google is known to dedicating one CPU for the work. That's a reasonable option to someone like Google, but it wouldn't be so to some others. DAMON and DAMOS: An engine for data access pattern-oriented memory management ----------------------------------------------------------------------------- DAMON[4] is a framework for general data access monitoring. Its adaptive monitoring overhead control feature minimizes its monitoring overhead. It also let the upper-bound of the overhead be configurable by clients, regardless of the size of the monitoring target memory. While monitoring 70 GiB memory of a production system every 5 milliseconds, it consumes less than 1% single CPU time. For this, it could sacrify some of the quality of the monitoring results. Nevertheless, the lower-bound of the quality is configurable, and it uses a best-effort algorithm for better quality. Our test results[5] show the quality is practical enough. From the production system monitoring, we were able to find a 4 KiB region in the 70 GiB memory that shows highest access frequency. We normally don't monitor the data access pattern just for fun but to improve something like memory management. Proactive reclamation is one such usage. For such general cases, DAMON provides a feature called DAMon-based Operation Schemes (DAMOS)[6]. It makes DAMON an engine for general data access pattern oriented memory management. Using this, clients can ask DAMON to find memory regions of specific data access pattern and apply some memory management action (e.g., page out, move to head of the LRU list, use huge page, ...). We call the request 'scheme'. Proactive Reclamation on top of DAMON/DAMOS ------------------------------------------- Therefore, by using DAMON for the cold pages detection, the proactive reclamation's monitoring overhead issue can be solved. Actually, we previously implemented a version of proactive reclamation using DAMOS and achieved noticeable improvements with our evaluation setup[5]. Nevertheless, it more for a proof-of-concept, rather than production uses. It supports only virtual address spaces of processes, and require additional tuning efforts for given workloads and the hardware. For the tuning, we introduced a simple auto-tuning user space tool[8]. Google is also known to using a ML-based similar approach for their fleets[2]. But, making it just works with intuitive knobs in the kernel would be helpful for general users. To this end, this patchset improves DAMOS to be ready for such production usages, and implements another version of the proactive reclamation, namely DAMON_RECLAIM, on top of it. DAMOS Improvements: Aggressiveness Control, Prioritization, and Watermarks -------------------------------------------------------------------------- First of all, the current version of DAMOS supports only virtual address spaces. This patchset makes it supports the physical address space for the page out action. Next major problem of the current version of DAMOS is the lack of the aggressiveness control, which can results in arbitrary overhead. For example, if huge memory regions having the data access pattern of interest are found, applying the requested action to all of the regions could incur significant overhead. It can be controlled by tuning the target data access pattern with manual or automated approaches[2,7]. But, some people would prefer the kernel to just work with only intuitive tuning or default values. For such cases, this patchset implements a safeguard, namely time/size quota. Using this, the clients can specify up to how much time can be used for applying the action, and/or up to how much memory regions the action can be applied within a user-specified time duration. A followup question is, to which memory regions should the action applied within the limits? We implement a simple regions prioritization mechanism for each action and make DAMOS to apply the action to high priority regions first. It also allows clients tune the prioritization mechanism to use different weights for size, access frequency, and age of memory regions. This means we could use not only LRU but also LFU or some fancy algorithms like CAR[9] with lightweight overhead. Though DAMON is lightweight, someone would want to remove even the cold pages monitoring overhead when it is unnecessary. Currently, it should manually turned on and off by clients, but some clients would simply want to turn it on and off based on some metrics like free memory ratio or memory fragmentation. For such cases, this patchset implements a watermarks-based automatic activation feature. It allows the clients configure the metric of their interest, and three watermarks of the metric. If the metric is higher than the high watermark or lower than the low watermark, the scheme is deactivated. If the metric is lower than the mid watermark but higher than the low watermark, the scheme is activated. DAMON-based Reclaim ------------------- Using the improved version of DAMOS, this patchset implements a static kernel module called 'damon_reclaim'. It finds memory regions that didn't accessed for specific time duration and page out. Consuming too much CPU for the paging out operations, or doing pageout too frequently can be critical for systems configuring their swap devices with software-defined in-memory block devices like zram/zswap or total number of writes limited devices like SSDs, respectively. To avoid the problems, the time/size quotas can be configured. Under the quotas, it pages out memory regions that didn't accessed longer first. Also, to remove the monitoring overhead under peaceful situation, and to fall back to the LRU-list based page granularity reclamation when it doesn't make progress, the three watermarks based activation mechanism is used, with the free memory ratio as the watermark metric. For convenient configurations, it provides several module parameters. Using these, sysadmins can enable/disable it, and tune its parameters including the coldness identification time threshold, the time/size quotas and the three watermarks. Evaluation ========== In short, DAMON_RECLAIM with 50ms/s time quota and regions prioritization on v5.15-rc5 Linux kernel with ZRAM swap device achieves 38.58% memory saving with only 1.94% runtime overhead. For this, DAMON_RECLAIM consumes only 4.97% of single CPU time. Setup ----- We evaluate DAMON_RECLAIM to show how each of the DAMOS improvements make effect. For this, we measure DAMON_RECLAIM's CPU consumption, entire system memory footprint, total number of major page faults, and runtime of 24 realistic workloads in PARSEC3 and SPLASH-2X benchmark suites on my QEMU/KVM based virtual machine. The virtual machine runs on an i3.metal AWS instance, has 130GiB memory, and runs a linux kernel built on latest -mm tree[1] plus this patchset. It also utilizes a 4 GiB ZRAM swap device. We repeats the measurement 5 times and use averages. [1] https://github.com/hnaz/linux-mm/tree/v5.15-rc5-mmots-2021-10-13-19-55 Detailed Results ---------------- The results are summarized in the below table. With coldness identification threshold of 5 seconds, DAMON_RECLAIM without the time quota-based speed limit achieves 47.21% memory saving, but incur 4.59% runtime slowdown to the workloads on average. For this, DAMON_RECLAIM consumes about 11.28% single CPU time. Applying time quotas of 200ms/s, 50ms/s, and 10ms/s without the regions prioritization reduces the slowdown to 4.89%, 2.65%, and 1.5%, respectively. Time quota of 200ms/s (20%) makes no real change compared to the quota unapplied version, because the quota unapplied version consumes only 11.28% CPU time. DAMON_RECLAIM's CPU utilization also similarly reduced: 11.24%, 5.51%, and 2.01% of single CPU time. That is, the overhead is proportional to the speed limit. Nevertheless, it also reduces the memory saving because it becomes less aggressive. In detail, the three variants show 48.76%, 37.83%, and 7.85% memory saving, respectively. Applying the regions prioritization (page out regions that not accessed longer first within the time quota) further reduces the performance degradation. Runtime slowdowns and total number of major page faults increase has been 4.89%/218,690% -> 4.39%/166,136% (200ms/s), 2.65%/111,886% -> 1.94%/59,053% (50ms/s), and 1.5%/34,973.40% -> 2.08%/8,781.75% (10ms/s). The runtime under 10ms/s time quota has increased with prioritization, but apparently that's under the margin of error. time quota prioritization memory_saving cpu_util slowdown pgmajfaults overhead N N 47.21% 11.28% 4.59% 194,802% 200ms/s N 48.76% 11.24% 4.89% 218,690% 50ms/s N 37.83% 5.51% 2.65% 111,886% 10ms/s N 7.85% 2.01% 1.5% 34,793.40% 200ms/s Y 50.08% 10.38% 4.39% 166,136% 50ms/s Y 38.58% 4.97% 1.94% 59,053% 10ms/s Y 3.63% 1.73% 2.08% 8,781.75% Baseline and Complete Git Trees =============================== The patches are based on the latest -mm tree (v5.15-rc5-mmots-2021-10-13-19-55). You can also clone the complete git tree from: $ git clone git://github.com/sjp38/linux -b damon_reclaim/patches/v1 The web is also available: https://git.kernel.org/pub/scm/linux/kernel/git/sj/linux.git/tag/?h=damon_reclaim/patches/v1 Sequence Of Patches =================== The first patch makes DAMOS support the physical address space for the page out action. Following five patches (patches 2-6) implement the time/size quotas. Next four patches (patches 7-10) implement the memory regions prioritization within the limit. Then, three following patches (patches 11-13) implement the watermarks-based schemes activation. Finally, the last two patches (patches 14-15) implement and document the DAMON-based reclamation using the advanced DAMOS. [1] https://www.kernel.org/doc/html/v5.15-rc1/vm/damon/index.html [2] https://research.google/pubs/pub48551/ [3] https://lwn.net/Articles/787611/ [4] https://damonitor.github.io [5] https://damonitor.github.io/doc/html/latest/vm/damon/eval.html [6] https://lore.kernel.org/linux-mm/20211001125604.29660-1-sj@kernel.org/ [7] https://github.com/awslabs/damoos [8] https://www.kernel.org/doc/html/latest/vm/free_page_reporting.html [9] https://www.usenix.org/conference/fast-04/car-clock-adaptive-replacement This patch (of 15): This makes the DAMON primitives for physical address space support the pageout action for DAMON-based Operation Schemes. With this commit, hence, users can easily implement system-level data access-aware reclamations using DAMOS. [sj@kernel.org: fix missing-prototype build warning] Link: https://lkml.kernel.org/r/20211025064220.13904-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211019150731.16699-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211019150731.16699-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Cameron Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Leonard Foerster Cc: Greg Thelen Cc: Markus Boehme Cc: David Rientjes Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 715dadd21f7c..9a327bc787b5 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -357,6 +357,8 @@ void damon_va_set_primitives(struct damon_ctx *ctx); void damon_pa_prepare_access_checks(struct damon_ctx *ctx); unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); bool damon_pa_target_valid(void *t); +int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_pa_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_PADDR */ -- cgit v1.2.3 From 2b8a248d5873343aa16f6c5ede30517693995f13 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:16 -0700 Subject: mm/damon/schemes: implement size quota for schemes application speed control There could be arbitrarily large memory regions fulfilling the target data access pattern of a DAMON-based operation scheme. In the case, applying the action of the scheme could incur too high overhead. To provide an intuitive way for avoiding it, this implements a feature called size quota. If the quota is set, DAMON tries to apply the action only up to the given amount of memory regions within a given time window. Link: https://lkml.kernel.org/r/20211019150731.16699-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 36 ++++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 9a327bc787b5..3a1ce9d9921c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -89,6 +89,26 @@ enum damos_action { DAMOS_STAT, /* Do nothing but only record the stat */ }; +/** + * struct damos_quota - Controls the aggressiveness of the given scheme. + * @sz: Maximum bytes of memory that the action can be applied. + * @reset_interval: Charge reset interval in milliseconds. + * + * To avoid consuming too much CPU time or IO resources for applying the + * &struct damos->action to large memory, DAMON allows users to set a size + * quota. The quota can be set by writing non-zero values to &sz. If the size + * quota is set, DAMON tries to apply the action only up to &sz bytes within + * &reset_interval. + */ +struct damos_quota { + unsigned long sz; + unsigned long reset_interval; + +/* private: For charging the quota */ + unsigned long charged_sz; + unsigned long charged_from; +}; + /** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. @@ -98,13 +118,20 @@ enum damos_action { * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. + * @quota: Control the aggressiveness of this scheme. * @stat_count: Total number of regions that this scheme is applied. * @stat_sz: Total size of regions that this scheme is applied. * @list: List head for siblings. * - * For each aggregation interval, DAMON applies @action to monitoring target - * regions fit in the condition and updates the statistics. Note that both - * the minimums and the maximums are inclusive. + * For each aggregation interval, DAMON finds regions which fit in the + * condition (&min_sz_region, &max_sz_region, &min_nr_accesses, + * &max_nr_accesses, &min_age_region, &max_age_region) and applies &action to + * those. To avoid consuming too much CPU time or IO resources for the + * &action, "a is used. + * + * After applying the &action to each region, &stat_count and &stat_sz is + * updated to reflect the number of regions and total size of regions that the + * &action is applied. */ struct damos { unsigned long min_sz_region; @@ -114,6 +141,7 @@ struct damos { unsigned int min_age_region; unsigned int max_age_region; enum damos_action action; + struct damos_quota quota; unsigned long stat_count; unsigned long stat_sz; struct list_head list; @@ -310,7 +338,7 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action); + enum damos_action action, struct damos_quota *quota); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); -- cgit v1.2.3 From 50585192bc2ef9309d32dabdbb5e735679f4f128 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:20 -0700 Subject: mm/damon/schemes: skip already charged targets and regions If DAMOS has stopped applying action in the middle of a group of memory regions due to its size quota, it starts the work again from the beginning of the address space in the next charge window. If there is a huge memory region at the beginning of the address space and it fulfills the scheme's target data access pattern always, the action will applied to only the region. This mitigates the case by skipping memory regions that charged in current charge window at the beginning of next charge window. Link: https://lkml.kernel.org/r/20211019150731.16699-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 3a1ce9d9921c..585d985768fd 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -107,6 +107,8 @@ struct damos_quota { /* private: For charging the quota */ unsigned long charged_sz; unsigned long charged_from; + struct damon_target *charge_target_from; + unsigned long charge_addr_from; }; /** @@ -307,6 +309,9 @@ struct damon_ctx { #define damon_prev_region(r) \ (container_of(r->list.prev, struct damon_region, list)) +#define damon_last_region(t) \ + (list_last_entry(&t->regions_list, struct damon_region, list)) + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) -- cgit v1.2.3 From 1cd2430300594a230dba9178ac9e286d868d9da2 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:23 -0700 Subject: mm/damon/schemes: implement time quota The size quota feature of DAMOS is useful for IO resource-critical systems, but not so intuitive for CPU time-critical systems. Systems using zram or zswap-like swap device would be examples. To provide another intuitive ways for such systems, this implements time-based quota for DAMON-based Operation Schemes. If the quota is set, DAMOS tries to use only up to the user-defined quota of CPU time within a given time window. Link: https://lkml.kernel.org/r/20211019150731.16699-5-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 585d985768fd..1e7671bf3d23 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -91,20 +91,35 @@ enum damos_action { /** * struct damos_quota - Controls the aggressiveness of the given scheme. + * @ms: Maximum milliseconds that the scheme can use. * @sz: Maximum bytes of memory that the action can be applied. * @reset_interval: Charge reset interval in milliseconds. * * To avoid consuming too much CPU time or IO resources for applying the - * &struct damos->action to large memory, DAMON allows users to set a size - * quota. The quota can be set by writing non-zero values to &sz. If the size - * quota is set, DAMON tries to apply the action only up to &sz bytes within - * &reset_interval. + * &struct damos->action to large memory, DAMON allows users to set time and/or + * size quotas. The quotas can be set by writing non-zero values to &ms and + * &sz, respectively. If the time quota is set, DAMON tries to use only up to + * &ms milliseconds within &reset_interval for applying the action. If the + * size quota is set, DAMON tries to apply the action only up to &sz bytes + * within &reset_interval. + * + * Internally, the time quota is transformed to a size quota using estimated + * throughput of the scheme's action. DAMON then compares it against &sz and + * uses smaller one as the effective quota. */ struct damos_quota { + unsigned long ms; unsigned long sz; unsigned long reset_interval; -/* private: For charging the quota */ +/* private: */ + /* For throughput estimation */ + unsigned long total_charged_sz; + unsigned long total_charged_ns; + + unsigned long esz; /* Effective size quota in bytes */ + + /* For charging the quota */ unsigned long charged_sz; unsigned long charged_from; struct damon_target *charge_target_from; -- cgit v1.2.3 From 38683e003153f7abfa612d7b7fe147efa4624af2 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:33 -0700 Subject: mm/damon/schemes: prioritize regions within the quotas This makes DAMON apply schemes to regions having higher priority first, if it cannot apply schemes to all regions due to the quotas. The prioritization function should be implemented in the monitoring primitives. Those would commonly calculate the priority of the region using attributes of regions, namely 'size', 'nr_accesses', and 'age'. For example, some primitive would calculate the priority of each region using a weighted sum of 'nr_accesses' and 'age' of the region. The optimal weights would depend on give environments, so this makes those customizable. Nevertheless, the score calculation functions are only encouraged to respect the weights, not mandated. Link: https://lkml.kernel.org/r/20211019150731.16699-8-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 1e7671bf3d23..5d47ad9e3911 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -14,6 +14,8 @@ /* Minimal region size. Every damon_region is aligned by this. */ #define DAMON_MIN_REGION PAGE_SIZE +/* Max priority score for DAMON-based operation schemes */ +#define DAMOS_MAX_SCORE (99) /** * struct damon_addr_range - Represents an address region of [@start, @end). @@ -95,6 +97,10 @@ enum damos_action { * @sz: Maximum bytes of memory that the action can be applied. * @reset_interval: Charge reset interval in milliseconds. * + * @weight_sz: Weight of the region's size for prioritization. + * @weight_nr_accesses: Weight of the region's nr_accesses for prioritization. + * @weight_age: Weight of the region's age for prioritization. + * * To avoid consuming too much CPU time or IO resources for applying the * &struct damos->action to large memory, DAMON allows users to set time and/or * size quotas. The quotas can be set by writing non-zero values to &ms and @@ -106,12 +112,22 @@ enum damos_action { * Internally, the time quota is transformed to a size quota using estimated * throughput of the scheme's action. DAMON then compares it against &sz and * uses smaller one as the effective quota. + * + * For selecting regions within the quota, DAMON prioritizes current scheme's + * target memory regions using the &struct damon_primitive->get_scheme_score. + * You could customize the prioritization logic by setting &weight_sz, + * &weight_nr_accesses, and &weight_age, because monitoring primitives are + * encouraged to respect those. */ struct damos_quota { unsigned long ms; unsigned long sz; unsigned long reset_interval; + unsigned int weight_sz; + unsigned int weight_nr_accesses; + unsigned int weight_age; + /* private: */ /* For throughput estimation */ unsigned long total_charged_sz; @@ -124,6 +140,10 @@ struct damos_quota { unsigned long charged_from; struct damon_target *charge_target_from; unsigned long charge_addr_from; + + /* For prioritization */ + unsigned long histogram[DAMOS_MAX_SCORE + 1]; + unsigned int min_score; }; /** @@ -174,6 +194,7 @@ struct damon_ctx; * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. + * @get_scheme_score: Get the score of a region for a scheme. * @apply_scheme: Apply a DAMON-based operation scheme. * @target_valid: Determine if the target is valid. * @cleanup: Clean up the context. @@ -200,6 +221,8 @@ struct damon_ctx; * of its update. The value will be used for regions adjustment threshold. * @reset_aggregated should reset the access monitoring results that aggregated * by @check_accesses. + * @get_scheme_score should return the priority score of a region for a scheme + * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action * to the region. This is not used for &DAMON_ARBITRARY_TARGET case. @@ -213,6 +236,9 @@ struct damon_primitive { void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); void (*reset_aggregated)(struct damon_ctx *context); + int (*get_scheme_score)(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme); int (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); bool (*target_valid)(void *target); -- cgit v1.2.3 From 198f0f4c58b9f481e4e51c8c70a6ab9852bbab7f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:37 -0700 Subject: mm/damon/vaddr,paddr: support pageout prioritization This makes the default monitoring primitives for virtual address spaces and the physical address sapce to support memory regions prioritization for 'PAGEOUT' DAMOS action. It calculates hotness of each region as weighted sum of 'nr_accesses' and 'age' of the region and get the priority score as reverse of the hotness, so that cold regions can be paged out first. Link: https://lkml.kernel.org/r/20211019150731.16699-9-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 5d47ad9e3911..1217566a0ebc 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -421,6 +421,8 @@ bool damon_va_target_valid(void *t); void damon_va_cleanup(struct damon_ctx *ctx); int damon_va_apply_scheme(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); +int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_va_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ @@ -433,6 +435,8 @@ unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); bool damon_pa_target_valid(void *t); int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); +int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_pa_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_PADDR */ -- cgit v1.2.3 From ee801b7dd7822a82fd7663048ad649545fac6df3 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:47 -0700 Subject: mm/damon/schemes: activate schemes based on a watermarks mechanism DAMON-based operation schemes need to be manually turned on and off. In some use cases, however, the condition for turning a scheme on and off would depend on the system's situation. For example, schemes for proactive pages reclamation would need to be turned on when some memory pressure is detected, and turned off when the system has enough free memory. For easier control of schemes activation based on the system situation, this introduces a watermarks-based mechanism. The client can describe the watermark metric (e.g., amount of free memory in the system), watermark check interval, and three watermarks, namely high, mid, and low. If the scheme is deactivated, it only gets the metric and compare that to the three watermarks for every check interval. If the metric is higher than the high watermark, the scheme is deactivated. If the metric is between the mid watermark and the low watermark, the scheme is activated. If the metric is lower than the low watermark, the scheme is deactivated again. This is to allow users fall back to traditional page-granularity mechanisms. Link: https://lkml.kernel.org/r/20211019150731.16699-12-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 51 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 1217566a0ebc..c93325efddd7 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -146,6 +146,45 @@ struct damos_quota { unsigned int min_score; }; +/** + * enum damos_wmark_metric - Represents the watermark metric. + * + * @DAMOS_WMARK_NONE: Ignore the watermarks of the given scheme. + * @DAMOS_WMARK_FREE_MEM_RATE: Free memory rate of the system in [0,1000]. + */ +enum damos_wmark_metric { + DAMOS_WMARK_NONE, + DAMOS_WMARK_FREE_MEM_RATE, +}; + +/** + * struct damos_watermarks - Controls when a given scheme should be activated. + * @metric: Metric for the watermarks. + * @interval: Watermarks check time interval in microseconds. + * @high: High watermark. + * @mid: Middle watermark. + * @low: Low watermark. + * + * If &metric is &DAMOS_WMARK_NONE, the scheme is always active. Being active + * means DAMON does monitoring and applying the action of the scheme to + * appropriate memory regions. Else, DAMON checks &metric of the system for at + * least every &interval microseconds and works as below. + * + * If &metric is higher than &high, the scheme is inactivated. If &metric is + * between &mid and &low, the scheme is activated. If &metric is lower than + * &low, the scheme is inactivated. + */ +struct damos_watermarks { + enum damos_wmark_metric metric; + unsigned long interval; + unsigned long high; + unsigned long mid; + unsigned long low; + +/* private: */ + bool activated; +}; + /** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. @@ -156,6 +195,7 @@ struct damos_quota { * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. + * @wmarks: Watermarks for automated (in)activation of this scheme. * @stat_count: Total number of regions that this scheme is applied. * @stat_sz: Total size of regions that this scheme is applied. * @list: List head for siblings. @@ -166,6 +206,14 @@ struct damos_quota { * those. To avoid consuming too much CPU time or IO resources for the * &action, "a is used. * + * To do the work only when needed, schemes can be activated for specific + * system situations using &wmarks. If all schemes that registered to the + * monitoring context are inactive, DAMON stops monitoring either, and just + * repeatedly checks the watermarks. + * + * If all schemes that registered to a &struct damon_ctx are inactive, DAMON + * stops monitoring and just repeatedly checks the watermarks. + * * After applying the &action to each region, &stat_count and &stat_sz is * updated to reflect the number of regions and total size of regions that the * &action is applied. @@ -179,6 +227,7 @@ struct damos { unsigned int max_age_region; enum damos_action action; struct damos_quota quota; + struct damos_watermarks wmarks; unsigned long stat_count; unsigned long stat_sz; struct list_head list; @@ -384,7 +433,8 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota); + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); -- cgit v1.2.3 From b5ca3e83ddb05342b1b30700b999cb9b107511f6 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 5 Nov 2021 13:48:07 -0700 Subject: mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on When the ctx->adaptive_targets list is empty, I did some test on monitor_on interface like this. # cat /sys/kernel/debug/damon/target_ids # # echo on > /sys/kernel/debug/damon/monitor_on # damon: kdamond (5390) starts Though the ctx->adaptive_targets list is empty, but the kthread_run still be called, and the kdamond.x thread still be created, this is meaningless. So there adds a judgment in 'dbgfs_monitor_on_write', if the ctx->adaptive_targets list is empty, return -EINVAL. Link: https://lkml.kernel.org/r/0a60a6e8ec9d71989e0848a4dc3311996ca3b5d4.1634720326.git.xhao@linux.alibaba.com Signed-off-by: Xin Hao Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index c93325efddd7..fa7f32614b65 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -440,6 +440,7 @@ void damon_destroy_scheme(struct damos *s); struct damon_target *damon_new_target(unsigned long id); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); +bool damon_targets_empty(struct damon_ctx *ctx); void damon_free_target(struct damon_target *t); void damon_destroy_target(struct damon_target *t); unsigned int damon_nr_regions(struct damon_target *t); -- cgit v1.2.3 From 0f91d13366a402420bf98eaaf393db03946c13e0 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 5 Nov 2021 13:48:22 -0700 Subject: mm/damon: simplify stop mechanism A kernel thread can exit gracefully with kthread_stop(). So we don't need a new flag 'kdamond_stop'. And to make sure the task struct is not freed when accessing it, get reference to it before termination. Link: https://lkml.kernel.org/r/20211027130517.4404-1-changbin.du@gmail.com Signed-off-by: Changbin Du Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index fa7f32614b65..321de9d72360 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -381,7 +381,6 @@ struct damon_ctx { /* public: */ struct task_struct *kdamond; - bool kdamond_stop; struct mutex kdamond_lock; struct damon_primitive primitive; -- cgit v1.2.3 From 658f9ae761b5965893727dd4edcdad56e5a439bb Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 5 Nov 2021 13:48:27 -0700 Subject: mm/damon: remove return value from before_terminate callback Since the return value of 'before_terminate' callback is never used, we make it have no return value. Link: https://lkml.kernel.org/r/20211029005023.8895-1-changbin.du@gmail.com Signed-off-by: Changbin Du Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 321de9d72360..b4d4be3cc987 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -322,7 +322,7 @@ struct damon_callback { int (*before_start)(struct damon_ctx *context); int (*after_sampling)(struct damon_ctx *context); int (*after_aggregation)(struct damon_ctx *context); - int (*before_terminate)(struct damon_ctx *context); + void (*before_terminate)(struct damon_ctx *context); }; /** -- cgit v1.2.3 From e1c9788cb39777e81ebfbf31ae80b4ec14eb6f6d Mon Sep 17 00:00:00 2001 From: Kotresh HR Date: Mon, 27 Sep 2021 19:22:27 +0530 Subject: ceph: don't rely on error_string to validate blocklisted session. The "error_string" in the metadata of MClientSession is being parsed by kclient to validate whether the session is blocklisted. The "error_string" is for humans and shouldn't be relied on it. Hence added the flag to MClientsession to indicate the session is blocklisted. [ jlayton: minor formatting cleanup ] URL: https://tracker.ceph.com/issues/47450 Signed-off-by: Kotresh HR Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index bc2699feddbe..7ad6c3d0db7d 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -302,6 +302,8 @@ enum { CEPH_SESSION_REQUEST_FLUSH_MDLOG, }; +#define CEPH_SESSION_BLOCKLISTED (1 << 0) /* session blocklisted */ + extern const char *ceph_session_op_name(int op); struct ceph_mds_session_head { -- cgit v1.2.3 From aca39d9e86f3edeaac5d2c467f5fd31e0b0df606 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= Date: Thu, 4 Nov 2021 12:31:46 +0000 Subject: libceph, ceph: move ceph_osdc_copy_from() into cephfs code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch moves ceph_osdc_copy_from() function out of libceph code into cephfs. There are no other users for this function, and there is the need (in another patch) to access internal ceph_osd_request struct members. Signed-off-by: Luís Henriques Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 83fa08a06507..3431011f364d 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -475,6 +475,14 @@ extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req, u64 expected_object_size, u64 expected_write_size, u32 flags); +extern int osd_req_op_copy_from_init(struct ceph_osd_request *req, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + u32 dst_fadvise_flags, + u32 truncate_seq, u64 truncate_size, + u8 copy_from_flags); extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, @@ -515,17 +523,6 @@ int ceph_osdc_call(struct ceph_osd_client *osdc, struct page *req_page, size_t req_len, struct page **resp_pages, size_t *resp_len); -int ceph_osdc_copy_from(struct ceph_osd_client *osdc, - u64 src_snapid, u64 src_version, - struct ceph_object_id *src_oid, - struct ceph_object_locator *src_oloc, - u32 src_fadvise_flags, - struct ceph_object_id *dst_oid, - struct ceph_object_locator *dst_oloc, - u32 dst_fadvise_flags, - u32 truncate_seq, u64 truncate_size, - u8 copy_from_flags); - /* watch/notify */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, -- cgit v1.2.3 From c6975d7cab5b903aadbc0f78f9af4fae1bd23a50 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 5 Nov 2021 11:05:09 -0400 Subject: arm64: Track no early_pgtable_alloc() for kmemleak After switched page size from 64KB to 4KB on several arm64 servers here, kmemleak starts to run out of early memory pool due to a huge number of those early_pgtable_alloc() calls: kmemleak_alloc_phys() memblock_alloc_range_nid() memblock_phys_alloc_range() early_pgtable_alloc() init_pmd() alloc_init_pud() __create_pgd_mapping() __map_memblock() paging_init() setup_arch() start_kernel() Increased the default value of DEBUG_KMEMLEAK_MEM_POOL_SIZE by 4 times won't be enough for a server with 200GB+ memory. There isn't much interesting to check memory leaks for those early page tables and those early memory mappings should not reference to other memory. Hence, no kmemleak false positives, and we can safely skip tracking those early allocations from kmemleak like we did in the commit fed84c785270 ("mm/memblock.c: skip kmemleak for kasan_init()") without needing to introduce complications to automatically scale the value depends on the runtime memory size etc. After the patch, the default value of DEBUG_KMEMLEAK_MEM_POOL_SIZE becomes sufficient again. Signed-off-by: Qian Cai Reviewed-by: Catalin Marinas Reviewed-by: Mike Rapoport Link: https://lore.kernel.org/r/20211105150509.7826-1-quic_qiancai@quicinc.com Signed-off-by: Will Deacon --- include/linux/memblock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 34de69b3b8ba..efc896155dae 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -372,7 +372,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r) /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) #define MEMBLOCK_ALLOC_ACCESSIBLE 0 -#define MEMBLOCK_ALLOC_KASAN 1 +#define MEMBLOCK_ALLOC_NOLEAKTRACE 1 /* We are using top down, so it is safe to use 0 here */ #define MEMBLOCK_LOW_LIMIT 0 -- cgit v1.2.3 From dfd5bb23ad75bdabde89ac3166705a450bf16acb Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Wed, 5 May 2021 14:00:06 +0200 Subject: PCI: Export pci_dev_lock() Commit e3a9b1212b9d ("PCI: Export pci_dev_trylock() and pci_dev_unlock()") already exported pci_dev_trylock()/pci_dev_unlock() however in some circumstances such as during error recovery it makes sense to block waiting to get full access to the device so also export pci_dev_lock(). Link: https://lore.kernel.org/all/20210928181014.GA713179@bhelgaas/ Acked-by: Pierre Morel Acked-by: Bjorn Helgaas Signed-off-by: Niklas Schnelle Signed-off-by: Vasily Gorbik --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b4dbcc86b3f1..d307b071b65e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1664,6 +1664,7 @@ void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); +void pci_dev_lock(struct pci_dev *dev); int pci_dev_trylock(struct pci_dev *dev); void pci_dev_unlock(struct pci_dev *dev); -- cgit v1.2.3 From 40a34121ac1dc52ed9cd34a8f4e48e32517a52fd Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 3 Nov 2021 13:47:32 -0700 Subject: bpf, sockmap: Use stricter sk state checks in sk_lookup_assign In order to fix an issue with sockets in TCP sockmap redirect cases we plan to allow CLOSE state sockets to exist in the sockmap. However, the check in bpf_sk_lookup_assign() currently only invalidates sockets in the TCP_ESTABLISHED case relying on the checks on sockmap insert to ensure we never SOCK_CLOSE state sockets in the map. To prepare for this change we flip the logic in bpf_sk_lookup_assign() to explicitly test for the accepted cases. Namely, a tcp socket in TCP_LISTEN or a udp socket in TCP_CLOSE state. This also makes the code more resilent to future changes. Suggested-by: Jakub Sitnicki Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20211103204736.248403-2-john.fastabend@gmail.com --- include/linux/skmsg.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index b4256847c707..584d94be9c8b 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -507,6 +507,18 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return !!psock->saved_data_ready; } +static inline bool sk_is_tcp(const struct sock *sk) +{ + return sk->sk_type == SOCK_STREAM && + sk->sk_protocol == IPPROTO_TCP; +} + +static inline bool sk_is_udp(const struct sock *sk) +{ + return sk->sk_type == SOCK_DGRAM && + sk->sk_protocol == IPPROTO_UDP; +} + #if IS_ENABLED(CONFIG_NET_SOCK_MSG) #define BPF_F_STRPARSER (1UL << 1) -- cgit v1.2.3 From cf30f6a5f0c60ec98a637b836bef6915f602c6ab Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Fri, 11 Sep 2020 16:49:00 -0700 Subject: lib: zstd: Add kernel-specific API This patch: - Moves `include/linux/zstd.h` -> `include/linux/zstd_lib.h` - Updates modified zstd headers to yearless copyright - Adds a new API in `include/linux/zstd.h` that is functionally equivalent to the in-use subset of the current API. Functions are renamed to avoid symbol collisions with zstd, to make it clear it is not the upstream zstd API, and to follow the kernel style guide. - Updates all callers to use the new API. There are no functional changes in this patch. Since there are no functional change, I felt it was okay to update all the callers in a single patch. Once the API is approved, the callers are mechanically changed. This patch is preparing for the 3rd patch in this series, which updates zstd to version 1.4.10. Since the upstream zstd API is no longer exposed to callers, the update can happen transparently. Signed-off-by: Nick Terrell Tested By: Paul Jones Tested-by: Oleksandr Natalenko Tested-by: Sedat Dilek # LLVM/Clang v13.0.0 on x86-64 Tested-by: Jean-Denis Girard --- include/linux/zstd.h | 1243 ++++++++++------------------------------------ include/linux/zstd_lib.h | 1157 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 1420 insertions(+), 980 deletions(-) create mode 100644 include/linux/zstd_lib.h (limited to 'include/linux') diff --git a/include/linux/zstd.h b/include/linux/zstd.h index e87f78c9b19c..9fbc7729b0a0 100644 --- a/include/linux/zstd.h +++ b/include/linux/zstd.h @@ -1,138 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * Copyright (c) Yann Collet, Facebook, Inc. * All rights reserved. * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of https://github.com/facebook/zstd) and + * the GPLv2 (found in the COPYING file in the root directory of + * https://github.com/facebook/zstd). You may select, at your option, one of the + * above-listed licenses. */ -#ifndef ZSTD_H -#define ZSTD_H +#ifndef LINUX_ZSTD_H +#define LINUX_ZSTD_H -/* ====== Dependency ======*/ -#include /* size_t */ +/** + * This is a kernel-style API that wraps the upstream zstd API, which cannot be + * used directly because the symbols aren't exported. It exposes the minimal + * functionality which is currently required by users of zstd in the kernel. + * Expose extra functions from lib/zstd/zstd.h as needed. + */ +/* ====== Dependency ====== */ +#include +#include -/*-***************************************************************************** - * Introduction +/* ====== Helper Functions ====== */ +/** + * zstd_compress_bound() - maximum compressed size in worst case scenario + * @src_size: The size of the data to compress. * - * zstd, short for Zstandard, is a fast lossless compression algorithm, - * targeting real-time compression scenarios at zlib-level and better - * compression ratios. The zstd compression library provides in-memory - * compression and decompression functions. The library supports compression - * levels from 1 up to ZSTD_maxCLevel() which is 22. Levels >= 20, labeled - * ultra, should be used with caution, as they require more memory. - * Compression can be done in: - * - a single step, reusing a context (described as Explicit memory management) - * - unbounded multiple steps (described as Streaming compression) - * The compression ratio achievable on small data can be highly improved using - * compression with a dictionary in: - * - a single step (described as Simple dictionary API) - * - a single step, reusing a dictionary (described as Fast dictionary API) - ******************************************************************************/ - -/*====== Helper functions ======*/ + * Return: The maximum compressed size in the worst case scenario. + */ +size_t zstd_compress_bound(size_t src_size); /** - * enum ZSTD_ErrorCode - zstd error codes + * zstd_is_error() - tells if a size_t function result is an error code + * @code: The function result to check for error. * - * Functions that return size_t can be checked for errors using ZSTD_isError() - * and the ZSTD_ErrorCode can be extracted using ZSTD_getErrorCode(). + * Return: Non-zero iff the code is an error. + */ +unsigned int zstd_is_error(size_t code); + +/** + * enum zstd_error_code - zstd error codes */ -typedef enum { - ZSTD_error_no_error, - ZSTD_error_GENERIC, - ZSTD_error_prefix_unknown, - ZSTD_error_version_unsupported, - ZSTD_error_parameter_unknown, - ZSTD_error_frameParameter_unsupported, - ZSTD_error_frameParameter_unsupportedBy32bits, - ZSTD_error_frameParameter_windowTooLarge, - ZSTD_error_compressionParameter_unsupported, - ZSTD_error_init_missing, - ZSTD_error_memory_allocation, - ZSTD_error_stage_wrong, - ZSTD_error_dstSize_tooSmall, - ZSTD_error_srcSize_wrong, - ZSTD_error_corruption_detected, - ZSTD_error_checksum_wrong, - ZSTD_error_tableLog_tooLarge, - ZSTD_error_maxSymbolValue_tooLarge, - ZSTD_error_maxSymbolValue_tooSmall, - ZSTD_error_dictionary_corrupted, - ZSTD_error_dictionary_wrong, - ZSTD_error_dictionaryCreation_failed, - ZSTD_error_maxCode -} ZSTD_ErrorCode; +typedef ZSTD_ErrorCode zstd_error_code; /** - * ZSTD_maxCLevel() - maximum compression level available + * zstd_get_error_code() - translates an error function result to an error code + * @code: The function result for which zstd_is_error(code) is true. * - * Return: Maximum compression level available. + * Return: A unique error code for this error. */ -int ZSTD_maxCLevel(void); +zstd_error_code zstd_get_error_code(size_t code); + /** - * ZSTD_compressBound() - maximum compressed size in worst case scenario - * @srcSize: The size of the data to compress. + * zstd_get_error_name() - translates an error function result to a string + * @code: The function result for which zstd_is_error(code) is true. * - * Return: The maximum compressed size in the worst case scenario. + * Return: An error string corresponding to the error code. */ -size_t ZSTD_compressBound(size_t srcSize); +const char *zstd_get_error_name(size_t code); + /** - * ZSTD_isError() - tells if a size_t function result is an error code - * @code: The function result to check for error. + * zstd_min_clevel() - minimum allowed compression level * - * Return: Non-zero iff the code is an error. + * Return: The minimum allowed compression level. */ -static __attribute__((unused)) unsigned int ZSTD_isError(size_t code) -{ - return code > (size_t)-ZSTD_error_maxCode; -} +int zstd_min_clevel(void); + /** - * ZSTD_getErrorCode() - translates an error function result to a ZSTD_ErrorCode - * @functionResult: The result of a function for which ZSTD_isError() is true. + * zstd_max_clevel() - maximum allowed compression level * - * Return: The ZSTD_ErrorCode corresponding to the functionResult or 0 - * if the functionResult isn't an error. + * Return: The maximum allowed compression level. */ -static __attribute__((unused)) ZSTD_ErrorCode ZSTD_getErrorCode( - size_t functionResult) -{ - if (!ZSTD_isError(functionResult)) - return (ZSTD_ErrorCode)0; - return (ZSTD_ErrorCode)(0 - functionResult); -} +int zstd_max_clevel(void); + +/* ====== Parameter Selection ====== */ /** - * enum ZSTD_strategy - zstd compression search strategy + * enum zstd_strategy - zstd compression search strategy * - * From faster to stronger. + * From faster to stronger. See zstd_lib.h. */ -typedef enum { - ZSTD_fast, - ZSTD_dfast, - ZSTD_greedy, - ZSTD_lazy, - ZSTD_lazy2, - ZSTD_btlazy2, - ZSTD_btopt, - ZSTD_btopt2 -} ZSTD_strategy; +typedef ZSTD_strategy zstd_strategy; /** - * struct ZSTD_compressionParameters - zstd compression parameters + * struct zstd_compression_parameters - zstd compression parameters * @windowLog: Log of the largest match distance. Larger means more * compression, and more memory needed during decompression. - * @chainLog: Fully searched segment. Larger means more compression, slower, - * and more memory (useless for fast). + * @chainLog: Fully searched segment. Larger means more compression, + * slower, and more memory (useless for fast). * @hashLog: Dispatch table. Larger means more compression, * slower, and more memory. * @searchLog: Number of searches. Larger means more compression and slower. @@ -141,1017 +99,342 @@ typedef enum { * @targetLength: Acceptable match size for optimal parser (only). Larger means * more compression, and slower. * @strategy: The zstd compression strategy. + * + * See zstd_lib.h. */ -typedef struct { - unsigned int windowLog; - unsigned int chainLog; - unsigned int hashLog; - unsigned int searchLog; - unsigned int searchLength; - unsigned int targetLength; - ZSTD_strategy strategy; -} ZSTD_compressionParameters; +typedef ZSTD_compressionParameters zstd_compression_parameters; /** - * struct ZSTD_frameParameters - zstd frame parameters - * @contentSizeFlag: Controls whether content size will be present in the frame - * header (when known). - * @checksumFlag: Controls whether a 32-bit checksum is generated at the end - * of the frame for error detection. - * @noDictIDFlag: Controls whether dictID will be saved into the frame header - * when using dictionary compression. + * struct zstd_frame_parameters - zstd frame parameters + * @contentSizeFlag: Controls whether content size will be present in the + * frame header (when known). + * @checksumFlag: Controls whether a 32-bit checksum is generated at the + * end of the frame for error detection. + * @noDictIDFlag: Controls whether dictID will be saved into the frame + * header when using dictionary compression. * - * The default value is all fields set to 0. + * The default value is all fields set to 0. See zstd_lib.h. */ -typedef struct { - unsigned int contentSizeFlag; - unsigned int checksumFlag; - unsigned int noDictIDFlag; -} ZSTD_frameParameters; +typedef ZSTD_frameParameters zstd_frame_parameters; /** - * struct ZSTD_parameters - zstd parameters + * struct zstd_parameters - zstd parameters * @cParams: The compression parameters. * @fParams: The frame parameters. */ -typedef struct { - ZSTD_compressionParameters cParams; - ZSTD_frameParameters fParams; -} ZSTD_parameters; +typedef ZSTD_parameters zstd_parameters; /** - * ZSTD_getCParams() - returns ZSTD_compressionParameters for selected level - * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). - * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. - * @dictSize: The dictionary size or 0 if a dictionary isn't being used. + * zstd_get_params() - returns zstd_parameters for selected level + * @level: The compression level + * @estimated_src_size: The estimated source size to compress or 0 + * if unknown. * - * Return: The selected ZSTD_compressionParameters. + * Return: The selected zstd_parameters. */ -ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, - unsigned long long estimatedSrcSize, size_t dictSize); +zstd_parameters zstd_get_params(int level, + unsigned long long estimated_src_size); -/** - * ZSTD_getParams() - returns ZSTD_parameters for selected level - * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). - * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. - * @dictSize: The dictionary size or 0 if a dictionary isn't being used. - * - * The same as ZSTD_getCParams() except also selects the default frame - * parameters (all zero). - * - * Return: The selected ZSTD_parameters. - */ -ZSTD_parameters ZSTD_getParams(int compressionLevel, - unsigned long long estimatedSrcSize, size_t dictSize); +/* ====== Single-pass Compression ====== */ -/*-************************************* - * Explicit memory management - **************************************/ +typedef ZSTD_CCtx zstd_cctx; /** - * ZSTD_CCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_CCtx - * @cParams: The compression parameters to be used for compression. + * zstd_cctx_workspace_bound() - max memory needed to initialize a zstd_cctx + * @parameters: The compression parameters to be used. * * If multiple compression parameters might be used, the caller must call - * ZSTD_CCtxWorkspaceBound() for each set of parameters and use the maximum + * zstd_cctx_workspace_bound() for each set of parameters and use the maximum * size. * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCCtx(). + * Return: A lower bound on the size of the workspace that is passed to + * zstd_init_cctx(). */ -size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams); +size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *parameters); /** - * struct ZSTD_CCtx - the zstd compression context - * - * When compressing many times it is recommended to allocate a context just once - * and reuse it for each successive compression operation. - */ -typedef struct ZSTD_CCtx_s ZSTD_CCtx; -/** - * ZSTD_initCCtx() - initialize a zstd compression context - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Use ZSTD_CCtxWorkspaceBound() to - * determine how large the workspace must be. - * - * Return: A compression context emplaced into workspace. - */ -ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize); - -/** - * ZSTD_compressCCtx() - compress src into dst - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, ZSTD_parameters params); - -/** - * ZSTD_DCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_DCtx - * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDCtx(). - */ -size_t ZSTD_DCtxWorkspaceBound(void); - -/** - * struct ZSTD_DCtx - the zstd decompression context - * - * When decompressing many times it is recommended to allocate a context just - * once and reuse it for each successive decompression operation. - */ -typedef struct ZSTD_DCtx_s ZSTD_DCtx; -/** - * ZSTD_initDCtx() - initialize a zstd decompression context - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Use ZSTD_DCtxWorkspaceBound() to - * determine how large the workspace must be. - * - * Return: A decompression context emplaced into workspace. - */ -ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize); - -/** - * ZSTD_decompressDCtx() - decompress zstd compressed src into dst - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_decompressDCtx(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); - -/*-************************ - * Simple dictionary API - **************************/ - -/** - * ZSTD_compress_usingDict() - compress src into dst using a dictionary - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @dict: The dictionary to use for compression. - * @dictSize: The size of the dictionary. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * - * Compression using a predefined dictionary. The same dictionary must be used - * during decompression. - * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const void *dict, size_t dictSize, - ZSTD_parameters params); - -/** - * ZSTD_decompress_usingDict() - decompress src into dst using a dictionary - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * @dict: The dictionary to use for decompression. The same dictionary - * must've been used to compress the data. - * @dictSize: The size of the dictionary. - * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_decompress_usingDict(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const void *dict, size_t dictSize); - -/*-************************** - * Fast dictionary API - ***************************/ - -/** - * ZSTD_CDictWorkspaceBound() - memory needed to initialize a ZSTD_CDict - * @cParams: The compression parameters to be used for compression. + * zstd_init_cctx() - initialize a zstd compression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspace_size: The size of workspace. Use zstd_cctx_workspace_bound() to + * determine how large the workspace must be. * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCDict(). - */ -size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams); - -/** - * struct ZSTD_CDict - a digested dictionary to be used for compression + * Return: A zstd compression context or NULL on error. */ -typedef struct ZSTD_CDict_s ZSTD_CDict; +zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size); /** - * ZSTD_initCDict() - initialize a digested dictionary for compression - * @dictBuffer: The dictionary to digest. The buffer is referenced by the - * ZSTD_CDict so it must outlive the returned ZSTD_CDict. - * @dictSize: The size of the dictionary. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * @workspace: The workspace. It must outlive the returned ZSTD_CDict. - * @workspaceSize: The workspace size. Must be at least - * ZSTD_CDictWorkspaceBound(params.cParams). + * zstd_compress_cctx() - compress src into dst with the initialized parameters + * @cctx: The context. Must have been initialized with zstd_init_cctx(). + * @dst: The buffer to compress src into. + * @dst_capacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @src_size: The size of the data to compress. + * @parameters: The compression parameters to be used. * - * When compressing multiple messages / blocks with the same dictionary it is - * recommended to load it just once. The ZSTD_CDict merely references the - * dictBuffer, so it must outlive the returned ZSTD_CDict. - * - * Return: The digested dictionary emplaced into workspace. + * Return: The compressed size or an error, which can be checked using + * zstd_is_error(). */ -ZSTD_CDict *ZSTD_initCDict(const void *dictBuffer, size_t dictSize, - ZSTD_parameters params, void *workspace, size_t workspaceSize); +size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, + const void *src, size_t src_size, const zstd_parameters *parameters); -/** - * ZSTD_compress_usingCDict() - compress src into dst using a ZSTD_CDict - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(cParams) where - * cParams are the compression parameters used to initialize the - * cdict. - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @cdict: The digested dictionary to use for compression. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * - * Compression using a digested dictionary. The same dictionary must be used - * during decompression. - * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const ZSTD_CDict *cdict); +/* ====== Single-pass Decompression ====== */ +typedef ZSTD_DCtx zstd_dctx; /** - * ZSTD_DDictWorkspaceBound() - memory needed to initialize a ZSTD_DDict + * zstd_dctx_workspace_bound() - max memory needed to initialize a zstd_dctx * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDDict(). - */ -size_t ZSTD_DDictWorkspaceBound(void); - -/** - * struct ZSTD_DDict - a digested dictionary to be used for decompression + * Return: A lower bound on the size of the workspace that is passed to + * zstd_init_dctx(). */ -typedef struct ZSTD_DDict_s ZSTD_DDict; +size_t zstd_dctx_workspace_bound(void); /** - * ZSTD_initDDict() - initialize a digested dictionary for decompression - * @dictBuffer: The dictionary to digest. The buffer is referenced by the - * ZSTD_DDict so it must outlive the returned ZSTD_DDict. - * @dictSize: The size of the dictionary. - * @workspace: The workspace. It must outlive the returned ZSTD_DDict. - * @workspaceSize: The workspace size. Must be at least - * ZSTD_DDictWorkspaceBound(). - * - * When decompressing multiple messages / blocks with the same dictionary it is - * recommended to load it just once. The ZSTD_DDict merely references the - * dictBuffer, so it must outlive the returned ZSTD_DDict. + * zstd_init_dctx() - initialize a zstd decompression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspace_size: The size of workspace. Use zstd_dctx_workspace_bound() to + * determine how large the workspace must be. * - * Return: The digested dictionary emplaced into workspace. + * Return: A zstd decompression context or NULL on error. */ -ZSTD_DDict *ZSTD_initDDict(const void *dictBuffer, size_t dictSize, - void *workspace, size_t workspaceSize); +zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size); /** - * ZSTD_decompress_usingDDict() - decompress src into dst using a ZSTD_DDict - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * @ddict: The digested dictionary to use for decompression. The same - * dictionary must've been used to compress the data. + * zstd_decompress_dctx() - decompress zstd compressed src into dst + * @dctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dst_capacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @src_size: The exact size of the data to decompress. * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). + * Return: The decompressed size or an error, which can be checked using + * zstd_is_error(). */ -size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, - size_t dstCapacity, const void *src, size_t srcSize, - const ZSTD_DDict *ddict); +size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity, + const void *src, size_t src_size); - -/*-************************** - * Streaming - ***************************/ +/* ====== Streaming Buffers ====== */ /** - * struct ZSTD_inBuffer - input buffer for streaming + * struct zstd_in_buffer - input buffer for streaming * @src: Start of the input buffer. * @size: Size of the input buffer. * @pos: Position where reading stopped. Will be updated. * Necessarily 0 <= pos <= size. + * + * See zstd_lib.h. */ -typedef struct ZSTD_inBuffer_s { - const void *src; - size_t size; - size_t pos; -} ZSTD_inBuffer; +typedef ZSTD_inBuffer zstd_in_buffer; /** - * struct ZSTD_outBuffer - output buffer for streaming + * struct zstd_out_buffer - output buffer for streaming * @dst: Start of the output buffer. * @size: Size of the output buffer. * @pos: Position where writing stopped. Will be updated. * Necessarily 0 <= pos <= size. + * + * See zstd_lib.h. */ -typedef struct ZSTD_outBuffer_s { - void *dst; - size_t size; - size_t pos; -} ZSTD_outBuffer; +typedef ZSTD_outBuffer zstd_out_buffer; +/* ====== Streaming Compression ====== */ - -/*-***************************************************************************** - * Streaming compression - HowTo - * - * A ZSTD_CStream object is required to track streaming operation. - * Use ZSTD_initCStream() to initialize a ZSTD_CStream object. - * ZSTD_CStream objects can be reused multiple times on consecutive compression - * operations. It is recommended to re-use ZSTD_CStream in situations where many - * streaming operations will be achieved consecutively. Use one separate - * ZSTD_CStream per thread for parallel execution. - * - * Use ZSTD_compressStream() repetitively to consume input stream. - * The function will automatically update both `pos` fields. - * Note that it may not consume the entire input, in which case `pos < size`, - * and it's up to the caller to present again remaining data. - * It returns a hint for the preferred number of bytes to use as an input for - * the next function call. - * - * At any moment, it's possible to flush whatever data remains within internal - * buffer, using ZSTD_flushStream(). `output->pos` will be updated. There might - * still be some content left within the internal buffer if `output->size` is - * too small. It returns the number of bytes left in the internal buffer and - * must be called until it returns 0. - * - * ZSTD_endStream() instructs to finish a frame. It will perform a flush and - * write frame epilogue. The epilogue is required for decoders to consider a - * frame completed. Similar to ZSTD_flushStream(), it may not be able to flush - * the full content if `output->size` is too small. In which case, call again - * ZSTD_endStream() to complete the flush. It returns the number of bytes left - * in the internal buffer and must be called until it returns 0. - ******************************************************************************/ +typedef ZSTD_CStream zstd_cstream; /** - * ZSTD_CStreamWorkspaceBound() - memory needed to initialize a ZSTD_CStream - * @cParams: The compression parameters to be used for compression. + * zstd_cstream_workspace_bound() - memory needed to initialize a zstd_cstream + * @cparams: The compression parameters to be used for compression. * * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCStream() and ZSTD_initCStream_usingCDict(). - */ -size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams); - -/** - * struct ZSTD_CStream - the zstd streaming compression context + * zstd_init_cstream(). */ -typedef struct ZSTD_CStream_s ZSTD_CStream; +size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams); -/*===== ZSTD_CStream management functions =====*/ /** - * ZSTD_initCStream() - initialize a zstd streaming compression context - * @params: The zstd compression parameters. - * @pledgedSrcSize: If params.fParams.contentSizeFlag == 1 then the caller must - * pass the source size (zero means empty source). Otherwise, - * the caller may optionally pass the source size, or zero if - * unknown. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_CStreamWorkspaceBound(params.cParams) to determine - * how large the workspace must be. + * zstd_init_cstream() - initialize a zstd streaming compression context + * @parameters The zstd parameters to use for compression. + * @pledged_src_size: If params.fParams.contentSizeFlag == 1 then the caller + * must pass the source size (zero means empty source). + * Otherwise, the caller may optionally pass the source + * size, or zero if unknown. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspace_size: The size of workspace. + * Use zstd_cstream_workspace_bound(params->cparams) to + * determine how large the workspace must be. * - * Return: The zstd streaming compression context. + * Return: The zstd streaming compression context or NULL on error. */ -ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, - unsigned long long pledgedSrcSize, void *workspace, - size_t workspaceSize); +zstd_cstream *zstd_init_cstream(const zstd_parameters *parameters, + unsigned long long pledged_src_size, void *workspace, size_t workspace_size); /** - * ZSTD_initCStream_usingCDict() - initialize a streaming compression context - * @cdict: The digested dictionary to use for compression. - * @pledgedSrcSize: Optionally the source size, or zero if unknown. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Call ZSTD_CStreamWorkspaceBound() - * with the cParams used to initialize the cdict to determine - * how large the workspace must be. - * - * Return: The zstd streaming compression context. - */ -ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, - unsigned long long pledgedSrcSize, void *workspace, - size_t workspaceSize); - -/*===== Streaming compression functions =====*/ -/** - * ZSTD_resetCStream() - reset the context using parameters from creation - * @zcs: The zstd streaming compression context to reset. - * @pledgedSrcSize: Optionally the source size, or zero if unknown. + * zstd_reset_cstream() - reset the context using parameters from creation + * @cstream: The zstd streaming compression context to reset. + * @pledged_src_size: Optionally the source size, or zero if unknown. * * Resets the context using the parameters from creation. Skips dictionary - * loading, since it can be reused. If `pledgedSrcSize` is non-zero the frame + * loading, since it can be reused. If `pledged_src_size` is non-zero the frame * content size is always written into the frame header. * - * Return: Zero or an error, which can be checked using ZSTD_isError(). + * Return: Zero or an error, which can be checked using + * zstd_is_error(). */ -size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize); +size_t zstd_reset_cstream(zstd_cstream *cstream, + unsigned long long pledged_src_size); + /** - * ZSTD_compressStream() - streaming compress some of input into output - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. - * @input: Source buffer. `input->pos` is updated to indicate how much data was - * read. Note that it may not consume the entire input, in which case - * `input->pos < input->size`, and it's up to the caller to present - * remaining data again. + * zstd_compress_stream() - streaming compress some of input into output + * @cstream: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * @input: Source buffer. `input->pos` is updated to indicate how much data + * was read. Note that it may not consume the entire input, in which + * case `input->pos < input->size`, and it's up to the caller to + * present remaining data again. * * The `input` and `output` buffers may be any size. Guaranteed to make some * forward progress if `input` and `output` are not empty. * - * Return: A hint for the number of bytes to use as the input for the next - * function call or an error, which can be checked using - * ZSTD_isError(). + * Return: A hint for the number of bytes to use as the input for the next + * function call or an error, which can be checked using + * zstd_is_error(). */ -size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, - ZSTD_inBuffer *input); +size_t zstd_compress_stream(zstd_cstream *cstream, zstd_out_buffer *output, + zstd_in_buffer *input); + /** - * ZSTD_flushStream() - flush internal buffers into output - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. + * zstd_flush_stream() - flush internal buffers into output + * @cstream: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. * - * ZSTD_flushStream() must be called until it returns 0, meaning all the data - * has been flushed. Since ZSTD_flushStream() causes a block to be ended, + * zstd_flush_stream() must be called until it returns 0, meaning all the data + * has been flushed. Since zstd_flush_stream() causes a block to be ended, * calling it too often will degrade the compression ratio. * - * Return: The number of bytes still present within internal buffers or an - * error, which can be checked using ZSTD_isError(). - */ -size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); -/** - * ZSTD_endStream() - flush internal buffers into output and end the frame - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. - * - * ZSTD_endStream() must be called until it returns 0, meaning all the data has - * been flushed and the frame epilogue has been written. - * - * Return: The number of bytes still present within internal buffers or an - * error, which can be checked using ZSTD_isError(). + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using zstd_is_error(). */ -size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); +size_t zstd_flush_stream(zstd_cstream *cstream, zstd_out_buffer *output); /** - * ZSTD_CStreamInSize() - recommended size for the input buffer - * - * Return: The recommended size for the input buffer. - */ -size_t ZSTD_CStreamInSize(void); -/** - * ZSTD_CStreamOutSize() - recommended size for the output buffer + * zstd_end_stream() - flush internal buffers into output and end the frame + * @cstream: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. * - * When the output buffer is at least this large, it is guaranteed to be large - * enough to flush at least one complete compressed block. + * zstd_end_stream() must be called until it returns 0, meaning all the data has + * been flushed and the frame epilogue has been written. * - * Return: The recommended size for the output buffer. + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using zstd_is_error(). */ -size_t ZSTD_CStreamOutSize(void); +size_t zstd_end_stream(zstd_cstream *cstream, zstd_out_buffer *output); +/* ====== Streaming Decompression ====== */ - -/*-***************************************************************************** - * Streaming decompression - HowTo - * - * A ZSTD_DStream object is required to track streaming operations. - * Use ZSTD_initDStream() to initialize a ZSTD_DStream object. - * ZSTD_DStream objects can be re-used multiple times. - * - * Use ZSTD_decompressStream() repetitively to consume your input. - * The function will update both `pos` fields. - * If `input->pos < input->size`, some input has not been consumed. - * It's up to the caller to present again remaining data. - * If `output->pos < output->size`, decoder has flushed everything it could. - * Returns 0 iff a frame is completely decoded and fully flushed. - * Otherwise it returns a suggested next input size that will never load more - * than the current frame. - ******************************************************************************/ +typedef ZSTD_DStream zstd_dstream; /** - * ZSTD_DStreamWorkspaceBound() - memory needed to initialize a ZSTD_DStream - * @maxWindowSize: The maximum window size allowed for compressed frames. + * zstd_dstream_workspace_bound() - memory needed to initialize a zstd_dstream + * @max_window_size: The maximum window size allowed for compressed frames. * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDStream() and ZSTD_initDStream_usingDDict(). + * Return: A lower bound on the size of the workspace that is passed + * to zstd_init_dstream(). */ -size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize); +size_t zstd_dstream_workspace_bound(size_t max_window_size); /** - * struct ZSTD_DStream - the zstd streaming decompression context - */ -typedef struct ZSTD_DStream_s ZSTD_DStream; -/*===== ZSTD_DStream management functions =====*/ -/** - * ZSTD_initDStream() - initialize a zstd streaming decompression context - * @maxWindowSize: The maximum window size allowed for compressed frames. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine - * how large the workspace must be. - * - * Return: The zstd streaming decompression context. - */ -ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, - size_t workspaceSize); -/** - * ZSTD_initDStream_usingDDict() - initialize streaming decompression context - * @maxWindowSize: The maximum window size allowed for compressed frames. - * @ddict: The digested dictionary to use for decompression. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine - * how large the workspace must be. + * zstd_init_dstream() - initialize a zstd streaming decompression context + * @max_window_size: The maximum window size allowed for compressed frames. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use zstd_dstream_workspace_bound(max_window_size) to + * determine how large the workspace must be. * - * Return: The zstd streaming decompression context. + * Return: The zstd streaming decompression context. */ -ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, - const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize); +zstd_dstream *zstd_init_dstream(size_t max_window_size, void *workspace, + size_t workspace_size); -/*===== Streaming decompression functions =====*/ /** - * ZSTD_resetDStream() - reset the context using parameters from creation - * @zds: The zstd streaming decompression context to reset. + * zstd_reset_dstream() - reset the context using parameters from creation + * @dstream: The zstd streaming decompression context to reset. * * Resets the context using the parameters from creation. Skips dictionary * loading, since it can be reused. * - * Return: Zero or an error, which can be checked using ZSTD_isError(). + * Return: Zero or an error, which can be checked using zstd_is_error(). */ -size_t ZSTD_resetDStream(ZSTD_DStream *zds); +size_t zstd_reset_dstream(zstd_dstream *dstream); + /** - * ZSTD_decompressStream() - streaming decompress some of input into output - * @zds: The zstd streaming decompression context. - * @output: Destination buffer. `output.pos` is updated to indicate how much - * decompressed data was written. - * @input: Source buffer. `input.pos` is updated to indicate how much data was - * read. Note that it may not consume the entire input, in which case - * `input.pos < input.size`, and it's up to the caller to present - * remaining data again. + * zstd_decompress_stream() - streaming decompress some of input into output + * @dstream: The zstd streaming decompression context. + * @output: Destination buffer. `output.pos` is updated to indicate how much + * decompressed data was written. + * @input: Source buffer. `input.pos` is updated to indicate how much data was + * read. Note that it may not consume the entire input, in which case + * `input.pos < input.size`, and it's up to the caller to present + * remaining data again. * * The `input` and `output` buffers may be any size. Guaranteed to make some * forward progress if `input` and `output` are not empty. - * ZSTD_decompressStream() will not consume the last byte of the frame until + * zstd_decompress_stream() will not consume the last byte of the frame until * the entire frame is flushed. * - * Return: Returns 0 iff a frame is completely decoded and fully flushed. - * Otherwise returns a hint for the number of bytes to use as the input - * for the next function call or an error, which can be checked using - * ZSTD_isError(). The size hint will never load more than the frame. - */ -size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, - ZSTD_inBuffer *input); - -/** - * ZSTD_DStreamInSize() - recommended size for the input buffer - * - * Return: The recommended size for the input buffer. - */ -size_t ZSTD_DStreamInSize(void); -/** - * ZSTD_DStreamOutSize() - recommended size for the output buffer - * - * When the output buffer is at least this large, it is guaranteed to be large - * enough to flush at least one complete decompressed block. - * - * Return: The recommended size for the output buffer. - */ -size_t ZSTD_DStreamOutSize(void); - - -/* --- Constants ---*/ -#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ -#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U - -#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) -#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) - -#define ZSTD_WINDOWLOG_MAX_32 27 -#define ZSTD_WINDOWLOG_MAX_64 27 -#define ZSTD_WINDOWLOG_MAX \ - ((unsigned int)(sizeof(size_t) == 4 \ - ? ZSTD_WINDOWLOG_MAX_32 \ - : ZSTD_WINDOWLOG_MAX_64)) -#define ZSTD_WINDOWLOG_MIN 10 -#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX -#define ZSTD_HASHLOG_MIN 6 -#define ZSTD_CHAINLOG_MAX (ZSTD_WINDOWLOG_MAX+1) -#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN -#define ZSTD_HASHLOG3_MAX 17 -#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) -#define ZSTD_SEARCHLOG_MIN 1 -/* only for ZSTD_fast, other strategies are limited to 6 */ -#define ZSTD_SEARCHLENGTH_MAX 7 -/* only for ZSTD_btopt, other strategies are limited to 4 */ -#define ZSTD_SEARCHLENGTH_MIN 3 -#define ZSTD_TARGETLENGTH_MIN 4 -#define ZSTD_TARGETLENGTH_MAX 999 - -/* for static allocation */ -#define ZSTD_FRAMEHEADERSIZE_MAX 18 -#define ZSTD_FRAMEHEADERSIZE_MIN 6 -#define ZSTD_frameHeaderSize_prefix 5 -#define ZSTD_frameHeaderSize_min ZSTD_FRAMEHEADERSIZE_MIN -#define ZSTD_frameHeaderSize_max ZSTD_FRAMEHEADERSIZE_MAX -/* magic number + skippable frame length */ -#define ZSTD_skippableHeaderSize 8 - - -/*-************************************* - * Compressed size functions - **************************************/ - -/** - * ZSTD_findFrameCompressedSize() - returns the size of a compressed frame - * @src: Source buffer. It should point to the start of a zstd encoded frame - * or a skippable frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * size of the frame. - * - * Return: The compressed size of the frame pointed to by `src` or an error, - * which can be check with ZSTD_isError(). - * Suitable to pass to ZSTD_decompress() or similar functions. - */ -size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize); - -/*-************************************* - * Decompressed size functions - **************************************/ -/** - * ZSTD_getFrameContentSize() - returns the content size in a zstd frame header - * @src: It should point to the start of a zstd encoded frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * frame header. `ZSTD_frameHeaderSize_max` is always large enough. - * - * Return: The frame content size stored in the frame header if known. - * `ZSTD_CONTENTSIZE_UNKNOWN` if the content size isn't stored in the - * frame header. `ZSTD_CONTENTSIZE_ERROR` on invalid input. - */ -unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); - -/** - * ZSTD_findDecompressedSize() - returns decompressed size of a series of frames - * @src: It should point to the start of a series of zstd encoded and/or - * skippable frames. - * @srcSize: The exact size of the series of frames. - * - * If any zstd encoded frame in the series doesn't have the frame content size - * set, `ZSTD_CONTENTSIZE_UNKNOWN` is returned. But frame content size is always - * set when using ZSTD_compress(). The decompressed size can be very large. - * If the source is untrusted, the decompressed size could be wrong or - * intentionally modified. Always ensure the result fits within the - * application's authorized limits. ZSTD_findDecompressedSize() handles multiple - * frames, and so it must traverse the input to read each frame header. This is - * efficient as most of the data is skipped, however it does mean that all frame - * data must be present and valid. - * - * Return: Decompressed size of all the data contained in the frames if known. - * `ZSTD_CONTENTSIZE_UNKNOWN` if the decompressed size is unknown. - * `ZSTD_CONTENTSIZE_ERROR` if an error occurred. - */ -unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize); - -/*-************************************* - * Advanced compression functions - **************************************/ -/** - * ZSTD_checkCParams() - ensure parameter values remain within authorized range - * @cParams: The zstd compression parameters. - * - * Return: Zero or an error, which can be checked using ZSTD_isError(). - */ -size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams); - -/** - * ZSTD_adjustCParams() - optimize parameters for a given srcSize and dictSize - * @srcSize: Optionally the estimated source size, or zero if unknown. - * @dictSize: Optionally the estimated dictionary size, or zero if unknown. - * - * Return: The optimized parameters. - */ -ZSTD_compressionParameters ZSTD_adjustCParams( - ZSTD_compressionParameters cParams, unsigned long long srcSize, - size_t dictSize); - -/*--- Advanced decompression functions ---*/ - -/** - * ZSTD_isFrame() - returns true iff the buffer starts with a valid frame - * @buffer: The source buffer to check. - * @size: The size of the source buffer, must be at least 4 bytes. - * - * Return: True iff the buffer starts with a zstd or skippable frame identifier. - */ -unsigned int ZSTD_isFrame(const void *buffer, size_t size); - -/** - * ZSTD_getDictID_fromDict() - returns the dictionary id stored in a dictionary - * @dict: The dictionary buffer. - * @dictSize: The size of the dictionary buffer. - * - * Return: The dictionary id stored within the dictionary or 0 if the - * dictionary is not a zstd dictionary. If it returns 0 the - * dictionary can still be loaded as a content-only dictionary. + * Return: Returns 0 iff a frame is completely decoded and fully flushed. + * Otherwise returns a hint for the number of bytes to use as the + * input for the next function call or an error, which can be checked + * using zstd_is_error(). The size hint will never load more than the + * frame. */ -unsigned int ZSTD_getDictID_fromDict(const void *dict, size_t dictSize); +size_t zstd_decompress_stream(zstd_dstream *dstream, zstd_out_buffer *output, + zstd_in_buffer *input); -/** - * ZSTD_getDictID_fromDDict() - returns the dictionary id stored in a ZSTD_DDict - * @ddict: The ddict to find the id of. - * - * Return: The dictionary id stored within `ddict` or 0 if the dictionary is not - * a zstd dictionary. If it returns 0 `ddict` will be loaded as a - * content-only dictionary. - */ -unsigned int ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict); +/* ====== Frame Inspection Functions ====== */ /** - * ZSTD_getDictID_fromFrame() - returns the dictionary id stored in a zstd frame - * @src: Source buffer. It must be a zstd encoded frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * frame header. `ZSTD_frameHeaderSize_max` is always large enough. + * zstd_find_frame_compressed_size() - returns the size of a compressed frame + * @src: Source buffer. It should point to the start of a zstd encoded + * frame or a skippable frame. + * @src_size: The size of the source buffer. It must be at least as large as the + * size of the frame. * - * Return: The dictionary id required to decompress the frame stored within - * `src` or 0 if the dictionary id could not be decoded. It can return - * 0 if the frame does not require a dictionary, the dictionary id - * wasn't stored in the frame, `src` is not a zstd frame, or `srcSize` - * is too small. + * Return: The compressed size of the frame pointed to by `src` or an error, + * which can be check with zstd_is_error(). + * Suitable to pass to ZSTD_decompress() or similar functions. */ -unsigned int ZSTD_getDictID_fromFrame(const void *src, size_t srcSize); +size_t zstd_find_frame_compressed_size(const void *src, size_t src_size); /** - * struct ZSTD_frameParams - zstd frame parameters stored in the frame header + * struct zstd_frame_params - zstd frame parameters stored in the frame header * @frameContentSize: The frame content size, or 0 if not present. * @windowSize: The window size, or 0 if the frame is a skippable frame. * @dictID: The dictionary id, or 0 if not present. * @checksumFlag: Whether a checksum was used. */ -typedef struct { - unsigned long long frameContentSize; - unsigned int windowSize; - unsigned int dictID; - unsigned int checksumFlag; -} ZSTD_frameParams; +typedef ZSTD_frameParams zstd_frame_header; /** - * ZSTD_getFrameParams() - extracts parameters from a zstd or skippable frame - * @fparamsPtr: On success the frame parameters are written here. - * @src: The source buffer. It must point to a zstd or skippable frame. - * @srcSize: The size of the source buffer. `ZSTD_frameHeaderSize_max` is - * always large enough to succeed. + * zstd_get_frame_header() - extracts parameters from a zstd or skippable frame + * @params: On success the frame parameters are written here. + * @src: The source buffer. It must point to a zstd or skippable frame. + * @src_size: The size of the source buffer. * - * Return: 0 on success. If more data is required it returns how many bytes - * must be provided to make forward progress. Otherwise it returns - * an error, which can be checked using ZSTD_isError(). + * Return: 0 on success. If more data is required it returns how many bytes + * must be provided to make forward progress. Otherwise it returns + * an error, which can be checked using zstd_is_error(). */ -size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, - size_t srcSize); - -/*-***************************************************************************** - * Buffer-less and synchronous inner streaming functions - * - * This is an advanced API, giving full control over buffer management, for - * users which need direct control over memory. - * But it's also a complex one, with many restrictions (documented below). - * Prefer using normal streaming API for an easier experience - ******************************************************************************/ - -/*-***************************************************************************** - * Buffer-less streaming compression (synchronous mode) - * - * A ZSTD_CCtx object is required to track streaming operations. - * Use ZSTD_initCCtx() to initialize a context. - * ZSTD_CCtx object can be re-used multiple times within successive compression - * operations. - * - * Start by initializing a context. - * Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary - * compression, - * or ZSTD_compressBegin_advanced(), for finer parameter control. - * It's also possible to duplicate a reference context which has already been - * initialized, using ZSTD_copyCCtx() - * - * Then, consume your input using ZSTD_compressContinue(). - * There are some important considerations to keep in mind when using this - * advanced function : - * - ZSTD_compressContinue() has no internal buffer. It uses externally provided - * buffer only. - * - Interface is synchronous : input is consumed entirely and produce 1+ - * (or more) compressed blocks. - * - Caller must ensure there is enough space in `dst` to store compressed data - * under worst case scenario. Worst case evaluation is provided by - * ZSTD_compressBound(). - * ZSTD_compressContinue() doesn't guarantee recover after a failed - * compression. - * - ZSTD_compressContinue() presumes prior input ***is still accessible and - * unmodified*** (up to maximum distance size, see WindowLog). - * It remembers all previous contiguous blocks, plus one separated memory - * segment (which can itself consists of multiple contiguous blocks) - * - ZSTD_compressContinue() detects that prior input has been overwritten when - * `src` buffer overlaps. In which case, it will "discard" the relevant memory - * section from its history. - * - * Finish a frame with ZSTD_compressEnd(), which will write the last block(s) - * and optional checksum. It's possible to use srcSize==0, in which case, it - * will write a final empty block to end the frame. Without last block mark, - * frames will be considered unfinished (corrupted) by decoders. - * - * `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new - * frame. - ******************************************************************************/ - -/*===== Buffer-less streaming compression functions =====*/ -size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel); -size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, - size_t dictSize, int compressionLevel); -size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, - size_t dictSize, ZSTD_parameters params, - unsigned long long pledgedSrcSize); -size_t ZSTD_copyCCtx(ZSTD_CCtx *cctx, const ZSTD_CCtx *preparedCCtx, - unsigned long long pledgedSrcSize); -size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, - unsigned long long pledgedSrcSize); -size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); - - - -/*-***************************************************************************** - * Buffer-less streaming decompression (synchronous mode) - * - * A ZSTD_DCtx object is required to track streaming operations. - * Use ZSTD_initDCtx() to initialize a context. - * A ZSTD_DCtx object can be re-used multiple times. - * - * First typical operation is to retrieve frame parameters, using - * ZSTD_getFrameParams(). It fills a ZSTD_frameParams structure which provide - * important information to correctly decode the frame, such as the minimum - * rolling buffer size to allocate to decompress data (`windowSize`), and the - * dictionary ID used. - * Note: content size is optional, it may not be present. 0 means unknown. - * Note that these values could be wrong, either because of data malformation, - * or because an attacker is spoofing deliberate false information. As a - * consequence, check that values remain within valid application range, - * especially `windowSize`, before allocation. Each application can set its own - * limit, depending on local restrictions. For extended interoperability, it is - * recommended to support at least 8 MB. - * Frame parameters are extracted from the beginning of the compressed frame. - * Data fragment must be large enough to ensure successful decoding, typically - * `ZSTD_frameHeaderSize_max` bytes. - * Result: 0: successful decoding, the `ZSTD_frameParams` structure is filled. - * >0: `srcSize` is too small, provide at least this many bytes. - * errorCode, which can be tested using ZSTD_isError(). - * - * Start decompression, with ZSTD_decompressBegin() or - * ZSTD_decompressBegin_usingDict(). Alternatively, you can copy a prepared - * context, using ZSTD_copyDCtx(). - * - * Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() - * alternatively. - * ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' - * to ZSTD_decompressContinue(). - * ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will - * fail. - * - * The result of ZSTD_decompressContinue() is the number of bytes regenerated - * within 'dst' (necessarily <= dstCapacity). It can be zero, which is not an - * error; it just means ZSTD_decompressContinue() has decoded some metadata - * item. It can also be an error code, which can be tested with ZSTD_isError(). - * - * ZSTD_decompressContinue() needs previous data blocks during decompression, up - * to `windowSize`. They should preferably be located contiguously, prior to - * current block. Alternatively, a round buffer of sufficient size is also - * possible. Sufficient size is determined by frame parameters. - * ZSTD_decompressContinue() is very sensitive to contiguity, if 2 blocks don't - * follow each other, make sure that either the compressor breaks contiguity at - * the same place, or that previous contiguous segment is large enough to - * properly handle maximum back-reference. - * - * A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. - * Context can then be reset to start a new decompression. - * - * Note: it's possible to know if next input to present is a header or a block, - * using ZSTD_nextInputType(). This information is not required to properly - * decode a frame. - * - * == Special case: skippable frames == - * - * Skippable frames allow integration of user-defined data into a flow of - * concatenated frames. Skippable frames will be ignored (skipped) by a - * decompressor. The format of skippable frames is as follows: - * a) Skippable frame ID - 4 Bytes, Little endian format, any value from - * 0x184D2A50 to 0x184D2A5F - * b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits - * c) Frame Content - any content (User Data) of length equal to Frame Size - * For skippable frames ZSTD_decompressContinue() always returns 0. - * For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 - * what means that a frame is skippable. - * Note: If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might - * actually be a zstd encoded frame with no content. For purposes of - * decompression, it is valid in both cases to skip the frame using - * ZSTD_findFrameCompressedSize() to find its size in bytes. - * It also returns frame size as fparamsPtr->frameContentSize. - ******************************************************************************/ - -/*===== Buffer-less streaming decompression functions =====*/ -size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx); -size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, - size_t dictSize); -void ZSTD_copyDCtx(ZSTD_DCtx *dctx, const ZSTD_DCtx *preparedDCtx); -size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx); -size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -typedef enum { - ZSTDnit_frameHeader, - ZSTDnit_blockHeader, - ZSTDnit_block, - ZSTDnit_lastBlock, - ZSTDnit_checksum, - ZSTDnit_skippableFrame -} ZSTD_nextInputType_e; -ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx); - -/*-***************************************************************************** - * Block functions - * - * Block functions produce and decode raw zstd blocks, without frame metadata. - * Frame metadata cost is typically ~18 bytes, which can be non-negligible for - * very small blocks (< 100 bytes). User will have to take in charge required - * information to regenerate data, such as compressed and content sizes. - * - * A few rules to respect: - * - Compressing and decompressing require a context structure - * + Use ZSTD_initCCtx() and ZSTD_initDCtx() - * - It is necessary to init context before starting - * + compression : ZSTD_compressBegin() - * + decompression : ZSTD_decompressBegin() - * + variants _usingDict() are also allowed - * + copyCCtx() and copyDCtx() work too - * - Block size is limited, it must be <= ZSTD_getBlockSizeMax() - * + If you need to compress more, cut data into multiple blocks - * + Consider using the regular ZSTD_compress() instead, as frame metadata - * costs become negligible when source size is large. - * - When a block is considered not compressible enough, ZSTD_compressBlock() - * result will be zero. In which case, nothing is produced into `dst`. - * + User must test for such outcome and deal directly with uncompressed data - * + ZSTD_decompressBlock() doesn't accept uncompressed data as input!!! - * + In case of multiple successive blocks, decoder must be informed of - * uncompressed block existence to follow proper history. Use - * ZSTD_insertBlock() in such a case. - ******************************************************************************/ - -/* Define for static allocation */ -#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) -/*===== Raw zstd block functions =====*/ -size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx); -size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, - size_t blockSize); +size_t zstd_get_frame_header(zstd_frame_header *params, const void *src, + size_t src_size); -#endif /* ZSTD_H */ +#endif /* LINUX_ZSTD_H */ diff --git a/include/linux/zstd_lib.h b/include/linux/zstd_lib.h new file mode 100644 index 000000000000..13151c34f725 --- /dev/null +++ b/include/linux/zstd_lib.h @@ -0,0 +1,1157 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of https://github.com/facebook/zstd. + * An additional grant of patent rights can be found in the PATENTS file in the + * same directory. + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License version 2 as published by the + * Free Software Foundation. This program is dual-licensed; you may select + * either version 2 of the GNU General Public License ("GPL") or BSD license + * ("BSD"). + */ + +#ifndef ZSTD_H +#define ZSTD_H + +/* ====== Dependency ======*/ +#include /* size_t */ + + +/*-***************************************************************************** + * Introduction + * + * zstd, short for Zstandard, is a fast lossless compression algorithm, + * targeting real-time compression scenarios at zlib-level and better + * compression ratios. The zstd compression library provides in-memory + * compression and decompression functions. The library supports compression + * levels from 1 up to ZSTD_maxCLevel() which is 22. Levels >= 20, labeled + * ultra, should be used with caution, as they require more memory. + * Compression can be done in: + * - a single step, reusing a context (described as Explicit memory management) + * - unbounded multiple steps (described as Streaming compression) + * The compression ratio achievable on small data can be highly improved using + * compression with a dictionary in: + * - a single step (described as Simple dictionary API) + * - a single step, reusing a dictionary (described as Fast dictionary API) + ******************************************************************************/ + +/*====== Helper functions ======*/ + +/** + * enum ZSTD_ErrorCode - zstd error codes + * + * Functions that return size_t can be checked for errors using ZSTD_isError() + * and the ZSTD_ErrorCode can be extracted using ZSTD_getErrorCode(). + */ +typedef enum { + ZSTD_error_no_error, + ZSTD_error_GENERIC, + ZSTD_error_prefix_unknown, + ZSTD_error_version_unsupported, + ZSTD_error_parameter_unknown, + ZSTD_error_frameParameter_unsupported, + ZSTD_error_frameParameter_unsupportedBy32bits, + ZSTD_error_frameParameter_windowTooLarge, + ZSTD_error_compressionParameter_unsupported, + ZSTD_error_init_missing, + ZSTD_error_memory_allocation, + ZSTD_error_stage_wrong, + ZSTD_error_dstSize_tooSmall, + ZSTD_error_srcSize_wrong, + ZSTD_error_corruption_detected, + ZSTD_error_checksum_wrong, + ZSTD_error_tableLog_tooLarge, + ZSTD_error_maxSymbolValue_tooLarge, + ZSTD_error_maxSymbolValue_tooSmall, + ZSTD_error_dictionary_corrupted, + ZSTD_error_dictionary_wrong, + ZSTD_error_dictionaryCreation_failed, + ZSTD_error_maxCode +} ZSTD_ErrorCode; + +/** + * ZSTD_maxCLevel() - maximum compression level available + * + * Return: Maximum compression level available. + */ +int ZSTD_maxCLevel(void); +/** + * ZSTD_compressBound() - maximum compressed size in worst case scenario + * @srcSize: The size of the data to compress. + * + * Return: The maximum compressed size in the worst case scenario. + */ +size_t ZSTD_compressBound(size_t srcSize); +/** + * ZSTD_isError() - tells if a size_t function result is an error code + * @code: The function result to check for error. + * + * Return: Non-zero iff the code is an error. + */ +static __attribute__((unused)) unsigned int ZSTD_isError(size_t code) +{ + return code > (size_t)-ZSTD_error_maxCode; +} +/** + * ZSTD_getErrorCode() - translates an error function result to a ZSTD_ErrorCode + * @functionResult: The result of a function for which ZSTD_isError() is true. + * + * Return: The ZSTD_ErrorCode corresponding to the functionResult or 0 + * if the functionResult isn't an error. + */ +static __attribute__((unused)) ZSTD_ErrorCode ZSTD_getErrorCode( + size_t functionResult) +{ + if (!ZSTD_isError(functionResult)) + return (ZSTD_ErrorCode)0; + return (ZSTD_ErrorCode)(0 - functionResult); +} + +/** + * enum ZSTD_strategy - zstd compression search strategy + * + * From faster to stronger. + */ +typedef enum { + ZSTD_fast, + ZSTD_dfast, + ZSTD_greedy, + ZSTD_lazy, + ZSTD_lazy2, + ZSTD_btlazy2, + ZSTD_btopt, + ZSTD_btopt2 +} ZSTD_strategy; + +/** + * struct ZSTD_compressionParameters - zstd compression parameters + * @windowLog: Log of the largest match distance. Larger means more + * compression, and more memory needed during decompression. + * @chainLog: Fully searched segment. Larger means more compression, slower, + * and more memory (useless for fast). + * @hashLog: Dispatch table. Larger means more compression, + * slower, and more memory. + * @searchLog: Number of searches. Larger means more compression and slower. + * @searchLength: Match length searched. Larger means faster decompression, + * sometimes less compression. + * @targetLength: Acceptable match size for optimal parser (only). Larger means + * more compression, and slower. + * @strategy: The zstd compression strategy. + */ +typedef struct { + unsigned int windowLog; + unsigned int chainLog; + unsigned int hashLog; + unsigned int searchLog; + unsigned int searchLength; + unsigned int targetLength; + ZSTD_strategy strategy; +} ZSTD_compressionParameters; + +/** + * struct ZSTD_frameParameters - zstd frame parameters + * @contentSizeFlag: Controls whether content size will be present in the frame + * header (when known). + * @checksumFlag: Controls whether a 32-bit checksum is generated at the end + * of the frame for error detection. + * @noDictIDFlag: Controls whether dictID will be saved into the frame header + * when using dictionary compression. + * + * The default value is all fields set to 0. + */ +typedef struct { + unsigned int contentSizeFlag; + unsigned int checksumFlag; + unsigned int noDictIDFlag; +} ZSTD_frameParameters; + +/** + * struct ZSTD_parameters - zstd parameters + * @cParams: The compression parameters. + * @fParams: The frame parameters. + */ +typedef struct { + ZSTD_compressionParameters cParams; + ZSTD_frameParameters fParams; +} ZSTD_parameters; + +/** + * ZSTD_getCParams() - returns ZSTD_compressionParameters for selected level + * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). + * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. + * @dictSize: The dictionary size or 0 if a dictionary isn't being used. + * + * Return: The selected ZSTD_compressionParameters. + */ +ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, + unsigned long long estimatedSrcSize, size_t dictSize); + +/** + * ZSTD_getParams() - returns ZSTD_parameters for selected level + * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). + * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. + * @dictSize: The dictionary size or 0 if a dictionary isn't being used. + * + * The same as ZSTD_getCParams() except also selects the default frame + * parameters (all zero). + * + * Return: The selected ZSTD_parameters. + */ +ZSTD_parameters ZSTD_getParams(int compressionLevel, + unsigned long long estimatedSrcSize, size_t dictSize); + +/*-************************************* + * Explicit memory management + **************************************/ + +/** + * ZSTD_CCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_CCtx + * @cParams: The compression parameters to be used for compression. + * + * If multiple compression parameters might be used, the caller must call + * ZSTD_CCtxWorkspaceBound() for each set of parameters and use the maximum + * size. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCCtx(). + */ +size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CCtx - the zstd compression context + * + * When compressing many times it is recommended to allocate a context just once + * and reuse it for each successive compression operation. + */ +typedef struct ZSTD_CCtx_s ZSTD_CCtx; +/** + * ZSTD_initCCtx() - initialize a zstd compression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Use ZSTD_CCtxWorkspaceBound() to + * determine how large the workspace must be. + * + * Return: A compression context emplaced into workspace. + */ +ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize); + +/** + * ZSTD_compressCCtx() - compress src into dst + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, ZSTD_parameters params); + +/** + * ZSTD_DCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_DCtx + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDCtx(). + */ +size_t ZSTD_DCtxWorkspaceBound(void); + +/** + * struct ZSTD_DCtx - the zstd decompression context + * + * When decompressing many times it is recommended to allocate a context just + * once and reuse it for each successive decompression operation. + */ +typedef struct ZSTD_DCtx_s ZSTD_DCtx; +/** + * ZSTD_initDCtx() - initialize a zstd decompression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Use ZSTD_DCtxWorkspaceBound() to + * determine how large the workspace must be. + * + * Return: A decompression context emplaced into workspace. + */ +ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize); + +/** + * ZSTD_decompressDCtx() - decompress zstd compressed src into dst + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompressDCtx(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); + +/*-************************ + * Simple dictionary API + **************************/ + +/** + * ZSTD_compress_usingDict() - compress src into dst using a dictionary + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @dict: The dictionary to use for compression. + * @dictSize: The size of the dictionary. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Compression using a predefined dictionary. The same dictionary must be used + * during decompression. + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const void *dict, size_t dictSize, + ZSTD_parameters params); + +/** + * ZSTD_decompress_usingDict() - decompress src into dst using a dictionary + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * @dict: The dictionary to use for decompression. The same dictionary + * must've been used to compress the data. + * @dictSize: The size of the dictionary. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompress_usingDict(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const void *dict, size_t dictSize); + +/*-************************** + * Fast dictionary API + ***************************/ + +/** + * ZSTD_CDictWorkspaceBound() - memory needed to initialize a ZSTD_CDict + * @cParams: The compression parameters to be used for compression. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCDict(). + */ +size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CDict - a digested dictionary to be used for compression + */ +typedef struct ZSTD_CDict_s ZSTD_CDict; + +/** + * ZSTD_initCDict() - initialize a digested dictionary for compression + * @dictBuffer: The dictionary to digest. The buffer is referenced by the + * ZSTD_CDict so it must outlive the returned ZSTD_CDict. + * @dictSize: The size of the dictionary. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * @workspace: The workspace. It must outlive the returned ZSTD_CDict. + * @workspaceSize: The workspace size. Must be at least + * ZSTD_CDictWorkspaceBound(params.cParams). + * + * When compressing multiple messages / blocks with the same dictionary it is + * recommended to load it just once. The ZSTD_CDict merely references the + * dictBuffer, so it must outlive the returned ZSTD_CDict. + * + * Return: The digested dictionary emplaced into workspace. + */ +ZSTD_CDict *ZSTD_initCDict(const void *dictBuffer, size_t dictSize, + ZSTD_parameters params, void *workspace, size_t workspaceSize); + +/** + * ZSTD_compress_usingCDict() - compress src into dst using a ZSTD_CDict + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(cParams) where + * cParams are the compression parameters used to initialize the + * cdict. + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @cdict: The digested dictionary to use for compression. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Compression using a digested dictionary. The same dictionary must be used + * during decompression. + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const ZSTD_CDict *cdict); + + +/** + * ZSTD_DDictWorkspaceBound() - memory needed to initialize a ZSTD_DDict + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDDict(). + */ +size_t ZSTD_DDictWorkspaceBound(void); + +/** + * struct ZSTD_DDict - a digested dictionary to be used for decompression + */ +typedef struct ZSTD_DDict_s ZSTD_DDict; + +/** + * ZSTD_initDDict() - initialize a digested dictionary for decompression + * @dictBuffer: The dictionary to digest. The buffer is referenced by the + * ZSTD_DDict so it must outlive the returned ZSTD_DDict. + * @dictSize: The size of the dictionary. + * @workspace: The workspace. It must outlive the returned ZSTD_DDict. + * @workspaceSize: The workspace size. Must be at least + * ZSTD_DDictWorkspaceBound(). + * + * When decompressing multiple messages / blocks with the same dictionary it is + * recommended to load it just once. The ZSTD_DDict merely references the + * dictBuffer, so it must outlive the returned ZSTD_DDict. + * + * Return: The digested dictionary emplaced into workspace. + */ +ZSTD_DDict *ZSTD_initDDict(const void *dictBuffer, size_t dictSize, + void *workspace, size_t workspaceSize); + +/** + * ZSTD_decompress_usingDDict() - decompress src into dst using a ZSTD_DDict + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * @ddict: The digested dictionary to use for decompression. The same + * dictionary must've been used to compress the data. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, + size_t dstCapacity, const void *src, size_t srcSize, + const ZSTD_DDict *ddict); + + +/*-************************** + * Streaming + ***************************/ + +/** + * struct ZSTD_inBuffer - input buffer for streaming + * @src: Start of the input buffer. + * @size: Size of the input buffer. + * @pos: Position where reading stopped. Will be updated. + * Necessarily 0 <= pos <= size. + */ +typedef struct ZSTD_inBuffer_s { + const void *src; + size_t size; + size_t pos; +} ZSTD_inBuffer; + +/** + * struct ZSTD_outBuffer - output buffer for streaming + * @dst: Start of the output buffer. + * @size: Size of the output buffer. + * @pos: Position where writing stopped. Will be updated. + * Necessarily 0 <= pos <= size. + */ +typedef struct ZSTD_outBuffer_s { + void *dst; + size_t size; + size_t pos; +} ZSTD_outBuffer; + + + +/*-***************************************************************************** + * Streaming compression - HowTo + * + * A ZSTD_CStream object is required to track streaming operation. + * Use ZSTD_initCStream() to initialize a ZSTD_CStream object. + * ZSTD_CStream objects can be reused multiple times on consecutive compression + * operations. It is recommended to re-use ZSTD_CStream in situations where many + * streaming operations will be achieved consecutively. Use one separate + * ZSTD_CStream per thread for parallel execution. + * + * Use ZSTD_compressStream() repetitively to consume input stream. + * The function will automatically update both `pos` fields. + * Note that it may not consume the entire input, in which case `pos < size`, + * and it's up to the caller to present again remaining data. + * It returns a hint for the preferred number of bytes to use as an input for + * the next function call. + * + * At any moment, it's possible to flush whatever data remains within internal + * buffer, using ZSTD_flushStream(). `output->pos` will be updated. There might + * still be some content left within the internal buffer if `output->size` is + * too small. It returns the number of bytes left in the internal buffer and + * must be called until it returns 0. + * + * ZSTD_endStream() instructs to finish a frame. It will perform a flush and + * write frame epilogue. The epilogue is required for decoders to consider a + * frame completed. Similar to ZSTD_flushStream(), it may not be able to flush + * the full content if `output->size` is too small. In which case, call again + * ZSTD_endStream() to complete the flush. It returns the number of bytes left + * in the internal buffer and must be called until it returns 0. + ******************************************************************************/ + +/** + * ZSTD_CStreamWorkspaceBound() - memory needed to initialize a ZSTD_CStream + * @cParams: The compression parameters to be used for compression. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCStream() and ZSTD_initCStream_usingCDict(). + */ +size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CStream - the zstd streaming compression context + */ +typedef struct ZSTD_CStream_s ZSTD_CStream; + +/*===== ZSTD_CStream management functions =====*/ +/** + * ZSTD_initCStream() - initialize a zstd streaming compression context + * @params: The zstd compression parameters. + * @pledgedSrcSize: If params.fParams.contentSizeFlag == 1 then the caller must + * pass the source size (zero means empty source). Otherwise, + * the caller may optionally pass the source size, or zero if + * unknown. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_CStreamWorkspaceBound(params.cParams) to determine + * how large the workspace must be. + * + * Return: The zstd streaming compression context. + */ +ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, + unsigned long long pledgedSrcSize, void *workspace, + size_t workspaceSize); + +/** + * ZSTD_initCStream_usingCDict() - initialize a streaming compression context + * @cdict: The digested dictionary to use for compression. + * @pledgedSrcSize: Optionally the source size, or zero if unknown. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Call ZSTD_CStreamWorkspaceBound() + * with the cParams used to initialize the cdict to determine + * how large the workspace must be. + * + * Return: The zstd streaming compression context. + */ +ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, + unsigned long long pledgedSrcSize, void *workspace, + size_t workspaceSize); + +/*===== Streaming compression functions =====*/ +/** + * ZSTD_resetCStream() - reset the context using parameters from creation + * @zcs: The zstd streaming compression context to reset. + * @pledgedSrcSize: Optionally the source size, or zero if unknown. + * + * Resets the context using the parameters from creation. Skips dictionary + * loading, since it can be reused. If `pledgedSrcSize` is non-zero the frame + * content size is always written into the frame header. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize); +/** + * ZSTD_compressStream() - streaming compress some of input into output + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * @input: Source buffer. `input->pos` is updated to indicate how much data was + * read. Note that it may not consume the entire input, in which case + * `input->pos < input->size`, and it's up to the caller to present + * remaining data again. + * + * The `input` and `output` buffers may be any size. Guaranteed to make some + * forward progress if `input` and `output` are not empty. + * + * Return: A hint for the number of bytes to use as the input for the next + * function call or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, + ZSTD_inBuffer *input); +/** + * ZSTD_flushStream() - flush internal buffers into output + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * + * ZSTD_flushStream() must be called until it returns 0, meaning all the data + * has been flushed. Since ZSTD_flushStream() causes a block to be ended, + * calling it too often will degrade the compression ratio. + * + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); +/** + * ZSTD_endStream() - flush internal buffers into output and end the frame + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * + * ZSTD_endStream() must be called until it returns 0, meaning all the data has + * been flushed and the frame epilogue has been written. + * + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); + +/** + * ZSTD_CStreamInSize() - recommended size for the input buffer + * + * Return: The recommended size for the input buffer. + */ +size_t ZSTD_CStreamInSize(void); +/** + * ZSTD_CStreamOutSize() - recommended size for the output buffer + * + * When the output buffer is at least this large, it is guaranteed to be large + * enough to flush at least one complete compressed block. + * + * Return: The recommended size for the output buffer. + */ +size_t ZSTD_CStreamOutSize(void); + + + +/*-***************************************************************************** + * Streaming decompression - HowTo + * + * A ZSTD_DStream object is required to track streaming operations. + * Use ZSTD_initDStream() to initialize a ZSTD_DStream object. + * ZSTD_DStream objects can be re-used multiple times. + * + * Use ZSTD_decompressStream() repetitively to consume your input. + * The function will update both `pos` fields. + * If `input->pos < input->size`, some input has not been consumed. + * It's up to the caller to present again remaining data. + * If `output->pos < output->size`, decoder has flushed everything it could. + * Returns 0 iff a frame is completely decoded and fully flushed. + * Otherwise it returns a suggested next input size that will never load more + * than the current frame. + ******************************************************************************/ + +/** + * ZSTD_DStreamWorkspaceBound() - memory needed to initialize a ZSTD_DStream + * @maxWindowSize: The maximum window size allowed for compressed frames. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDStream() and ZSTD_initDStream_usingDDict(). + */ +size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize); + +/** + * struct ZSTD_DStream - the zstd streaming decompression context + */ +typedef struct ZSTD_DStream_s ZSTD_DStream; +/*===== ZSTD_DStream management functions =====*/ +/** + * ZSTD_initDStream() - initialize a zstd streaming decompression context + * @maxWindowSize: The maximum window size allowed for compressed frames. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine + * how large the workspace must be. + * + * Return: The zstd streaming decompression context. + */ +ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, + size_t workspaceSize); +/** + * ZSTD_initDStream_usingDDict() - initialize streaming decompression context + * @maxWindowSize: The maximum window size allowed for compressed frames. + * @ddict: The digested dictionary to use for decompression. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine + * how large the workspace must be. + * + * Return: The zstd streaming decompression context. + */ +ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, + const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize); + +/*===== Streaming decompression functions =====*/ +/** + * ZSTD_resetDStream() - reset the context using parameters from creation + * @zds: The zstd streaming decompression context to reset. + * + * Resets the context using the parameters from creation. Skips dictionary + * loading, since it can be reused. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_resetDStream(ZSTD_DStream *zds); +/** + * ZSTD_decompressStream() - streaming decompress some of input into output + * @zds: The zstd streaming decompression context. + * @output: Destination buffer. `output.pos` is updated to indicate how much + * decompressed data was written. + * @input: Source buffer. `input.pos` is updated to indicate how much data was + * read. Note that it may not consume the entire input, in which case + * `input.pos < input.size`, and it's up to the caller to present + * remaining data again. + * + * The `input` and `output` buffers may be any size. Guaranteed to make some + * forward progress if `input` and `output` are not empty. + * ZSTD_decompressStream() will not consume the last byte of the frame until + * the entire frame is flushed. + * + * Return: Returns 0 iff a frame is completely decoded and fully flushed. + * Otherwise returns a hint for the number of bytes to use as the input + * for the next function call or an error, which can be checked using + * ZSTD_isError(). The size hint will never load more than the frame. + */ +size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, + ZSTD_inBuffer *input); + +/** + * ZSTD_DStreamInSize() - recommended size for the input buffer + * + * Return: The recommended size for the input buffer. + */ +size_t ZSTD_DStreamInSize(void); +/** + * ZSTD_DStreamOutSize() - recommended size for the output buffer + * + * When the output buffer is at least this large, it is guaranteed to be large + * enough to flush at least one complete decompressed block. + * + * Return: The recommended size for the output buffer. + */ +size_t ZSTD_DStreamOutSize(void); + + +/* --- Constants ---*/ +#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ +#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U + +#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + +#define ZSTD_WINDOWLOG_MAX_32 27 +#define ZSTD_WINDOWLOG_MAX_64 27 +#define ZSTD_WINDOWLOG_MAX \ + ((unsigned int)(sizeof(size_t) == 4 \ + ? ZSTD_WINDOWLOG_MAX_32 \ + : ZSTD_WINDOWLOG_MAX_64)) +#define ZSTD_WINDOWLOG_MIN 10 +#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX +#define ZSTD_HASHLOG_MIN 6 +#define ZSTD_CHAINLOG_MAX (ZSTD_WINDOWLOG_MAX+1) +#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN +#define ZSTD_HASHLOG3_MAX 17 +#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) +#define ZSTD_SEARCHLOG_MIN 1 +/* only for ZSTD_fast, other strategies are limited to 6 */ +#define ZSTD_SEARCHLENGTH_MAX 7 +/* only for ZSTD_btopt, other strategies are limited to 4 */ +#define ZSTD_SEARCHLENGTH_MIN 3 +#define ZSTD_TARGETLENGTH_MIN 4 +#define ZSTD_TARGETLENGTH_MAX 999 + +/* for static allocation */ +#define ZSTD_FRAMEHEADERSIZE_MAX 18 +#define ZSTD_FRAMEHEADERSIZE_MIN 6 +#define ZSTD_frameHeaderSize_prefix 5 +#define ZSTD_frameHeaderSize_min ZSTD_FRAMEHEADERSIZE_MIN +#define ZSTD_frameHeaderSize_max ZSTD_FRAMEHEADERSIZE_MAX +/* magic number + skippable frame length */ +#define ZSTD_skippableHeaderSize 8 + + +/*-************************************* + * Compressed size functions + **************************************/ + +/** + * ZSTD_findFrameCompressedSize() - returns the size of a compressed frame + * @src: Source buffer. It should point to the start of a zstd encoded frame + * or a skippable frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * size of the frame. + * + * Return: The compressed size of the frame pointed to by `src` or an error, + * which can be check with ZSTD_isError(). + * Suitable to pass to ZSTD_decompress() or similar functions. + */ +size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize); + +/*-************************************* + * Decompressed size functions + **************************************/ +/** + * ZSTD_getFrameContentSize() - returns the content size in a zstd frame header + * @src: It should point to the start of a zstd encoded frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * frame header. `ZSTD_frameHeaderSize_max` is always large enough. + * + * Return: The frame content size stored in the frame header if known. + * `ZSTD_CONTENTSIZE_UNKNOWN` if the content size isn't stored in the + * frame header. `ZSTD_CONTENTSIZE_ERROR` on invalid input. + */ +unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); + +/** + * ZSTD_findDecompressedSize() - returns decompressed size of a series of frames + * @src: It should point to the start of a series of zstd encoded and/or + * skippable frames. + * @srcSize: The exact size of the series of frames. + * + * If any zstd encoded frame in the series doesn't have the frame content size + * set, `ZSTD_CONTENTSIZE_UNKNOWN` is returned. But frame content size is always + * set when using ZSTD_compress(). The decompressed size can be very large. + * If the source is untrusted, the decompressed size could be wrong or + * intentionally modified. Always ensure the result fits within the + * application's authorized limits. ZSTD_findDecompressedSize() handles multiple + * frames, and so it must traverse the input to read each frame header. This is + * efficient as most of the data is skipped, however it does mean that all frame + * data must be present and valid. + * + * Return: Decompressed size of all the data contained in the frames if known. + * `ZSTD_CONTENTSIZE_UNKNOWN` if the decompressed size is unknown. + * `ZSTD_CONTENTSIZE_ERROR` if an error occurred. + */ +unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize); + +/*-************************************* + * Advanced compression functions + **************************************/ +/** + * ZSTD_checkCParams() - ensure parameter values remain within authorized range + * @cParams: The zstd compression parameters. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams); + +/** + * ZSTD_adjustCParams() - optimize parameters for a given srcSize and dictSize + * @srcSize: Optionally the estimated source size, or zero if unknown. + * @dictSize: Optionally the estimated dictionary size, or zero if unknown. + * + * Return: The optimized parameters. + */ +ZSTD_compressionParameters ZSTD_adjustCParams( + ZSTD_compressionParameters cParams, unsigned long long srcSize, + size_t dictSize); + +/*--- Advanced decompression functions ---*/ + +/** + * ZSTD_isFrame() - returns true iff the buffer starts with a valid frame + * @buffer: The source buffer to check. + * @size: The size of the source buffer, must be at least 4 bytes. + * + * Return: True iff the buffer starts with a zstd or skippable frame identifier. + */ +unsigned int ZSTD_isFrame(const void *buffer, size_t size); + +/** + * ZSTD_getDictID_fromDict() - returns the dictionary id stored in a dictionary + * @dict: The dictionary buffer. + * @dictSize: The size of the dictionary buffer. + * + * Return: The dictionary id stored within the dictionary or 0 if the + * dictionary is not a zstd dictionary. If it returns 0 the + * dictionary can still be loaded as a content-only dictionary. + */ +unsigned int ZSTD_getDictID_fromDict(const void *dict, size_t dictSize); + +/** + * ZSTD_getDictID_fromDDict() - returns the dictionary id stored in a ZSTD_DDict + * @ddict: The ddict to find the id of. + * + * Return: The dictionary id stored within `ddict` or 0 if the dictionary is not + * a zstd dictionary. If it returns 0 `ddict` will be loaded as a + * content-only dictionary. + */ +unsigned int ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict); + +/** + * ZSTD_getDictID_fromFrame() - returns the dictionary id stored in a zstd frame + * @src: Source buffer. It must be a zstd encoded frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * frame header. `ZSTD_frameHeaderSize_max` is always large enough. + * + * Return: The dictionary id required to decompress the frame stored within + * `src` or 0 if the dictionary id could not be decoded. It can return + * 0 if the frame does not require a dictionary, the dictionary id + * wasn't stored in the frame, `src` is not a zstd frame, or `srcSize` + * is too small. + */ +unsigned int ZSTD_getDictID_fromFrame(const void *src, size_t srcSize); + +/** + * struct ZSTD_frameParams - zstd frame parameters stored in the frame header + * @frameContentSize: The frame content size, or 0 if not present. + * @windowSize: The window size, or 0 if the frame is a skippable frame. + * @dictID: The dictionary id, or 0 if not present. + * @checksumFlag: Whether a checksum was used. + */ +typedef struct { + unsigned long long frameContentSize; + unsigned int windowSize; + unsigned int dictID; + unsigned int checksumFlag; +} ZSTD_frameParams; + +/** + * ZSTD_getFrameParams() - extracts parameters from a zstd or skippable frame + * @fparamsPtr: On success the frame parameters are written here. + * @src: The source buffer. It must point to a zstd or skippable frame. + * @srcSize: The size of the source buffer. `ZSTD_frameHeaderSize_max` is + * always large enough to succeed. + * + * Return: 0 on success. If more data is required it returns how many bytes + * must be provided to make forward progress. Otherwise it returns + * an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, + size_t srcSize); + +/*-***************************************************************************** + * Buffer-less and synchronous inner streaming functions + * + * This is an advanced API, giving full control over buffer management, for + * users which need direct control over memory. + * But it's also a complex one, with many restrictions (documented below). + * Prefer using normal streaming API for an easier experience + ******************************************************************************/ + +/*-***************************************************************************** + * Buffer-less streaming compression (synchronous mode) + * + * A ZSTD_CCtx object is required to track streaming operations. + * Use ZSTD_initCCtx() to initialize a context. + * ZSTD_CCtx object can be re-used multiple times within successive compression + * operations. + * + * Start by initializing a context. + * Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary + * compression, + * or ZSTD_compressBegin_advanced(), for finer parameter control. + * It's also possible to duplicate a reference context which has already been + * initialized, using ZSTD_copyCCtx() + * + * Then, consume your input using ZSTD_compressContinue(). + * There are some important considerations to keep in mind when using this + * advanced function : + * - ZSTD_compressContinue() has no internal buffer. It uses externally provided + * buffer only. + * - Interface is synchronous : input is consumed entirely and produce 1+ + * (or more) compressed blocks. + * - Caller must ensure there is enough space in `dst` to store compressed data + * under worst case scenario. Worst case evaluation is provided by + * ZSTD_compressBound(). + * ZSTD_compressContinue() doesn't guarantee recover after a failed + * compression. + * - ZSTD_compressContinue() presumes prior input ***is still accessible and + * unmodified*** (up to maximum distance size, see WindowLog). + * It remembers all previous contiguous blocks, plus one separated memory + * segment (which can itself consists of multiple contiguous blocks) + * - ZSTD_compressContinue() detects that prior input has been overwritten when + * `src` buffer overlaps. In which case, it will "discard" the relevant memory + * section from its history. + * + * Finish a frame with ZSTD_compressEnd(), which will write the last block(s) + * and optional checksum. It's possible to use srcSize==0, in which case, it + * will write a final empty block to end the frame. Without last block mark, + * frames will be considered unfinished (corrupted) by decoders. + * + * `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new + * frame. + ******************************************************************************/ + +/*===== Buffer-less streaming compression functions =====*/ +size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel); +size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, + size_t dictSize, int compressionLevel); +size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, + size_t dictSize, ZSTD_parameters params, + unsigned long long pledgedSrcSize); +size_t ZSTD_copyCCtx(ZSTD_CCtx *cctx, const ZSTD_CCtx *preparedCCtx, + unsigned long long pledgedSrcSize); +size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, + unsigned long long pledgedSrcSize); +size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); + + + +/*-***************************************************************************** + * Buffer-less streaming decompression (synchronous mode) + * + * A ZSTD_DCtx object is required to track streaming operations. + * Use ZSTD_initDCtx() to initialize a context. + * A ZSTD_DCtx object can be re-used multiple times. + * + * First typical operation is to retrieve frame parameters, using + * ZSTD_getFrameParams(). It fills a ZSTD_frameParams structure which provide + * important information to correctly decode the frame, such as the minimum + * rolling buffer size to allocate to decompress data (`windowSize`), and the + * dictionary ID used. + * Note: content size is optional, it may not be present. 0 means unknown. + * Note that these values could be wrong, either because of data malformation, + * or because an attacker is spoofing deliberate false information. As a + * consequence, check that values remain within valid application range, + * especially `windowSize`, before allocation. Each application can set its own + * limit, depending on local restrictions. For extended interoperability, it is + * recommended to support at least 8 MB. + * Frame parameters are extracted from the beginning of the compressed frame. + * Data fragment must be large enough to ensure successful decoding, typically + * `ZSTD_frameHeaderSize_max` bytes. + * Result: 0: successful decoding, the `ZSTD_frameParams` structure is filled. + * >0: `srcSize` is too small, provide at least this many bytes. + * errorCode, which can be tested using ZSTD_isError(). + * + * Start decompression, with ZSTD_decompressBegin() or + * ZSTD_decompressBegin_usingDict(). Alternatively, you can copy a prepared + * context, using ZSTD_copyDCtx(). + * + * Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() + * alternatively. + * ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' + * to ZSTD_decompressContinue(). + * ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will + * fail. + * + * The result of ZSTD_decompressContinue() is the number of bytes regenerated + * within 'dst' (necessarily <= dstCapacity). It can be zero, which is not an + * error; it just means ZSTD_decompressContinue() has decoded some metadata + * item. It can also be an error code, which can be tested with ZSTD_isError(). + * + * ZSTD_decompressContinue() needs previous data blocks during decompression, up + * to `windowSize`. They should preferably be located contiguously, prior to + * current block. Alternatively, a round buffer of sufficient size is also + * possible. Sufficient size is determined by frame parameters. + * ZSTD_decompressContinue() is very sensitive to contiguity, if 2 blocks don't + * follow each other, make sure that either the compressor breaks contiguity at + * the same place, or that previous contiguous segment is large enough to + * properly handle maximum back-reference. + * + * A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. + * Context can then be reset to start a new decompression. + * + * Note: it's possible to know if next input to present is a header or a block, + * using ZSTD_nextInputType(). This information is not required to properly + * decode a frame. + * + * == Special case: skippable frames == + * + * Skippable frames allow integration of user-defined data into a flow of + * concatenated frames. Skippable frames will be ignored (skipped) by a + * decompressor. The format of skippable frames is as follows: + * a) Skippable frame ID - 4 Bytes, Little endian format, any value from + * 0x184D2A50 to 0x184D2A5F + * b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits + * c) Frame Content - any content (User Data) of length equal to Frame Size + * For skippable frames ZSTD_decompressContinue() always returns 0. + * For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 + * what means that a frame is skippable. + * Note: If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might + * actually be a zstd encoded frame with no content. For purposes of + * decompression, it is valid in both cases to skip the frame using + * ZSTD_findFrameCompressedSize() to find its size in bytes. + * It also returns frame size as fparamsPtr->frameContentSize. + ******************************************************************************/ + +/*===== Buffer-less streaming decompression functions =====*/ +size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx); +size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, + size_t dictSize); +void ZSTD_copyDCtx(ZSTD_DCtx *dctx, const ZSTD_DCtx *preparedDCtx); +size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx); +size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +typedef enum { + ZSTDnit_frameHeader, + ZSTDnit_blockHeader, + ZSTDnit_block, + ZSTDnit_lastBlock, + ZSTDnit_checksum, + ZSTDnit_skippableFrame +} ZSTD_nextInputType_e; +ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx); + +/*-***************************************************************************** + * Block functions + * + * Block functions produce and decode raw zstd blocks, without frame metadata. + * Frame metadata cost is typically ~18 bytes, which can be non-negligible for + * very small blocks (< 100 bytes). User will have to take in charge required + * information to regenerate data, such as compressed and content sizes. + * + * A few rules to respect: + * - Compressing and decompressing require a context structure + * + Use ZSTD_initCCtx() and ZSTD_initDCtx() + * - It is necessary to init context before starting + * + compression : ZSTD_compressBegin() + * + decompression : ZSTD_decompressBegin() + * + variants _usingDict() are also allowed + * + copyCCtx() and copyDCtx() work too + * - Block size is limited, it must be <= ZSTD_getBlockSizeMax() + * + If you need to compress more, cut data into multiple blocks + * + Consider using the regular ZSTD_compress() instead, as frame metadata + * costs become negligible when source size is large. + * - When a block is considered not compressible enough, ZSTD_compressBlock() + * result will be zero. In which case, nothing is produced into `dst`. + * + User must test for such outcome and deal directly with uncompressed data + * + ZSTD_decompressBlock() doesn't accept uncompressed data as input!!! + * + In case of multiple successive blocks, decoder must be informed of + * uncompressed block existence to follow proper history. Use + * ZSTD_insertBlock() in such a case. + ******************************************************************************/ + +/* Define for static allocation */ +#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) +/*===== Raw zstd block functions =====*/ +size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx); +size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, + size_t blockSize); + +#endif /* ZSTD_H */ -- cgit v1.2.3 From e0c1b49f5b674cca7b10549c53b3791d0bbc90a8 Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Fri, 11 Sep 2020 16:37:08 -0700 Subject: lib: zstd: Upgrade to latest upstream zstd version 1.4.10 Upgrade to the latest upstream zstd version 1.4.10. This patch is 100% generated from upstream zstd commit 20821a46f412 [0]. This patch is very large because it is transitioning from the custom kernel zstd to using upstream directly. The new zstd follows upstreams file structure which is different. Future update patches will be much smaller because they will only contain the changes from one upstream zstd release. As an aid for review I've created a commit [1] that shows the diff between upstream zstd as-is (which doesn't compile), and the zstd code imported in this patch. The verion of zstd in this patch is generated from upstream with changes applied by automation to replace upstreams libc dependencies, remove unnecessary portability macros, replace `/**` comments with `/*` comments, and use the kernel's xxhash instead of bundling it. The benefits of this patch are as follows: 1. Using upstream directly with automated script to generate kernel code. This allows us to update the kernel every upstream release, so the kernel gets the latest bug fixes and performance improvements, and doesn't get 3 years out of date again. The automation and the translated code are tested every upstream commit to ensure it continues to work. 2. Upgrades from a custom zstd based on 1.3.1 to 1.4.10, getting 3 years of performance improvements and bug fixes. On x86_64 I've measured 15% faster BtrFS and SquashFS decompression+read speeds, 35% faster kernel decompression, and 30% faster ZRAM decompression+read speeds. 3. Zstd-1.4.10 supports negative compression levels, which allow zstd to match or subsume lzo's performance. 4. Maintains the same kernel-specific wrapper API, so no callers have to be modified with zstd version updates. One concern that was brought up was stack usage. Upstream zstd had already removed most of its heavy stack usage functions, but I just removed the last functions that allocate arrays on the stack. I've measured the high water mark for both compression and decompression before and after this patch. Decompression is approximately neutral, using about 1.2KB of stack space. Compression levels up to 3 regressed from 1.4KB -> 1.6KB, and higher compression levels regressed from 1.5KB -> 2KB. We've added unit tests upstream to prevent further regression. I believe that this is a reasonable increase, and if it does end up causing problems, this commit can be cleanly reverted, because it only touches zstd. I chose the bulk update instead of replaying upstream commits because there have been ~3500 upstream commits since the 1.3.1 release, zstd wasn't ready to be used in the kernel as-is before a month ago, and not all upstream zstd commits build. The bulk update preserves bisectablity because bugs can be bisected to the zstd version update. At that point the update can be reverted, and we can work with upstream to find and fix the bug. Note that upstream zstd release 1.4.10 doesn't exist yet. I have cut a staging branch at 20821a46f412 [0] and will apply any changes requested to the staging branch. Once we're ready to merge this update I will cut a zstd release at the commit we merge, so we have a known zstd release in the kernel. The implementation of the kernel API is contained in zstd_compress_module.c and zstd_decompress_module.c. [0] https://github.com/facebook/zstd/commit/20821a46f4122f9abd7c7b245d28162dde8129c9 [1] https://github.com/terrelln/linux/commit/e0fa481d0e3df26918da0a13749740a1f6777574 Signed-off-by: Nick Terrell Tested By: Paul Jones Tested-by: Oleksandr Natalenko Tested-by: Sedat Dilek # LLVM/Clang v13.0.0 on x86-64 Tested-by: Jean-Denis Girard --- include/linux/zstd.h | 13 +- include/linux/zstd_errors.h | 77 + include/linux/zstd_lib.h | 3367 +++++++++++++++++++++++++++++-------------- 3 files changed, 2408 insertions(+), 1049 deletions(-) create mode 100644 include/linux/zstd_errors.h (limited to 'include/linux') diff --git a/include/linux/zstd.h b/include/linux/zstd.h index 9fbc7729b0a0..113408eef6ec 100644 --- a/include/linux/zstd.h +++ b/include/linux/zstd.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ /* * Copyright (c) Yann Collet, Facebook, Inc. * All rights reserved. @@ -22,6 +22,7 @@ /* ====== Dependency ====== */ #include +#include #include /* ====== Helper Functions ====== */ @@ -417,12 +418,18 @@ size_t zstd_find_frame_compressed_size(const void *src, size_t src_size); /** * struct zstd_frame_params - zstd frame parameters stored in the frame header - * @frameContentSize: The frame content size, or 0 if not present. + * @frameContentSize: The frame content size, or ZSTD_CONTENTSIZE_UNKNOWN if not + * present. * @windowSize: The window size, or 0 if the frame is a skippable frame. + * @blockSizeMax: The maximum block size. + * @frameType: The frame type (zstd or skippable) + * @headerSize: The size of the frame header. * @dictID: The dictionary id, or 0 if not present. * @checksumFlag: Whether a checksum was used. + * + * See zstd_lib.h. */ -typedef ZSTD_frameParams zstd_frame_header; +typedef ZSTD_frameHeader zstd_frame_header; /** * zstd_get_frame_header() - extracts parameters from a zstd or skippable frame diff --git a/include/linux/zstd_errors.h b/include/linux/zstd_errors.h new file mode 100644 index 000000000000..58b6dd45a969 --- /dev/null +++ b/include/linux/zstd_errors.h @@ -0,0 +1,77 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_ERRORS_H_398273423 +#define ZSTD_ERRORS_H_398273423 + + +/*===== dependency =====*/ +#include /* size_t */ + + +/* ===== ZSTDERRORLIB_API : control library symbols visibility ===== */ +#define ZSTDERRORLIB_VISIBILITY +#define ZSTDERRORLIB_API ZSTDERRORLIB_VISIBILITY + +/*-********************************************* + * Error codes list + *-********************************************* + * Error codes _values_ are pinned down since v1.3.1 only. + * Therefore, don't rely on values if you may link to any version < v1.3.1. + * + * Only values < 100 are considered stable. + * + * note 1 : this API shall be used with static linking only. + * dynamic linking is not yet officially supported. + * note 2 : Prefer relying on the enum than on its value whenever possible + * This is the only supported way to use the error list < v1.3.1 + * note 3 : ZSTD_isError() is always correct, whatever the library version. + **********************************************/ +typedef enum { + ZSTD_error_no_error = 0, + ZSTD_error_GENERIC = 1, + ZSTD_error_prefix_unknown = 10, + ZSTD_error_version_unsupported = 12, + ZSTD_error_frameParameter_unsupported = 14, + ZSTD_error_frameParameter_windowTooLarge = 16, + ZSTD_error_corruption_detected = 20, + ZSTD_error_checksum_wrong = 22, + ZSTD_error_dictionary_corrupted = 30, + ZSTD_error_dictionary_wrong = 32, + ZSTD_error_dictionaryCreation_failed = 34, + ZSTD_error_parameter_unsupported = 40, + ZSTD_error_parameter_outOfBound = 42, + ZSTD_error_tableLog_tooLarge = 44, + ZSTD_error_maxSymbolValue_tooLarge = 46, + ZSTD_error_maxSymbolValue_tooSmall = 48, + ZSTD_error_stage_wrong = 60, + ZSTD_error_init_missing = 62, + ZSTD_error_memory_allocation = 64, + ZSTD_error_workSpace_tooSmall= 66, + ZSTD_error_dstSize_tooSmall = 70, + ZSTD_error_srcSize_wrong = 72, + ZSTD_error_dstBuffer_null = 74, + /* following error codes are __NOT STABLE__, they can be removed or changed in future versions */ + ZSTD_error_frameIndex_tooLarge = 100, + ZSTD_error_seekableIO = 102, + ZSTD_error_dstBuffer_wrong = 104, + ZSTD_error_srcBuffer_wrong = 105, + ZSTD_error_maxCode = 120 /* never EVER use this value directly, it can change in future versions! Use ZSTD_isError() instead */ +} ZSTD_ErrorCode; + +/*! ZSTD_getErrorCode() : + convert a `size_t` function result into a `ZSTD_ErrorCode` enum type, + which can be used to compare with enum list published above */ +ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult); +ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code); /*< Same as ZSTD_getErrorName, but using a `ZSTD_ErrorCode` enum argument */ + + + +#endif /* ZSTD_ERRORS_H_398273423 */ diff --git a/include/linux/zstd_lib.h b/include/linux/zstd_lib.h index 13151c34f725..b8c7dbf98390 100644 --- a/include/linux/zstd_lib.h +++ b/include/linux/zstd_lib.h @@ -2,1156 +2,2431 @@ * Copyright (c) Yann Collet, Facebook, Inc. * All rights reserved. * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. */ -#ifndef ZSTD_H -#define ZSTD_H +#ifndef ZSTD_H_235446 +#define ZSTD_H_235446 /* ====== Dependency ======*/ +#include /* INT_MAX */ #include /* size_t */ -/*-***************************************************************************** - * Introduction - * - * zstd, short for Zstandard, is a fast lossless compression algorithm, - * targeting real-time compression scenarios at zlib-level and better - * compression ratios. The zstd compression library provides in-memory - * compression and decompression functions. The library supports compression - * levels from 1 up to ZSTD_maxCLevel() which is 22. Levels >= 20, labeled - * ultra, should be used with caution, as they require more memory. - * Compression can be done in: - * - a single step, reusing a context (described as Explicit memory management) - * - unbounded multiple steps (described as Streaming compression) - * The compression ratio achievable on small data can be highly improved using - * compression with a dictionary in: - * - a single step (described as Simple dictionary API) - * - a single step, reusing a dictionary (described as Fast dictionary API) - ******************************************************************************/ +/* ===== ZSTDLIB_API : control library symbols visibility ===== */ +#define ZSTDLIB_VISIBILITY +#define ZSTDLIB_API ZSTDLIB_VISIBILITY + + +/* ***************************************************************************** + Introduction + + zstd, short for Zstandard, is a fast lossless compression algorithm, targeting + real-time compression scenarios at zlib-level and better compression ratios. + The zstd compression library provides in-memory compression and decompression + functions. + + The library supports regular compression levels from 1 up to ZSTD_maxCLevel(), + which is currently 22. Levels >= 20, labeled `--ultra`, should be used with + caution, as they require more memory. The library also offers negative + compression levels, which extend the range of speed vs. ratio preferences. + The lower the level, the faster the speed (at the cost of compression). + + Compression can be done in: + - a single step (described as Simple API) + - a single step, reusing a context (described as Explicit context) + - unbounded multiple steps (described as Streaming compression) + + The compression ratio achievable on small data can be highly improved using + a dictionary. Dictionary compression can be performed in: + - a single step (described as Simple dictionary API) + - a single step, reusing a dictionary (described as Bulk-processing + dictionary API) + + Advanced experimental functions can be accessed using + `#define ZSTD_STATIC_LINKING_ONLY` before including zstd.h. + + Advanced experimental APIs should never be used with a dynamically-linked + library. They are not "stable"; their definitions or signatures may change in + the future. Only static linking is allowed. +*******************************************************************************/ + +/*------ Version ------*/ +#define ZSTD_VERSION_MAJOR 1 +#define ZSTD_VERSION_MINOR 4 +#define ZSTD_VERSION_RELEASE 10 +#define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE) + +/*! ZSTD_versionNumber() : + * Return runtime library version, the value is (MAJOR*100*100 + MINOR*100 + RELEASE). */ +ZSTDLIB_API unsigned ZSTD_versionNumber(void); + +#define ZSTD_LIB_VERSION ZSTD_VERSION_MAJOR.ZSTD_VERSION_MINOR.ZSTD_VERSION_RELEASE +#define ZSTD_QUOTE(str) #str +#define ZSTD_EXPAND_AND_QUOTE(str) ZSTD_QUOTE(str) +#define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION) + +/*! ZSTD_versionString() : + * Return runtime library version, like "1.4.5". Requires v1.3.0+. */ +ZSTDLIB_API const char* ZSTD_versionString(void); + +/* ************************************* + * Default constant + ***************************************/ +#ifndef ZSTD_CLEVEL_DEFAULT +# define ZSTD_CLEVEL_DEFAULT 3 +#endif + +/* ************************************* + * Constants + ***************************************/ + +/* All magic numbers are supposed read/written to/from files/memory using little-endian convention */ +#define ZSTD_MAGICNUMBER 0xFD2FB528 /* valid since v0.8.0 */ +#define ZSTD_MAGIC_DICTIONARY 0xEC30A437 /* valid since v0.7.0 */ +#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50 /* all 16 values, from 0x184D2A50 to 0x184D2A5F, signal the beginning of a skippable frame */ +#define ZSTD_MAGIC_SKIPPABLE_MASK 0xFFFFFFF0 + +#define ZSTD_BLOCKSIZELOG_MAX 17 +#define ZSTD_BLOCKSIZE_MAX (1<= `ZSTD_compressBound(srcSize)`. + * @return : compressed size written into `dst` (<= `dstCapacity), + * or an error code if it fails (which can be tested using ZSTD_isError()). */ +ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + int compressionLevel); + +/*! ZSTD_decompress() : + * `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames. + * `dstCapacity` is an upper bound of originalSize to regenerate. + * If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data. + * @return : the number of bytes decompressed into `dst` (<= `dstCapacity`), + * or an errorCode if it fails (which can be tested using ZSTD_isError()). */ +ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity, + const void* src, size_t compressedSize); + +/*! ZSTD_getFrameContentSize() : requires v1.3.0+ + * `src` should point to the start of a ZSTD encoded frame. + * `srcSize` must be at least as large as the frame header. + * hint : any size >= `ZSTD_frameHeaderSize_max` is large enough. + * @return : - decompressed size of `src` frame content, if known + * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined + * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) + * note 1 : a 0 return value means the frame is valid but "empty". + * note 2 : decompressed size is an optional field, it may not be present, typically in streaming mode. + * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. + * In which case, it's necessary to use streaming mode to decompress data. + * Optionally, application can rely on some implicit limit, + * as ZSTD_decompress() only needs an upper bound of decompressed size. + * (For example, data could be necessarily cut into blocks <= 16 KB). + * note 3 : decompressed size is always present when compression is completed using single-pass functions, + * such as ZSTD_compress(), ZSTD_compressCCtx() ZSTD_compress_usingDict() or ZSTD_compress_usingCDict(). + * note 4 : decompressed size can be very large (64-bits value), + * potentially larger than what local system can handle as a single memory segment. + * In which case, it's necessary to use streaming mode to decompress data. + * note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified. + * Always ensure return value fits within application's authorized limits. + * Each application can set its own limits. + * note 6 : This function replaces ZSTD_getDecompressedSize() */ +#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) +ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); + +/*! ZSTD_getDecompressedSize() : + * NOTE: This function is now obsolete, in favor of ZSTD_getFrameContentSize(). + * Both functions work the same way, but ZSTD_getDecompressedSize() blends + * "empty", "unknown" and "error" results to the same return value (0), + * while ZSTD_getFrameContentSize() gives them separate return values. + * @return : decompressed size of `src` frame content _if known and not empty_, 0 otherwise. */ +ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize); + +/*! ZSTD_findFrameCompressedSize() : + * `src` should point to the start of a ZSTD frame or skippable frame. + * `srcSize` must be >= first frame size + * @return : the compressed size of the first frame starting at `src`, + * suitable to pass as `srcSize` to `ZSTD_decompress` or similar, + * or an error code if input is invalid */ +ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize); + /*====== Helper functions ======*/ +#define ZSTD_COMPRESSBOUND(srcSize) ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0)) /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */ +ZSTDLIB_API size_t ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */ +ZSTDLIB_API unsigned ZSTD_isError(size_t code); /*!< tells if a `size_t` function result is an error code */ +ZSTDLIB_API const char* ZSTD_getErrorName(size_t code); /*!< provides readable string from an error code */ +ZSTDLIB_API int ZSTD_minCLevel(void); /*!< minimum negative compression level allowed */ +ZSTDLIB_API int ZSTD_maxCLevel(void); /*!< maximum compression level available */ + + +/* ************************************* +* Explicit context +***************************************/ +/*= Compression context + * When compressing many times, + * it is recommended to allocate a context just once, + * and re-use it for each successive compression operation. + * This will make workload friendlier for system's memory. + * Note : re-using context is just a speed / resource optimization. + * It doesn't change the compression ratio, which remains identical. + * Note 2 : In multi-threaded environments, + * use one different context per thread for parallel execution. + */ +typedef struct ZSTD_CCtx_s ZSTD_CCtx; +ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx(void); +ZSTDLIB_API size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx); /* accept NULL pointer */ + +/*! ZSTD_compressCCtx() : + * Same as ZSTD_compress(), using an explicit ZSTD_CCtx. + * Important : in order to behave similarly to `ZSTD_compress()`, + * this function compresses at requested compression level, + * __ignoring any other parameter__ . + * If any advanced parameter was set using the advanced API, + * they will all be reset. Only `compressionLevel` remains. + */ +ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + int compressionLevel); + +/*= Decompression context + * When decompressing many times, + * it is recommended to allocate a context only once, + * and re-use it for each successive compression operation. + * This will make workload friendlier for system's memory. + * Use one context per thread for parallel execution. */ +typedef struct ZSTD_DCtx_s ZSTD_DCtx; +ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx(void); +ZSTDLIB_API size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx); /* accept NULL pointer */ + +/*! ZSTD_decompressDCtx() : + * Same as ZSTD_decompress(), + * requires an allocated ZSTD_DCtx. + * Compatible with sticky parameters. + */ +ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize); -/** - * enum ZSTD_ErrorCode - zstd error codes + +/* ************************************* +* Advanced compression API +***************************************/ + +/* API design : + * Parameters are pushed one by one into an existing context, + * using ZSTD_CCtx_set*() functions. + * Pushed parameters are sticky : they are valid for next compressed frame, and any subsequent frame. + * "sticky" parameters are applicable to `ZSTD_compress2()` and `ZSTD_compressStream*()` ! + * __They do not apply to "simple" one-shot variants such as ZSTD_compressCCtx()__ . + * + * It's possible to reset all parameters to "default" using ZSTD_CCtx_reset(). * - * Functions that return size_t can be checked for errors using ZSTD_isError() - * and the ZSTD_ErrorCode can be extracted using ZSTD_getErrorCode(). + * This API supercedes all other "advanced" API entry points in the experimental section. + * In the future, we expect to remove from experimental API entry points which are redundant with this API. + */ + + +/* Compression strategies, listed from fastest to strongest */ +typedef enum { ZSTD_fast=1, + ZSTD_dfast=2, + ZSTD_greedy=3, + ZSTD_lazy=4, + ZSTD_lazy2=5, + ZSTD_btlazy2=6, + ZSTD_btopt=7, + ZSTD_btultra=8, + ZSTD_btultra2=9 + /* note : new strategies _might_ be added in the future. + Only the order (from fast to strong) is guaranteed */ +} ZSTD_strategy; + + +typedef enum { + + /* compression parameters + * Note: When compressing with a ZSTD_CDict these parameters are superseded + * by the parameters used to construct the ZSTD_CDict. + * See ZSTD_CCtx_refCDict() for more info (superseded-by-cdict). */ + ZSTD_c_compressionLevel=100, /* Set compression parameters according to pre-defined cLevel table. + * Note that exact compression parameters are dynamically determined, + * depending on both compression level and srcSize (when known). + * Default level is ZSTD_CLEVEL_DEFAULT==3. + * Special: value 0 means default, which is controlled by ZSTD_CLEVEL_DEFAULT. + * Note 1 : it's possible to pass a negative compression level. + * Note 2 : setting a level does not automatically set all other compression parameters + * to default. Setting this will however eventually dynamically impact the compression + * parameters which have not been manually set. The manually set + * ones will 'stick'. */ + /* Advanced compression parameters : + * It's possible to pin down compression parameters to some specific values. + * In which case, these values are no longer dynamically selected by the compressor */ + ZSTD_c_windowLog=101, /* Maximum allowed back-reference distance, expressed as power of 2. + * This will set a memory budget for streaming decompression, + * with larger values requiring more memory + * and typically compressing more. + * Must be clamped between ZSTD_WINDOWLOG_MIN and ZSTD_WINDOWLOG_MAX. + * Special: value 0 means "use default windowLog". + * Note: Using a windowLog greater than ZSTD_WINDOWLOG_LIMIT_DEFAULT + * requires explicitly allowing such size at streaming decompression stage. */ + ZSTD_c_hashLog=102, /* Size of the initial probe table, as a power of 2. + * Resulting memory usage is (1 << (hashLog+2)). + * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX. + * Larger tables improve compression ratio of strategies <= dFast, + * and improve speed of strategies > dFast. + * Special: value 0 means "use default hashLog". */ + ZSTD_c_chainLog=103, /* Size of the multi-probe search table, as a power of 2. + * Resulting memory usage is (1 << (chainLog+2)). + * Must be clamped between ZSTD_CHAINLOG_MIN and ZSTD_CHAINLOG_MAX. + * Larger tables result in better and slower compression. + * This parameter is useless for "fast" strategy. + * It's still useful when using "dfast" strategy, + * in which case it defines a secondary probe table. + * Special: value 0 means "use default chainLog". */ + ZSTD_c_searchLog=104, /* Number of search attempts, as a power of 2. + * More attempts result in better and slower compression. + * This parameter is useless for "fast" and "dFast" strategies. + * Special: value 0 means "use default searchLog". */ + ZSTD_c_minMatch=105, /* Minimum size of searched matches. + * Note that Zstandard can still find matches of smaller size, + * it just tweaks its search algorithm to look for this size and larger. + * Larger values increase compression and decompression speed, but decrease ratio. + * Must be clamped between ZSTD_MINMATCH_MIN and ZSTD_MINMATCH_MAX. + * Note that currently, for all strategies < btopt, effective minimum is 4. + * , for all strategies > fast, effective maximum is 6. + * Special: value 0 means "use default minMatchLength". */ + ZSTD_c_targetLength=106, /* Impact of this field depends on strategy. + * For strategies btopt, btultra & btultra2: + * Length of Match considered "good enough" to stop search. + * Larger values make compression stronger, and slower. + * For strategy fast: + * Distance between match sampling. + * Larger values make compression faster, and weaker. + * Special: value 0 means "use default targetLength". */ + ZSTD_c_strategy=107, /* See ZSTD_strategy enum definition. + * The higher the value of selected strategy, the more complex it is, + * resulting in stronger and slower compression. + * Special: value 0 means "use default strategy". */ + + /* LDM mode parameters */ + ZSTD_c_enableLongDistanceMatching=160, /* Enable long distance matching. + * This parameter is designed to improve compression ratio + * for large inputs, by finding large matches at long distance. + * It increases memory usage and window size. + * Note: enabling this parameter increases default ZSTD_c_windowLog to 128 MB + * except when expressly set to a different value. + * Note: will be enabled by default if ZSTD_c_windowLog >= 128 MB and + * compression strategy >= ZSTD_btopt (== compression level 16+) */ + ZSTD_c_ldmHashLog=161, /* Size of the table for long distance matching, as a power of 2. + * Larger values increase memory usage and compression ratio, + * but decrease compression speed. + * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX + * default: windowlog - 7. + * Special: value 0 means "automatically determine hashlog". */ + ZSTD_c_ldmMinMatch=162, /* Minimum match size for long distance matcher. + * Larger/too small values usually decrease compression ratio. + * Must be clamped between ZSTD_LDM_MINMATCH_MIN and ZSTD_LDM_MINMATCH_MAX. + * Special: value 0 means "use default value" (default: 64). */ + ZSTD_c_ldmBucketSizeLog=163, /* Log size of each bucket in the LDM hash table for collision resolution. + * Larger values improve collision resolution but decrease compression speed. + * The maximum value is ZSTD_LDM_BUCKETSIZELOG_MAX. + * Special: value 0 means "use default value" (default: 3). */ + ZSTD_c_ldmHashRateLog=164, /* Frequency of inserting/looking up entries into the LDM hash table. + * Must be clamped between 0 and (ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN). + * Default is MAX(0, (windowLog - ldmHashLog)), optimizing hash table usage. + * Larger values improve compression speed. + * Deviating far from default value will likely result in a compression ratio decrease. + * Special: value 0 means "automatically determine hashRateLog". */ + + /* frame parameters */ + ZSTD_c_contentSizeFlag=200, /* Content size will be written into frame header _whenever known_ (default:1) + * Content size must be known at the beginning of compression. + * This is automatically the case when using ZSTD_compress2(), + * For streaming scenarios, content size must be provided with ZSTD_CCtx_setPledgedSrcSize() */ + ZSTD_c_checksumFlag=201, /* A 32-bits checksum of content is written at end of frame (default:0) */ + ZSTD_c_dictIDFlag=202, /* When applicable, dictionary's ID is written into frame header (default:1) */ + + /* multi-threading parameters */ + /* These parameters are only active if multi-threading is enabled (compiled with build macro ZSTD_MULTITHREAD). + * Otherwise, trying to set any other value than default (0) will be a no-op and return an error. + * In a situation where it's unknown if the linked library supports multi-threading or not, + * setting ZSTD_c_nbWorkers to any value >= 1 and consulting the return value provides a quick way to check this property. + */ + ZSTD_c_nbWorkers=400, /* Select how many threads will be spawned to compress in parallel. + * When nbWorkers >= 1, triggers asynchronous mode when invoking ZSTD_compressStream*() : + * ZSTD_compressStream*() consumes input and flush output if possible, but immediately gives back control to caller, + * while compression is performed in parallel, within worker thread(s). + * (note : a strong exception to this rule is when first invocation of ZSTD_compressStream2() sets ZSTD_e_end : + * in which case, ZSTD_compressStream2() delegates to ZSTD_compress2(), which is always a blocking call). + * More workers improve speed, but also increase memory usage. + * Default value is `0`, aka "single-threaded mode" : no worker is spawned, + * compression is performed inside Caller's thread, and all invocations are blocking */ + ZSTD_c_jobSize=401, /* Size of a compression job. This value is enforced only when nbWorkers >= 1. + * Each compression job is completed in parallel, so this value can indirectly impact the nb of active threads. + * 0 means default, which is dynamically determined based on compression parameters. + * Job size must be a minimum of overlap size, or 1 MB, whichever is largest. + * The minimum size is automatically and transparently enforced. */ + ZSTD_c_overlapLog=402, /* Control the overlap size, as a fraction of window size. + * The overlap size is an amount of data reloaded from previous job at the beginning of a new job. + * It helps preserve compression ratio, while each job is compressed in parallel. + * This value is enforced only when nbWorkers >= 1. + * Larger values increase compression ratio, but decrease speed. + * Possible values range from 0 to 9 : + * - 0 means "default" : value will be determined by the library, depending on strategy + * - 1 means "no overlap" + * - 9 means "full overlap", using a full window size. + * Each intermediate rank increases/decreases load size by a factor 2 : + * 9: full window; 8: w/2; 7: w/4; 6: w/8; 5:w/16; 4: w/32; 3:w/64; 2:w/128; 1:no overlap; 0:default + * default value varies between 6 and 9, depending on strategy */ + + /* note : additional experimental parameters are also available + * within the experimental section of the API. + * At the time of this writing, they include : + * ZSTD_c_rsyncable + * ZSTD_c_format + * ZSTD_c_forceMaxWindow + * ZSTD_c_forceAttachDict + * ZSTD_c_literalCompressionMode + * ZSTD_c_targetCBlockSize + * ZSTD_c_srcSizeHint + * ZSTD_c_enableDedicatedDictSearch + * ZSTD_c_stableInBuffer + * ZSTD_c_stableOutBuffer + * ZSTD_c_blockDelimiters + * ZSTD_c_validateSequences + * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. + * note : never ever use experimentalParam? names directly; + * also, the enums values themselves are unstable and can still change. + */ + ZSTD_c_experimentalParam1=500, + ZSTD_c_experimentalParam2=10, + ZSTD_c_experimentalParam3=1000, + ZSTD_c_experimentalParam4=1001, + ZSTD_c_experimentalParam5=1002, + ZSTD_c_experimentalParam6=1003, + ZSTD_c_experimentalParam7=1004, + ZSTD_c_experimentalParam8=1005, + ZSTD_c_experimentalParam9=1006, + ZSTD_c_experimentalParam10=1007, + ZSTD_c_experimentalParam11=1008, + ZSTD_c_experimentalParam12=1009 +} ZSTD_cParameter; + +typedef struct { + size_t error; + int lowerBound; + int upperBound; +} ZSTD_bounds; + +/*! ZSTD_cParam_getBounds() : + * All parameters must belong to an interval with lower and upper bounds, + * otherwise they will either trigger an error or be automatically clamped. + * @return : a structure, ZSTD_bounds, which contains + * - an error status field, which must be tested using ZSTD_isError() + * - lower and upper bounds, both inclusive + */ +ZSTDLIB_API ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter cParam); + +/*! ZSTD_CCtx_setParameter() : + * Set one compression parameter, selected by enum ZSTD_cParameter. + * All parameters have valid bounds. Bounds can be queried using ZSTD_cParam_getBounds(). + * Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter). + * Setting a parameter is generally only possible during frame initialization (before starting compression). + * Exception : when using multi-threading mode (nbWorkers >= 1), + * the following parameters can be updated _during_ compression (within same frame): + * => compressionLevel, hashLog, chainLog, searchLog, minMatch, targetLength and strategy. + * new parameters will be active for next job only (after a flush()). + * @return : an error code (which can be tested using ZSTD_isError()). */ +ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value); + +/*! ZSTD_CCtx_setPledgedSrcSize() : + * Total input data size to be compressed as a single frame. + * Value will be written in frame header, unless if explicitly forbidden using ZSTD_c_contentSizeFlag. + * This value will also be controlled at end of frame, and trigger an error if not respected. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : pledgedSrcSize==0 actually means zero, aka an empty frame. + * In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN. + * ZSTD_CONTENTSIZE_UNKNOWN is default value for any new frame. + * Note 2 : pledgedSrcSize is only valid once, for the next frame. + * It's discarded at the end of the frame, and replaced by ZSTD_CONTENTSIZE_UNKNOWN. + * Note 3 : Whenever all input data is provided and consumed in a single round, + * for example with ZSTD_compress2(), + * or invoking immediately ZSTD_compressStream2(,,,ZSTD_e_end), + * this value is automatically overridden by srcSize instead. + */ +ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize); + typedef enum { - ZSTD_error_no_error, - ZSTD_error_GENERIC, - ZSTD_error_prefix_unknown, - ZSTD_error_version_unsupported, - ZSTD_error_parameter_unknown, - ZSTD_error_frameParameter_unsupported, - ZSTD_error_frameParameter_unsupportedBy32bits, - ZSTD_error_frameParameter_windowTooLarge, - ZSTD_error_compressionParameter_unsupported, - ZSTD_error_init_missing, - ZSTD_error_memory_allocation, - ZSTD_error_stage_wrong, - ZSTD_error_dstSize_tooSmall, - ZSTD_error_srcSize_wrong, - ZSTD_error_corruption_detected, - ZSTD_error_checksum_wrong, - ZSTD_error_tableLog_tooLarge, - ZSTD_error_maxSymbolValue_tooLarge, - ZSTD_error_maxSymbolValue_tooSmall, - ZSTD_error_dictionary_corrupted, - ZSTD_error_dictionary_wrong, - ZSTD_error_dictionaryCreation_failed, - ZSTD_error_maxCode -} ZSTD_ErrorCode; - -/** - * ZSTD_maxCLevel() - maximum compression level available - * - * Return: Maximum compression level available. - */ -int ZSTD_maxCLevel(void); -/** - * ZSTD_compressBound() - maximum compressed size in worst case scenario - * @srcSize: The size of the data to compress. - * - * Return: The maximum compressed size in the worst case scenario. - */ -size_t ZSTD_compressBound(size_t srcSize); -/** - * ZSTD_isError() - tells if a size_t function result is an error code - * @code: The function result to check for error. - * - * Return: Non-zero iff the code is an error. - */ -static __attribute__((unused)) unsigned int ZSTD_isError(size_t code) -{ - return code > (size_t)-ZSTD_error_maxCode; -} -/** - * ZSTD_getErrorCode() - translates an error function result to a ZSTD_ErrorCode - * @functionResult: The result of a function for which ZSTD_isError() is true. - * - * Return: The ZSTD_ErrorCode corresponding to the functionResult or 0 - * if the functionResult isn't an error. - */ -static __attribute__((unused)) ZSTD_ErrorCode ZSTD_getErrorCode( - size_t functionResult) -{ - if (!ZSTD_isError(functionResult)) - return (ZSTD_ErrorCode)0; - return (ZSTD_ErrorCode)(0 - functionResult); -} - -/** - * enum ZSTD_strategy - zstd compression search strategy - * - * From faster to stronger. + ZSTD_reset_session_only = 1, + ZSTD_reset_parameters = 2, + ZSTD_reset_session_and_parameters = 3 +} ZSTD_ResetDirective; + +/*! ZSTD_CCtx_reset() : + * There are 2 different things that can be reset, independently or jointly : + * - The session : will stop compressing current frame, and make CCtx ready to start a new one. + * Useful after an error, or to interrupt any ongoing compression. + * Any internal data not yet flushed is cancelled. + * Compression parameters and dictionary remain unchanged. + * They will be used to compress next frame. + * Resetting session never fails. + * - The parameters : changes all parameters back to "default". + * This removes any reference to any dictionary too. + * Parameters can only be changed between 2 sessions (i.e. no compression is currently ongoing) + * otherwise the reset fails, and function returns an error value (which can be tested using ZSTD_isError()) + * - Both : similar to resetting the session, followed by resetting parameters. */ +ZSTDLIB_API size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset); + +/*! ZSTD_compress2() : + * Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API. + * ZSTD_compress2() always starts a new frame. + * Should cctx hold data from a previously unfinished frame, everything about it is forgotten. + * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() + * - The function is always blocking, returns when compression is completed. + * Hint : compression runs faster if `dstCapacity` >= `ZSTD_compressBound(srcSize)`. + * @return : compressed size written into `dst` (<= `dstCapacity), + * or an error code if it fails (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize); + + +/* ************************************* +* Advanced decompression API +***************************************/ + +/* The advanced API pushes parameters one by one into an existing DCtx context. + * Parameters are sticky, and remain valid for all following frames + * using the same DCtx context. + * It's possible to reset parameters to default values using ZSTD_DCtx_reset(). + * Note : This API is compatible with existing ZSTD_decompressDCtx() and ZSTD_decompressStream(). + * Therefore, no new decompression function is necessary. + */ + typedef enum { - ZSTD_fast, - ZSTD_dfast, - ZSTD_greedy, - ZSTD_lazy, - ZSTD_lazy2, - ZSTD_btlazy2, - ZSTD_btopt, - ZSTD_btopt2 -} ZSTD_strategy; -/** - * struct ZSTD_compressionParameters - zstd compression parameters - * @windowLog: Log of the largest match distance. Larger means more - * compression, and more memory needed during decompression. - * @chainLog: Fully searched segment. Larger means more compression, slower, - * and more memory (useless for fast). - * @hashLog: Dispatch table. Larger means more compression, - * slower, and more memory. - * @searchLog: Number of searches. Larger means more compression and slower. - * @searchLength: Match length searched. Larger means faster decompression, - * sometimes less compression. - * @targetLength: Acceptable match size for optimal parser (only). Larger means - * more compression, and slower. - * @strategy: The zstd compression strategy. + ZSTD_d_windowLogMax=100, /* Select a size limit (in power of 2) beyond which + * the streaming API will refuse to allocate memory buffer + * in order to protect the host from unreasonable memory requirements. + * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode. + * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT). + * Special: value 0 means "use default maximum windowLog". */ + + /* note : additional experimental parameters are also available + * within the experimental section of the API. + * At the time of this writing, they include : + * ZSTD_d_format + * ZSTD_d_stableOutBuffer + * ZSTD_d_forceIgnoreChecksum + * ZSTD_d_refMultipleDDicts + * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. + * note : never ever use experimentalParam? names directly + */ + ZSTD_d_experimentalParam1=1000, + ZSTD_d_experimentalParam2=1001, + ZSTD_d_experimentalParam3=1002, + ZSTD_d_experimentalParam4=1003 + +} ZSTD_dParameter; + +/*! ZSTD_dParam_getBounds() : + * All parameters must belong to an interval with lower and upper bounds, + * otherwise they will either trigger an error or be automatically clamped. + * @return : a structure, ZSTD_bounds, which contains + * - an error status field, which must be tested using ZSTD_isError() + * - both lower and upper bounds, inclusive */ -typedef struct { - unsigned int windowLog; - unsigned int chainLog; - unsigned int hashLog; - unsigned int searchLog; - unsigned int searchLength; - unsigned int targetLength; - ZSTD_strategy strategy; -} ZSTD_compressionParameters; +ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam); + +/*! ZSTD_DCtx_setParameter() : + * Set one compression parameter, selected by enum ZSTD_dParameter. + * All parameters have valid bounds. Bounds can be queried using ZSTD_dParam_getBounds(). + * Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter). + * Setting a parameter is only possible during frame initialization (before starting decompression). + * @return : 0, or an error code (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value); + +/*! ZSTD_DCtx_reset() : + * Return a DCtx to clean state. + * Session and parameters can be reset jointly or separately. + * Parameters can only be reset when no active frame is being decompressed. + * @return : 0, or an error code, which can be tested with ZSTD_isError() + */ +ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); + + +/* ************************** +* Streaming +****************************/ + +typedef struct ZSTD_inBuffer_s { + const void* src; /*< start of input buffer */ + size_t size; /*< size of input buffer */ + size_t pos; /*< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */ +} ZSTD_inBuffer; + +typedef struct ZSTD_outBuffer_s { + void* dst; /*< start of output buffer */ + size_t size; /*< size of output buffer */ + size_t pos; /*< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */ +} ZSTD_outBuffer; + -/** - * struct ZSTD_frameParameters - zstd frame parameters - * @contentSizeFlag: Controls whether content size will be present in the frame - * header (when known). - * @checksumFlag: Controls whether a 32-bit checksum is generated at the end - * of the frame for error detection. - * @noDictIDFlag: Controls whether dictID will be saved into the frame header - * when using dictionary compression. + +/*-*********************************************************************** +* Streaming compression - HowTo +* +* A ZSTD_CStream object is required to track streaming operation. +* Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources. +* ZSTD_CStream objects can be reused multiple times on consecutive compression operations. +* It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory. +* +* For parallel execution, use one separate ZSTD_CStream per thread. +* +* note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing. +* +* Parameters are sticky : when starting a new compression on the same context, +* it will re-use the same sticky parameters as previous compression session. +* When in doubt, it's recommended to fully initialize the context before usage. +* Use ZSTD_CCtx_reset() to reset the context and ZSTD_CCtx_setParameter(), +* ZSTD_CCtx_setPledgedSrcSize(), or ZSTD_CCtx_loadDictionary() and friends to +* set more specific parameters, the pledged source size, or load a dictionary. +* +* Use ZSTD_compressStream2() with ZSTD_e_continue as many times as necessary to +* consume input stream. The function will automatically update both `pos` +* fields within `input` and `output`. +* Note that the function may not consume the entire input, for example, because +* the output buffer is already full, in which case `input.pos < input.size`. +* The caller must check if input has been entirely consumed. +* If not, the caller must make some room to receive more compressed data, +* and then present again remaining input data. +* note: ZSTD_e_continue is guaranteed to make some forward progress when called, +* but doesn't guarantee maximal forward progress. This is especially relevant +* when compressing with multiple threads. The call won't block if it can +* consume some input, but if it can't it will wait for some, but not all, +* output to be flushed. +* @return : provides a minimum amount of data remaining to be flushed from internal buffers +* or an error code, which can be tested using ZSTD_isError(). +* +* At any moment, it's possible to flush whatever data might remain stuck within internal buffer, +* using ZSTD_compressStream2() with ZSTD_e_flush. `output->pos` will be updated. +* Note that, if `output->size` is too small, a single invocation with ZSTD_e_flush might not be enough (return code > 0). +* In which case, make some room to receive more compressed data, and call again ZSTD_compressStream2() with ZSTD_e_flush. +* You must continue calling ZSTD_compressStream2() with ZSTD_e_flush until it returns 0, at which point you can change the +* operation. +* note: ZSTD_e_flush will flush as much output as possible, meaning when compressing with multiple threads, it will +* block until the flush is complete or the output buffer is full. +* @return : 0 if internal buffers are entirely flushed, +* >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), +* or an error code, which can be tested using ZSTD_isError(). +* +* Calling ZSTD_compressStream2() with ZSTD_e_end instructs to finish a frame. +* It will perform a flush and write frame epilogue. +* The epilogue is required for decoders to consider a frame completed. +* flush operation is the same, and follows same rules as calling ZSTD_compressStream2() with ZSTD_e_flush. +* You must continue calling ZSTD_compressStream2() with ZSTD_e_end until it returns 0, at which point you are free to +* start a new frame. +* note: ZSTD_e_end will flush as much output as possible, meaning when compressing with multiple threads, it will +* block until the flush is complete or the output buffer is full. +* @return : 0 if frame fully completed and fully flushed, +* >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), +* or an error code, which can be tested using ZSTD_isError(). +* +* *******************************************************************/ + +typedef ZSTD_CCtx ZSTD_CStream; /*< CCtx and CStream are now effectively same object (>= v1.3.0) */ + /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */ +/*===== ZSTD_CStream management functions =====*/ +ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void); +ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs); /* accept NULL pointer */ + +/*===== Streaming compression functions =====*/ +typedef enum { + ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */ + ZSTD_e_flush=1, /* flush any data provided so far, + * it creates (at least) one new block, that can be decoded immediately on reception; + * frame will continue: any future data can still reference previously compressed data, improving compression. + * note : multithreaded compression will block to flush as much output as possible. */ + ZSTD_e_end=2 /* flush any remaining data _and_ close current frame. + * note that frame is only closed after compressed data is fully flushed (return value == 0). + * After that point, any additional data starts a new frame. + * note : each frame is independent (does not reference any content from previous frame). + : note : multithreaded compression will block to flush as much output as possible. */ +} ZSTD_EndDirective; + +/*! ZSTD_compressStream2() : + * Behaves about the same as ZSTD_compressStream, with additional control on end directive. + * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() + * - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode) + * - output->pos must be <= dstCapacity, input->pos must be <= srcSize + * - output->pos and input->pos will be updated. They are guaranteed to remain below their respective limit. + * - endOp must be a valid directive + * - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller. + * - When nbWorkers>=1, function is non-blocking : it copies a portion of input, distributes jobs to internal worker threads, flush to output whatever is available, + * and then immediately returns, just indicating that there is some data remaining to be flushed. + * The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte. + * - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking. + * - @return provides a minimum amount of data remaining to be flushed from internal buffers + * or an error code, which can be tested using ZSTD_isError(). + * if @return != 0, flush is not fully completed, there is still some data left within internal buffers. + * This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers. + * For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed. + * - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0), + * only ZSTD_e_end or ZSTD_e_flush operations are allowed. + * Before starting a new compression job, or changing compression parameters, + * it is required to fully flush internal buffers. + */ +ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective endOp); + + +/* These buffer sizes are softly recommended. + * They are not required : ZSTD_compressStream*() happily accepts any buffer size, for both input and output. + * Respecting the recommended size just makes it a bit easier for ZSTD_compressStream*(), + * reducing the amount of memory shuffling and buffering, resulting in minor performance savings. + * + * However, note that these recommendations are from the perspective of a C caller program. + * If the streaming interface is invoked from some other language, + * especially managed ones such as Java or Go, through a foreign function interface such as jni or cgo, + * a major performance rule is to reduce crossing such interface to an absolute minimum. + * It's not rare that performance ends being spent more into the interface, rather than compression itself. + * In which cases, prefer using large buffers, as large as practical, + * for both input and output, to reduce the nb of roundtrips. + */ +ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /*< recommended size for input buffer */ +ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /*< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block. */ + + +/* ***************************************************************************** + * This following is a legacy streaming API. + * It can be replaced by ZSTD_CCtx_reset() and ZSTD_compressStream2(). + * It is redundant, but remains fully supported. + * Advanced parameters and dictionary compression can only be used through the + * new API. + ******************************************************************************/ + +/*! + * Equivalent to: * - * The default value is all fields set to 0. + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any) + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + */ +ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel); +/*! + * Alternative for ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue). + * NOTE: The return value is different. ZSTD_compressStream() returns a hint for + * the next read size (if non-zero and not an error). ZSTD_compressStream2() + * returns the minimum nb of bytes left to flush (if non-zero and not an error). */ +ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input); +/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_flush). */ +ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); +/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */ +ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); + + +/*-*************************************************************************** +* Streaming decompression - HowTo +* +* A ZSTD_DStream object is required to track streaming operations. +* Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources. +* ZSTD_DStream objects can be re-used multiple times. +* +* Use ZSTD_initDStream() to start a new decompression operation. +* @return : recommended first input size +* Alternatively, use advanced API to set specific properties. +* +* Use ZSTD_decompressStream() repetitively to consume your input. +* The function will update both `pos` fields. +* If `input.pos < input.size`, some input has not been consumed. +* It's up to the caller to present again remaining data. +* The function tries to flush all data decoded immediately, respecting output buffer size. +* If `output.pos < output.size`, decoder has flushed everything it could. +* But if `output.pos == output.size`, there might be some data left within internal buffers., +* In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer. +* Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX. +* @return : 0 when a frame is completely decoded and fully flushed, +* or an error code, which can be tested using ZSTD_isError(), +* or any other value > 0, which means there is still some decoding or flushing to do to complete current frame : +* the return value is a suggested next input size (just a hint for better latency) +* that will never request more than the remaining frame size. +* *******************************************************************************/ + +typedef ZSTD_DCtx ZSTD_DStream; /*< DCtx and DStream are now effectively same object (>= v1.3.0) */ + /* For compatibility with versions <= v1.2.0, prefer differentiating them. */ +/*===== ZSTD_DStream management functions =====*/ +ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void); +ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds); /* accept NULL pointer */ + +/*===== Streaming decompression functions =====*/ + +/* This function is redundant with the advanced API and equivalent to: + * + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_refDDict(zds, NULL); + */ +ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds); + +ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input); + +ZSTDLIB_API size_t ZSTD_DStreamInSize(void); /*!< recommended size for input buffer */ +ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */ + + +/* ************************ +* Simple dictionary API +***************************/ +/*! ZSTD_compress_usingDict() : + * Compression at an explicit compression level using a Dictionary. + * A dictionary can be any arbitrary data segment (also called a prefix), + * or a buffer with specified information (see dictBuilder/zdict.h). + * Note : This function loads the dictionary, resulting in significant startup delay. + * It's intended for a dictionary used only once. + * Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. */ +ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + int compressionLevel); + +/*! ZSTD_decompress_usingDict() : + * Decompression using a known Dictionary. + * Dictionary must be identical to the one used during compression. + * Note : This function loads the dictionary, resulting in significant startup delay. + * It's intended for a dictionary used only once. + * Note : When `dict == NULL || dictSize < 8` no dictionary is used. */ +ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize); + + +/* ********************************* + * Bulk processing dictionary API + **********************************/ +typedef struct ZSTD_CDict_s ZSTD_CDict; + +/*! ZSTD_createCDict() : + * When compressing multiple messages or blocks using the same dictionary, + * it's recommended to digest the dictionary only once, since it's a costly operation. + * ZSTD_createCDict() will create a state from digesting a dictionary. + * The resulting state can be used for future compression operations with very limited startup cost. + * ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only. + * @dictBuffer can be released after ZSTD_CDict creation, because its content is copied within CDict. + * Note 1 : Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate @dictBuffer content. + * Note 2 : A ZSTD_CDict can be created from an empty @dictBuffer, + * in which case the only thing that it transports is the @compressionLevel. + * This can be useful in a pipeline featuring ZSTD_compress_usingCDict() exclusively, + * expecting a ZSTD_CDict parameter with any data, including those without a known dictionary. */ +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, + int compressionLevel); + +/*! ZSTD_freeCDict() : + * Function frees memory allocated by ZSTD_createCDict(). + * If a NULL pointer is passed, no operation is performed. */ +ZSTDLIB_API size_t ZSTD_freeCDict(ZSTD_CDict* CDict); + +/*! ZSTD_compress_usingCDict() : + * Compression using a digested Dictionary. + * Recommended when same dictionary is used multiple times. + * Note : compression level is _decided at dictionary creation time_, + * and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */ +ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict); + + +typedef struct ZSTD_DDict_s ZSTD_DDict; + +/*! ZSTD_createDDict() : + * Create a digested dictionary, ready to start decompression operation without startup delay. + * dictBuffer can be released after DDict creation, as its content is copied inside DDict. */ +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize); + +/*! ZSTD_freeDDict() : + * Function frees memory allocated with ZSTD_createDDict() + * If a NULL pointer is passed, no operation is performed. */ +ZSTDLIB_API size_t ZSTD_freeDDict(ZSTD_DDict* ddict); + +/*! ZSTD_decompress_usingDDict() : + * Decompression using a digested Dictionary. + * Recommended when same dictionary is used multiple times. */ +ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_DDict* ddict); + + +/* ****************************** + * Dictionary helper functions + *******************************/ + +/*! ZSTD_getDictID_fromDict() : + * Provides the dictID stored within dictionary. + * if @return == 0, the dictionary is not conformant with Zstandard specification. + * It can still be loaded, but as a content-only dictionary. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize); + +/*! ZSTD_getDictID_fromDDict() : + * Provides the dictID of the dictionary loaded into `ddict`. + * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. + * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict); + +/*! ZSTD_getDictID_fromFrame() : + * Provides the dictID required to decompressed the frame stored within `src`. + * If @return == 0, the dictID could not be decoded. + * This could for one of the following reasons : + * - The frame does not require a dictionary to be decoded (most common case). + * - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information. + * Note : this use case also happens when using a non-conformant dictionary. + * - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`). + * - This is not a Zstandard frame. + * When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); + + +/* ***************************************************************************** + * Advanced dictionary and prefix API + * + * This API allows dictionaries to be used with ZSTD_compress2(), + * ZSTD_compressStream2(), and ZSTD_decompress(). Dictionaries are sticky, and + * only reset with the context is reset with ZSTD_reset_parameters or + * ZSTD_reset_session_and_parameters. Prefixes are single-use. + ******************************************************************************/ + + +/*! ZSTD_CCtx_loadDictionary() : + * Create an internal CDict from `dict` buffer. + * Decompression will have to use same dictionary. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special: Loading a NULL (or 0-size) dictionary invalidates previous dictionary, + * meaning "return to no-dictionary mode". + * Note 1 : Dictionary is sticky, it will be used for all future compressed frames. + * To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters). + * Note 2 : Loading a dictionary involves building tables. + * It's also a CPU consuming operation, with non-negligible impact on latency. + * Tables are dependent on compression parameters, and for this reason, + * compression parameters can no longer be changed after loading a dictionary. + * Note 3 :`dict` content will be copied internally. + * Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference content instead. + * In such a case, dictionary buffer must outlive its users. + * Note 4 : Use ZSTD_CCtx_loadDictionary_advanced() + * to precisely select how dictionary content must be interpreted. */ +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); + +/*! ZSTD_CCtx_refCDict() : + * Reference a prepared dictionary, to be used for all next compressed frames. + * Note that compression parameters are enforced from within CDict, + * and supersede any compression parameter previously set within CCtx. + * The parameters ignored are labelled as "superseded-by-cdict" in the ZSTD_cParameter enum docs. + * The ignored parameters will be used again if the CCtx is returned to no-dictionary mode. + * The dictionary will remain valid for future compressed frames using same CCtx. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special : Referencing a NULL CDict means "return to no-dictionary mode". + * Note 1 : Currently, only one dictionary can be managed. + * Referencing a new dictionary effectively "discards" any previous one. + * Note 2 : CDict is just referenced, its lifetime must outlive its usage within CCtx. */ +ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); + +/*! ZSTD_CCtx_refPrefix() : + * Reference a prefix (single-usage dictionary) for next compressed frame. + * A prefix is **only used once**. Tables are discarded at end of frame (ZSTD_e_end). + * Decompression will need same prefix to properly regenerate data. + * Compressing with a prefix is similar in outcome as performing a diff and compressing it, + * but performs much faster, especially during decompression (compression speed is tunable with compression level). + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary + * Note 1 : Prefix buffer is referenced. It **must** outlive compression. + * Its content must remain unmodified during compression. + * Note 2 : If the intention is to diff some large src data blob with some prior version of itself, + * ensure that the window size is large enough to contain the entire source. + * See ZSTD_c_windowLog. + * Note 3 : Referencing a prefix involves building tables, which are dependent on compression parameters. + * It's a CPU consuming operation, with non-negligible impact on latency. + * If there is a need to use the same prefix multiple times, consider loadDictionary instead. + * Note 4 : By default, the prefix is interpreted as raw content (ZSTD_dct_rawContent). + * Use experimental ZSTD_CCtx_refPrefix_advanced() to alter dictionary interpretation. */ +ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, + const void* prefix, size_t prefixSize); + +/*! ZSTD_DCtx_loadDictionary() : + * Create an internal DDict from dict buffer, + * to be used to decompress next frames. + * The dictionary remains valid for all future frames, until explicitly invalidated. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary, + * meaning "return to no-dictionary mode". + * Note 1 : Loading a dictionary involves building tables, + * which has a non-negligible impact on CPU usage and latency. + * It's recommended to "load once, use many times", to amortize the cost + * Note 2 :`dict` content will be copied internally, so `dict` can be released after loading. + * Use ZSTD_DCtx_loadDictionary_byReference() to reference dictionary content instead. + * Note 3 : Use ZSTD_DCtx_loadDictionary_advanced() to take control of + * how dictionary content is loaded and interpreted. + */ +ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); + +/*! ZSTD_DCtx_refDDict() : + * Reference a prepared dictionary, to be used to decompress next frames. + * The dictionary remains active for decompression of future frames using same DCtx. + * + * If called with ZSTD_d_refMultipleDDicts enabled, repeated calls of this function + * will store the DDict references in a table, and the DDict used for decompression + * will be determined at decompression time, as per the dict ID in the frame. + * The memory for the table is allocated on the first call to refDDict, and can be + * freed with ZSTD_freeDCtx(). + * + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : Currently, only one dictionary can be managed. + * Referencing a new dictionary effectively "discards" any previous one. + * Special: referencing a NULL DDict means "return to no-dictionary mode". + * Note 2 : DDict is just referenced, its lifetime must outlive its usage from DCtx. + */ +ZSTDLIB_API size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); + +/*! ZSTD_DCtx_refPrefix() : + * Reference a prefix (single-usage dictionary) to decompress next frame. + * This is the reverse operation of ZSTD_CCtx_refPrefix(), + * and must use the same prefix as the one used during compression. + * Prefix is **only used once**. Reference is discarded at end of frame. + * End of frame is reached when ZSTD_decompressStream() returns 0. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : Adding any prefix (including NULL) invalidates any previously set prefix or dictionary + * Note 2 : Prefix buffer is referenced. It **must** outlive decompression. + * Prefix buffer must remain unmodified up to the end of frame, + * reached when ZSTD_decompressStream() returns 0. + * Note 3 : By default, the prefix is treated as raw content (ZSTD_dct_rawContent). + * Use ZSTD_CCtx_refPrefix_advanced() to alter dictMode (Experimental section) + * Note 4 : Referencing a raw content prefix has almost no cpu nor memory cost. + * A full dictionary is more costly, as it requires building tables. + */ +ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, + const void* prefix, size_t prefixSize); + +/* === Memory management === */ + +/*! ZSTD_sizeof_*() : + * These functions give the _current_ memory usage of selected object. + * Note that object memory usage can evolve (increase or decrease) over time. */ +ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx); +ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx); +ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); +ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); +ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict); +ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); + +#endif /* ZSTD_H_235446 */ + + +/* ************************************************************************************** + * ADVANCED AND EXPERIMENTAL FUNCTIONS + **************************************************************************************** + * The definitions in the following section are considered experimental. + * They are provided for advanced scenarios. + * They should never be used with a dynamic library, as prototypes may change in the future. + * Use them only in association with static linking. + * ***************************************************************************************/ + +#if !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY) +#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY + +/* ************************************************************************************** + * experimental API (static linking only) + **************************************************************************************** + * The following symbols and constants + * are not planned to join "stable API" status in the near future. + * They can still change in future versions. + * Some of them are planned to remain in the static_only section indefinitely. + * Some of them might be removed in the future (especially when redundant with existing stable functions) + * ***************************************************************************************/ + +#define ZSTD_FRAMEHEADERSIZE_PREFIX(format) ((format) == ZSTD_f_zstd1 ? 5 : 1) /* minimum input size required to query frame header size */ +#define ZSTD_FRAMEHEADERSIZE_MIN(format) ((format) == ZSTD_f_zstd1 ? 6 : 2) +#define ZSTD_FRAMEHEADERSIZE_MAX 18 /* can be useful for static allocation */ +#define ZSTD_SKIPPABLEHEADERSIZE 8 + +/* compression parameter bounds */ +#define ZSTD_WINDOWLOG_MAX_32 30 +#define ZSTD_WINDOWLOG_MAX_64 31 +#define ZSTD_WINDOWLOG_MAX ((int)(sizeof(size_t) == 4 ? ZSTD_WINDOWLOG_MAX_32 : ZSTD_WINDOWLOG_MAX_64)) +#define ZSTD_WINDOWLOG_MIN 10 +#define ZSTD_HASHLOG_MAX ((ZSTD_WINDOWLOG_MAX < 30) ? ZSTD_WINDOWLOG_MAX : 30) +#define ZSTD_HASHLOG_MIN 6 +#define ZSTD_CHAINLOG_MAX_32 29 +#define ZSTD_CHAINLOG_MAX_64 30 +#define ZSTD_CHAINLOG_MAX ((int)(sizeof(size_t) == 4 ? ZSTD_CHAINLOG_MAX_32 : ZSTD_CHAINLOG_MAX_64)) +#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN +#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) +#define ZSTD_SEARCHLOG_MIN 1 +#define ZSTD_MINMATCH_MAX 7 /* only for ZSTD_fast, other strategies are limited to 6 */ +#define ZSTD_MINMATCH_MIN 3 /* only for ZSTD_btopt+, faster strategies are limited to 4 */ +#define ZSTD_TARGETLENGTH_MAX ZSTD_BLOCKSIZE_MAX +#define ZSTD_TARGETLENGTH_MIN 0 /* note : comparing this constant to an unsigned results in a tautological test */ +#define ZSTD_STRATEGY_MIN ZSTD_fast +#define ZSTD_STRATEGY_MAX ZSTD_btultra2 + + +#define ZSTD_OVERLAPLOG_MIN 0 +#define ZSTD_OVERLAPLOG_MAX 9 + +#define ZSTD_WINDOWLOG_LIMIT_DEFAULT 27 /* by default, the streaming decoder will refuse any frame + * requiring larger than (1< 0: + * If litLength != 0: + * rep == 1 --> offset == repeat_offset_1 + * rep == 2 --> offset == repeat_offset_2 + * rep == 3 --> offset == repeat_offset_3 + * If litLength == 0: + * rep == 1 --> offset == repeat_offset_2 + * rep == 2 --> offset == repeat_offset_3 + * rep == 3 --> offset == repeat_offset_1 - 1 + * + * Note: This field is optional. ZSTD_generateSequences() will calculate the value of + * 'rep', but repeat offsets do not necessarily need to be calculated from an external + * sequence provider's perspective. For example, ZSTD_compressSequences() does not + * use this 'rep' field at all (as of now). + */ +} ZSTD_Sequence; + +typedef struct { + unsigned windowLog; /*< largest match distance : larger == more compression, more memory needed during decompression */ + unsigned chainLog; /*< fully searched segment : larger == more compression, slower, more memory (useless for fast) */ + unsigned hashLog; /*< dispatch table : larger == faster, more memory */ + unsigned searchLog; /*< nb of searches : larger == more compression, slower */ + unsigned minMatch; /*< match length searched : larger == faster decompression, sometimes less compression */ + unsigned targetLength; /*< acceptable match size for optimal parser (only) : larger == more compression, slower */ + ZSTD_strategy strategy; /*< see ZSTD_strategy definition above */ +} ZSTD_compressionParameters; + +typedef struct { + int contentSizeFlag; /*< 1: content size will be in frame header (when known) */ + int checksumFlag; /*< 1: generate a 32-bits checksum using XXH64 algorithm at end of frame, for error detection */ + int noDictIDFlag; /*< 1: no dictID will be saved into frame header (dictID is only useful for dictionary compression) */ } ZSTD_frameParameters; -/** - * struct ZSTD_parameters - zstd parameters - * @cParams: The compression parameters. - * @fParams: The frame parameters. - */ typedef struct { - ZSTD_compressionParameters cParams; - ZSTD_frameParameters fParams; + ZSTD_compressionParameters cParams; + ZSTD_frameParameters fParams; } ZSTD_parameters; -/** - * ZSTD_getCParams() - returns ZSTD_compressionParameters for selected level - * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). - * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. - * @dictSize: The dictionary size or 0 if a dictionary isn't being used. - * - * Return: The selected ZSTD_compressionParameters. +typedef enum { + ZSTD_dct_auto = 0, /* dictionary is "full" when starting with ZSTD_MAGIC_DICTIONARY, otherwise it is "rawContent" */ + ZSTD_dct_rawContent = 1, /* ensures dictionary is always loaded as rawContent, even if it starts with ZSTD_MAGIC_DICTIONARY */ + ZSTD_dct_fullDict = 2 /* refuses to load a dictionary if it does not respect Zstandard's specification, starting with ZSTD_MAGIC_DICTIONARY */ +} ZSTD_dictContentType_e; + +typedef enum { + ZSTD_dlm_byCopy = 0, /*< Copy dictionary content internally */ + ZSTD_dlm_byRef = 1 /*< Reference dictionary content -- the dictionary buffer must outlive its users. */ +} ZSTD_dictLoadMethod_e; + +typedef enum { + ZSTD_f_zstd1 = 0, /* zstd frame format, specified in zstd_compression_format.md (default) */ + ZSTD_f_zstd1_magicless = 1 /* Variant of zstd frame format, without initial 4-bytes magic number. + * Useful to save 4 bytes per generated frame. + * Decoder cannot recognise automatically this format, requiring this instruction. */ +} ZSTD_format_e; + +typedef enum { + /* Note: this enum controls ZSTD_d_forceIgnoreChecksum */ + ZSTD_d_validateChecksum = 0, + ZSTD_d_ignoreChecksum = 1 +} ZSTD_forceIgnoreChecksum_e; + +typedef enum { + /* Note: this enum controls ZSTD_d_refMultipleDDicts */ + ZSTD_rmd_refSingleDDict = 0, + ZSTD_rmd_refMultipleDDicts = 1 +} ZSTD_refMultipleDDicts_e; + +typedef enum { + /* Note: this enum and the behavior it controls are effectively internal + * implementation details of the compressor. They are expected to continue + * to evolve and should be considered only in the context of extremely + * advanced performance tuning. + * + * Zstd currently supports the use of a CDict in three ways: + * + * - The contents of the CDict can be copied into the working context. This + * means that the compression can search both the dictionary and input + * while operating on a single set of internal tables. This makes + * the compression faster per-byte of input. However, the initial copy of + * the CDict's tables incurs a fixed cost at the beginning of the + * compression. For small compressions (< 8 KB), that copy can dominate + * the cost of the compression. + * + * - The CDict's tables can be used in-place. In this model, compression is + * slower per input byte, because the compressor has to search two sets of + * tables. However, this model incurs no start-up cost (as long as the + * working context's tables can be reused). For small inputs, this can be + * faster than copying the CDict's tables. + * + * - The CDict's tables are not used at all, and instead we use the working + * context alone to reload the dictionary and use params based on the source + * size. See ZSTD_compress_insertDictionary() and ZSTD_compress_usingDict(). + * This method is effective when the dictionary sizes are very small relative + * to the input size, and the input size is fairly large to begin with. + * + * Zstd has a simple internal heuristic that selects which strategy to use + * at the beginning of a compression. However, if experimentation shows that + * Zstd is making poor choices, it is possible to override that choice with + * this enum. + */ + ZSTD_dictDefaultAttach = 0, /* Use the default heuristic. */ + ZSTD_dictForceAttach = 1, /* Never copy the dictionary. */ + ZSTD_dictForceCopy = 2, /* Always copy the dictionary. */ + ZSTD_dictForceLoad = 3 /* Always reload the dictionary */ +} ZSTD_dictAttachPref_e; + +typedef enum { + ZSTD_lcm_auto = 0, /*< Automatically determine the compression mode based on the compression level. + * Negative compression levels will be uncompressed, and positive compression + * levels will be compressed. */ + ZSTD_lcm_huffman = 1, /*< Always attempt Huffman compression. Uncompressed literals will still be + * emitted if Huffman compression is not profitable. */ + ZSTD_lcm_uncompressed = 2 /*< Always emit uncompressed literals. */ +} ZSTD_literalCompressionMode_e; + + +/* ************************************* +* Frame size functions +***************************************/ + +/*! ZSTD_findDecompressedSize() : + * `src` should point to the start of a series of ZSTD encoded and/or skippable frames + * `srcSize` must be the _exact_ size of this series + * (i.e. there should be a frame boundary at `src + srcSize`) + * @return : - decompressed size of all data in all successive frames + * - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN + * - if an error occurred: ZSTD_CONTENTSIZE_ERROR + * + * note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode. + * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. + * In which case, it's necessary to use streaming mode to decompress data. + * note 2 : decompressed size is always present when compression is done with ZSTD_compress() + * note 3 : decompressed size can be very large (64-bits value), + * potentially larger than what local system can handle as a single memory segment. + * In which case, it's necessary to use streaming mode to decompress data. + * note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified. + * Always ensure result fits within application's authorized limits. + * Each application can set its own limits. + * note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to + * read each contained frame header. This is fast as most of the data is skipped, + * however it does mean that all frame data must be present and valid. */ +ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize); + +/*! ZSTD_decompressBound() : + * `src` should point to the start of a series of ZSTD encoded and/or skippable frames + * `srcSize` must be the _exact_ size of this series + * (i.e. there should be a frame boundary at `src + srcSize`) + * @return : - upper-bound for the decompressed size of all data in all successive frames + * - if an error occurred: ZSTD_CONTENTSIZE_ERROR + * + * note 1 : an error can occur if `src` contains an invalid or incorrectly formatted frame. + * note 2 : the upper-bound is exact when the decompressed size field is available in every ZSTD encoded frame of `src`. + * in this case, `ZSTD_findDecompressedSize` and `ZSTD_decompressBound` return the same value. + * note 3 : when the decompressed size field isn't available, the upper-bound for that frame is calculated by: + * upper-bound = # blocks * min(128 KB, Window_Size) */ -ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, - unsigned long long estimatedSrcSize, size_t dictSize); +ZSTDLIB_API unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize); -/** - * ZSTD_getParams() - returns ZSTD_parameters for selected level - * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). - * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. - * @dictSize: The dictionary size or 0 if a dictionary isn't being used. +/*! ZSTD_frameHeaderSize() : + * srcSize must be >= ZSTD_FRAMEHEADERSIZE_PREFIX. + * @return : size of the Frame Header, + * or an error code (if srcSize is too small) */ +ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize); + +typedef enum { + ZSTD_sf_noBlockDelimiters = 0, /* Representation of ZSTD_Sequence has no block delimiters, sequences only */ + ZSTD_sf_explicitBlockDelimiters = 1 /* Representation of ZSTD_Sequence contains explicit block delimiters */ +} ZSTD_sequenceFormat_e; + +/*! ZSTD_generateSequences() : + * Generate sequences using ZSTD_compress2, given a source buffer. + * + * Each block will end with a dummy sequence + * with offset == 0, matchLength == 0, and litLength == length of last literals. + * litLength may be == 0, and if so, then the sequence of (of: 0 ml: 0 ll: 0) + * simply acts as a block delimiter. * - * The same as ZSTD_getCParams() except also selects the default frame - * parameters (all zero). + * zc can be used to insert custom compression params. + * This function invokes ZSTD_compress2 * - * Return: The selected ZSTD_parameters. + * The output of this function can be fed into ZSTD_compressSequences() with CCtx + * setting of ZSTD_c_blockDelimiters as ZSTD_sf_explicitBlockDelimiters + * @return : number of sequences generated */ -ZSTD_parameters ZSTD_getParams(int compressionLevel, - unsigned long long estimatedSrcSize, size_t dictSize); -/*-************************************* - * Explicit memory management - **************************************/ +ZSTDLIB_API size_t ZSTD_generateSequences(ZSTD_CCtx* zc, ZSTD_Sequence* outSeqs, + size_t outSeqsSize, const void* src, size_t srcSize); -/** - * ZSTD_CCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_CCtx - * @cParams: The compression parameters to be used for compression. +/*! ZSTD_mergeBlockDelimiters() : + * Given an array of ZSTD_Sequence, remove all sequences that represent block delimiters/last literals + * by merging them into into the literals of the next sequence. * - * If multiple compression parameters might be used, the caller must call - * ZSTD_CCtxWorkspaceBound() for each set of parameters and use the maximum - * size. + * As such, the final generated result has no explicit representation of block boundaries, + * and the final last literals segment is not represented in the sequences. * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCCtx(). + * The output of this function can be fed into ZSTD_compressSequences() with CCtx + * setting of ZSTD_c_blockDelimiters as ZSTD_sf_noBlockDelimiters + * @return : number of sequences left after merging + */ +ZSTDLIB_API size_t ZSTD_mergeBlockDelimiters(ZSTD_Sequence* sequences, size_t seqsSize); + +/*! ZSTD_compressSequences() : + * Compress an array of ZSTD_Sequence, generated from the original source buffer, into dst. + * If a dictionary is included, then the cctx should reference the dict. (see: ZSTD_CCtx_refCDict(), ZSTD_CCtx_loadDictionary(), etc.) + * The entire source is compressed into a single frame. + * + * The compression behavior changes based on cctx params. In particular: + * If ZSTD_c_blockDelimiters == ZSTD_sf_noBlockDelimiters, the array of ZSTD_Sequence is expected to contain + * no block delimiters (defined in ZSTD_Sequence). Block boundaries are roughly determined based on + * the block size derived from the cctx, and sequences may be split. This is the default setting. + * + * If ZSTD_c_blockDelimiters == ZSTD_sf_explicitBlockDelimiters, the array of ZSTD_Sequence is expected to contain + * block delimiters (defined in ZSTD_Sequence). Behavior is undefined if no block delimiters are provided. + * + * If ZSTD_c_validateSequences == 0, this function will blindly accept the sequences provided. Invalid sequences cause undefined + * behavior. If ZSTD_c_validateSequences == 1, then if sequence is invalid (see doc/zstd_compression_format.md for + * specifics regarding offset/matchlength requirements) then the function will bail out and return an error. + * + * In addition to the two adjustable experimental params, there are other important cctx params. + * - ZSTD_c_minMatch MUST be set as less than or equal to the smallest match generated by the match finder. It has a minimum value of ZSTD_MINMATCH_MIN. + * - ZSTD_c_compressionLevel accordingly adjusts the strength of the entropy coder, as it would in typical compression. + * - ZSTD_c_windowLog affects offset validation: this function will return an error at higher debug levels if a provided offset + * is larger than what the spec allows for a given window log and dictionary (if present). See: doc/zstd_compression_format.md + * + * Note: Repcodes are, as of now, always re-calculated within this function, so ZSTD_Sequence::rep is unused. + * Note 2: Once we integrate ability to ingest repcodes, the explicit block delims mode must respect those repcodes exactly, + * and cannot emit an RLE block that disagrees with the repcode history + * @return : final compressed size or a ZSTD error. */ -size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams); +ZSTDLIB_API size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* dst, size_t dstSize, + const ZSTD_Sequence* inSeqs, size_t inSeqsSize, + const void* src, size_t srcSize); -/** - * struct ZSTD_CCtx - the zstd compression context + +/*! ZSTD_writeSkippableFrame() : + * Generates a zstd skippable frame containing data given by src, and writes it to dst buffer. * - * When compressing many times it is recommended to allocate a context just once - * and reuse it for each successive compression operation. - */ -typedef struct ZSTD_CCtx_s ZSTD_CCtx; -/** - * ZSTD_initCCtx() - initialize a zstd compression context - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Use ZSTD_CCtxWorkspaceBound() to - * determine how large the workspace must be. + * Skippable frames begin with a a 4-byte magic number. There are 16 possible choices of magic number, + * ranging from ZSTD_MAGIC_SKIPPABLE_START to ZSTD_MAGIC_SKIPPABLE_START+15. + * As such, the parameter magicVariant controls the exact skippable frame magic number variant used, so + * the magic number used will be ZSTD_MAGIC_SKIPPABLE_START + magicVariant. * - * Return: A compression context emplaced into workspace. - */ -ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize); - -/** - * ZSTD_compressCCtx() - compress src into dst - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @params: The parameters to use for compression. See ZSTD_getParams(). + * Returns an error if destination buffer is not large enough, if the source size is not representable + * with a 4-byte unsigned int, or if the parameter magicVariant is greater than 15 (and therefore invalid). * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). + * @return : number of bytes written or a ZSTD error. */ -size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, ZSTD_parameters params); - -/** - * ZSTD_DCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_DCtx - * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDCtx(). +ZSTDLIB_API size_t ZSTD_writeSkippableFrame(void* dst, size_t dstCapacity, + const void* src, size_t srcSize, unsigned magicVariant); + + +/* ************************************* +* Memory management +***************************************/ + +/*! ZSTD_estimate*() : + * These functions make it possible to estimate memory usage + * of a future {D,C}Ctx, before its creation. + * + * ZSTD_estimateCCtxSize() will provide a memory budget large enough + * for any compression level up to selected one. + * Note : Unlike ZSTD_estimateCStreamSize*(), this estimate + * does not include space for a window buffer. + * Therefore, the estimation is only guaranteed for single-shot compressions, not streaming. + * The estimate will assume the input may be arbitrarily large, + * which is the worst case. + * + * When srcSize can be bound by a known and rather "small" value, + * this fact can be used to provide a tighter estimation + * because the CCtx compression context will need less memory. + * This tighter estimation can be provided by more advanced functions + * ZSTD_estimateCCtxSize_usingCParams(), which can be used in tandem with ZSTD_getCParams(), + * and ZSTD_estimateCCtxSize_usingCCtxParams(), which can be used in tandem with ZSTD_CCtxParams_setParameter(). + * Both can be used to estimate memory using custom compression parameters and arbitrary srcSize limits. + * + * Note 2 : only single-threaded compression is supported. + * ZSTD_estimateCCtxSize_usingCCtxParams() will return an error code if ZSTD_c_nbWorkers is >= 1. + */ +ZSTDLIB_API size_t ZSTD_estimateCCtxSize(int compressionLevel); +ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams); +ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params); +ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void); + +/*! ZSTD_estimateCStreamSize() : + * ZSTD_estimateCStreamSize() will provide a budget large enough for any compression level up to selected one. + * It will also consider src size to be arbitrarily "large", which is worst case. + * If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation. + * ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. + * ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. + * Note : CStream size estimation is only correct for single-threaded compression. + * ZSTD_DStream memory budget depends on window Size. + * This information can be passed manually, using ZSTD_estimateDStreamSize, + * or deducted from a valid frame Header, using ZSTD_estimateDStreamSize_fromFrame(); + * Note : if streaming is init with function ZSTD_init?Stream_usingDict(), + * an internal ?Dict will be created, which additional size is not estimated here. + * In this case, get total size by adding ZSTD_estimate?DictSize */ +ZSTDLIB_API size_t ZSTD_estimateCStreamSize(int compressionLevel); +ZSTDLIB_API size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams); +ZSTDLIB_API size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params); +ZSTDLIB_API size_t ZSTD_estimateDStreamSize(size_t windowSize); +ZSTDLIB_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize); + +/*! ZSTD_estimate?DictSize() : + * ZSTD_estimateCDictSize() will bet that src size is relatively "small", and content is copied, like ZSTD_createCDict(). + * ZSTD_estimateCDictSize_advanced() makes it possible to control compression parameters precisely, like ZSTD_createCDict_advanced(). + * Note : dictionaries created by reference (`ZSTD_dlm_byRef`) are logically smaller. + */ +ZSTDLIB_API size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel); +ZSTDLIB_API size_t ZSTD_estimateCDictSize_advanced(size_t dictSize, ZSTD_compressionParameters cParams, ZSTD_dictLoadMethod_e dictLoadMethod); +ZSTDLIB_API size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod); + +/*! ZSTD_initStatic*() : + * Initialize an object using a pre-allocated fixed-size buffer. + * workspace: The memory area to emplace the object into. + * Provided pointer *must be 8-bytes aligned*. + * Buffer must outlive object. + * workspaceSize: Use ZSTD_estimate*Size() to determine + * how large workspace must be to support target scenario. + * @return : pointer to object (same address as workspace, just different type), + * or NULL if error (size too small, incorrect alignment, etc.) + * Note : zstd will never resize nor malloc() when using a static buffer. + * If the object requires more memory than available, + * zstd will just error out (typically ZSTD_error_memory_allocation). + * Note 2 : there is no corresponding "free" function. + * Since workspace is allocated externally, it must be freed externally too. + * Note 3 : cParams : use ZSTD_getCParams() to convert a compression level + * into its associated cParams. + * Limitation 1 : currently not compatible with internal dictionary creation, triggered by + * ZSTD_CCtx_loadDictionary(), ZSTD_initCStream_usingDict() or ZSTD_initDStream_usingDict(). + * Limitation 2 : static cctx currently not compatible with multi-threading. + * Limitation 3 : static dctx is incompatible with legacy support. */ -size_t ZSTD_DCtxWorkspaceBound(void); +ZSTDLIB_API ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize); +ZSTDLIB_API ZSTD_CStream* ZSTD_initStaticCStream(void* workspace, size_t workspaceSize); /*< same as ZSTD_initStaticCCtx() */ + +ZSTDLIB_API ZSTD_DCtx* ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize); +ZSTDLIB_API ZSTD_DStream* ZSTD_initStaticDStream(void* workspace, size_t workspaceSize); /*< same as ZSTD_initStaticDCtx() */ + +ZSTDLIB_API const ZSTD_CDict* ZSTD_initStaticCDict( + void* workspace, size_t workspaceSize, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_compressionParameters cParams); + +ZSTDLIB_API const ZSTD_DDict* ZSTD_initStaticDDict( + void* workspace, size_t workspaceSize, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType); + + +/*! Custom memory allocation : + * These prototypes make it possible to pass your own allocation/free functions. + * ZSTD_customMem is provided at creation time, using ZSTD_create*_advanced() variants listed below. + * All allocation/free operations will be completed using these custom variants instead of regular ones. + */ +typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size); +typedef void (*ZSTD_freeFunction) (void* opaque, void* address); +typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem; +static +__attribute__((__unused__)) +ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL }; /*< this constant defers to stdlib's functions */ + +ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem); +ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem); +ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem); +ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem); + +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_compressionParameters cParams, + ZSTD_customMem customMem); + +/* ! Thread pool : + * These prototypes make it possible to share a thread pool among multiple compression contexts. + * This can limit resources for applications with multiple threads where each one uses + * a threaded compression mode (via ZSTD_c_nbWorkers parameter). + * ZSTD_createThreadPool creates a new thread pool with a given number of threads. + * Note that the lifetime of such pool must exist while being used. + * ZSTD_CCtx_refThreadPool assigns a thread pool to a context (use NULL argument value + * to use an internal thread pool). + * ZSTD_freeThreadPool frees a thread pool, accepts NULL pointer. + */ +typedef struct POOL_ctx_s ZSTD_threadPool; +ZSTDLIB_API ZSTD_threadPool* ZSTD_createThreadPool(size_t numThreads); +ZSTDLIB_API void ZSTD_freeThreadPool (ZSTD_threadPool* pool); /* accept NULL pointer */ +ZSTDLIB_API size_t ZSTD_CCtx_refThreadPool(ZSTD_CCtx* cctx, ZSTD_threadPool* pool); -/** - * struct ZSTD_DCtx - the zstd decompression context - * - * When decompressing many times it is recommended to allocate a context just - * once and reuse it for each successive decompression operation. + +/* + * This API is temporary and is expected to change or disappear in the future! */ -typedef struct ZSTD_DCtx_s ZSTD_DCtx; -/** - * ZSTD_initDCtx() - initialize a zstd decompression context - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Use ZSTD_DCtxWorkspaceBound() to - * determine how large the workspace must be. - * - * Return: A decompression context emplaced into workspace. - */ -ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize); - -/** - * ZSTD_decompressDCtx() - decompress zstd compressed src into dst - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_decompressDCtx(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); - -/*-************************ - * Simple dictionary API - **************************/ - -/** - * ZSTD_compress_usingDict() - compress src into dst using a dictionary - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @dict: The dictionary to use for compression. - * @dictSize: The size of the dictionary. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * - * Compression using a predefined dictionary. The same dictionary must be used - * during decompression. - * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const void *dict, size_t dictSize, - ZSTD_parameters params); - -/** - * ZSTD_decompress_usingDict() - decompress src into dst using a dictionary - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * @dict: The dictionary to use for decompression. The same dictionary - * must've been used to compress the data. - * @dictSize: The size of the dictionary. - * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_decompress_usingDict(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const void *dict, size_t dictSize); - -/*-************************** - * Fast dictionary API - ***************************/ - -/** - * ZSTD_CDictWorkspaceBound() - memory needed to initialize a ZSTD_CDict - * @cParams: The compression parameters to be used for compression. - * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCDict(). - */ -size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams); - -/** - * struct ZSTD_CDict - a digested dictionary to be used for compression +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced2( + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + const ZSTD_CCtx_params* cctxParams, + ZSTD_customMem customMem); + +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced( + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_customMem customMem); + + +/* ************************************* +* Advanced compression functions +***************************************/ + +/*! ZSTD_createCDict_byReference() : + * Create a digested dictionary for compression + * Dictionary content is just referenced, not duplicated. + * As a consequence, `dictBuffer` **must** outlive CDict, + * and its content must remain unmodified throughout the lifetime of CDict. + * note: equivalent to ZSTD_createCDict_advanced(), with dictLoadMethod==ZSTD_dlm_byRef */ +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel); + +/*! ZSTD_getDictID_fromCDict() : + * Provides the dictID of the dictionary loaded into `cdict`. + * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. + * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromCDict(const ZSTD_CDict* cdict); + +/*! ZSTD_getCParams() : + * @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize. + * `estimatedSrcSize` value is optional, select 0 if not known */ +ZSTDLIB_API ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize); + +/*! ZSTD_getParams() : + * same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`. + * All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 */ +ZSTDLIB_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize); + +/*! ZSTD_checkCParams() : + * Ensure param values remain within authorized range. + * @return 0 on success, or an error code (can be checked with ZSTD_isError()) */ +ZSTDLIB_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params); + +/*! ZSTD_adjustCParams() : + * optimize params for a given `srcSize` and `dictSize`. + * `srcSize` can be unknown, in which case use ZSTD_CONTENTSIZE_UNKNOWN. + * `dictSize` must be `0` when there is no dictionary. + * cPar can be invalid : all parameters will be clamped within valid range in the @return struct. + * This function never fails (wide contract) */ +ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize); + +/*! ZSTD_compress_advanced() : + * Note : this function is now DEPRECATED. + * It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_setParameter() and other parameter setters. + * This prototype will be marked as deprecated and generate compilation warning on reaching v1.5.x */ +ZSTDLIB_API size_t ZSTD_compress_advanced(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + ZSTD_parameters params); + +/*! ZSTD_compress_usingCDict_advanced() : + * Note : this function is now REDUNDANT. + * It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_loadDictionary() and other parameter setters. + * This prototype will be marked as deprecated and generate compilation warning in some future version */ +ZSTDLIB_API size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict, + ZSTD_frameParameters fParams); + + +/*! ZSTD_CCtx_loadDictionary_byReference() : + * Same as ZSTD_CCtx_loadDictionary(), but dictionary content is referenced, instead of being copied into CCtx. + * It saves some memory, but also requires that `dict` outlives its usage within `cctx` */ +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_byReference(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); + +/*! ZSTD_CCtx_loadDictionary_advanced() : + * Same as ZSTD_CCtx_loadDictionary(), but gives finer control over + * how to load the dictionary (by copy ? by reference ?) + * and how to interpret it (automatic ? force raw mode ? full mode only ?) */ +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType); + +/*! ZSTD_CCtx_refPrefix_advanced() : + * Same as ZSTD_CCtx_refPrefix(), but gives finer control over + * how to interpret prefix content (automatic ? force raw mode (default) ? full mode only ?) */ +ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType); + +/* === experimental parameters === */ +/* these parameters can be used with ZSTD_setParameter() + * they are not guaranteed to remain supported in the future */ + + /* Enables rsyncable mode, + * which makes compressed files more rsync friendly + * by adding periodic synchronization points to the compressed data. + * The target average block size is ZSTD_c_jobSize / 2. + * It's possible to modify the job size to increase or decrease + * the granularity of the synchronization point. + * Once the jobSize is smaller than the window size, + * it will result in compression ratio degradation. + * NOTE 1: rsyncable mode only works when multithreading is enabled. + * NOTE 2: rsyncable performs poorly in combination with long range mode, + * since it will decrease the effectiveness of synchronization points, + * though mileage may vary. + * NOTE 3: Rsyncable mode limits maximum compression speed to ~400 MB/s. + * If the selected compression level is already running significantly slower, + * the overall speed won't be significantly impacted. + */ + #define ZSTD_c_rsyncable ZSTD_c_experimentalParam1 + +/* Select a compression format. + * The value must be of type ZSTD_format_e. + * See ZSTD_format_e enum definition for details */ +#define ZSTD_c_format ZSTD_c_experimentalParam2 + +/* Force back-reference distances to remain < windowSize, + * even when referencing into Dictionary content (default:0) */ +#define ZSTD_c_forceMaxWindow ZSTD_c_experimentalParam3 + +/* Controls whether the contents of a CDict + * are used in place, or copied into the working context. + * Accepts values from the ZSTD_dictAttachPref_e enum. + * See the comments on that enum for an explanation of the feature. */ +#define ZSTD_c_forceAttachDict ZSTD_c_experimentalParam4 + +/* Controls how the literals are compressed (default is auto). + * The value must be of type ZSTD_literalCompressionMode_e. + * See ZSTD_literalCompressionMode_t enum definition for details. */ -typedef struct ZSTD_CDict_s ZSTD_CDict; +#define ZSTD_c_literalCompressionMode ZSTD_c_experimentalParam5 + +/* Tries to fit compressed block size to be around targetCBlockSize. + * No target when targetCBlockSize == 0. + * There is no guarantee on compressed block size (default:0) */ +#define ZSTD_c_targetCBlockSize ZSTD_c_experimentalParam6 + +/* User's best guess of source size. + * Hint is not valid when srcSizeHint == 0. + * There is no guarantee that hint is close to actual source size, + * but compression ratio may regress significantly if guess considerably underestimates */ +#define ZSTD_c_srcSizeHint ZSTD_c_experimentalParam7 + +/* Controls whether the new and experimental "dedicated dictionary search + * structure" can be used. This feature is still rough around the edges, be + * prepared for surprising behavior! + * + * How to use it: + * + * When using a CDict, whether to use this feature or not is controlled at + * CDict creation, and it must be set in a CCtxParams set passed into that + * construction (via ZSTD_createCDict_advanced2()). A compression will then + * use the feature or not based on how the CDict was constructed; the value of + * this param, set in the CCtx, will have no effect. + * + * However, when a dictionary buffer is passed into a CCtx, such as via + * ZSTD_CCtx_loadDictionary(), this param can be set on the CCtx to control + * whether the CDict that is created internally can use the feature or not. + * + * What it does: + * + * Normally, the internal data structures of the CDict are analogous to what + * would be stored in a CCtx after compressing the contents of a dictionary. + * To an approximation, a compression using a dictionary can then use those + * data structures to simply continue what is effectively a streaming + * compression where the simulated compression of the dictionary left off. + * Which is to say, the search structures in the CDict are normally the same + * format as in the CCtx. + * + * It is possible to do better, since the CDict is not like a CCtx: the search + * structures are written once during CDict creation, and then are only read + * after that, while the search structures in the CCtx are both read and + * written as the compression goes along. This means we can choose a search + * structure for the dictionary that is read-optimized. + * + * This feature enables the use of that different structure. + * + * Note that some of the members of the ZSTD_compressionParameters struct have + * different semantics and constraints in the dedicated search structure. It is + * highly recommended that you simply set a compression level in the CCtxParams + * you pass into the CDict creation call, and avoid messing with the cParams + * directly. + * + * Effects: + * + * This will only have any effect when the selected ZSTD_strategy + * implementation supports this feature. Currently, that's limited to + * ZSTD_greedy, ZSTD_lazy, and ZSTD_lazy2. + * + * Note that this means that the CDict tables can no longer be copied into the + * CCtx, so the dict attachment mode ZSTD_dictForceCopy will no longer be + * useable. The dictionary can only be attached or reloaded. + * + * In general, you should expect compression to be faster--sometimes very much + * so--and CDict creation to be slightly slower. Eventually, we will probably + * make this mode the default. + */ +#define ZSTD_c_enableDedicatedDictSearch ZSTD_c_experimentalParam8 + +/* ZSTD_c_stableInBuffer + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable. + * + * Tells the compressor that the ZSTD_inBuffer will ALWAYS be the same + * between calls, except for the modifications that zstd makes to pos (the + * caller must not modify pos). This is checked by the compressor, and + * compression will fail if it ever changes. This means the only flush + * mode that makes sense is ZSTD_e_end, so zstd will error if ZSTD_e_end + * is not used. The data in the ZSTD_inBuffer in the range [src, src + pos) + * MUST not be modified during compression or you will get data corruption. + * + * When this flag is enabled zstd won't allocate an input window buffer, + * because the user guarantees it can reference the ZSTD_inBuffer until + * the frame is complete. But, it will still allocate an output buffer + * large enough to fit a block (see ZSTD_c_stableOutBuffer). This will also + * avoid the memcpy() from the input buffer to the input window buffer. + * + * NOTE: ZSTD_compressStream2() will error if ZSTD_e_end is not used. + * That means this flag cannot be used with ZSTD_compressStream(). + * + * NOTE: So long as the ZSTD_inBuffer always points to valid memory, using + * this flag is ALWAYS memory safe, and will never access out-of-bounds + * memory. However, compression WILL fail if you violate the preconditions. + * + * WARNING: The data in the ZSTD_inBuffer in the range [dst, dst + pos) MUST + * not be modified during compression or you will get data corruption. This + * is because zstd needs to reference data in the ZSTD_inBuffer to find + * matches. Normally zstd maintains its own window buffer for this purpose, + * but passing this flag tells zstd to use the user provided buffer. + */ +#define ZSTD_c_stableInBuffer ZSTD_c_experimentalParam9 -/** - * ZSTD_initCDict() - initialize a digested dictionary for compression - * @dictBuffer: The dictionary to digest. The buffer is referenced by the - * ZSTD_CDict so it must outlive the returned ZSTD_CDict. - * @dictSize: The size of the dictionary. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * @workspace: The workspace. It must outlive the returned ZSTD_CDict. - * @workspaceSize: The workspace size. Must be at least - * ZSTD_CDictWorkspaceBound(params.cParams). +/* ZSTD_c_stableOutBuffer + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable. * - * When compressing multiple messages / blocks with the same dictionary it is - * recommended to load it just once. The ZSTD_CDict merely references the - * dictBuffer, so it must outlive the returned ZSTD_CDict. + * Tells he compressor that the ZSTD_outBuffer will not be resized between + * calls. Specifically: (out.size - out.pos) will never grow. This gives the + * compressor the freedom to say: If the compressed data doesn't fit in the + * output buffer then return ZSTD_error_dstSizeTooSmall. This allows us to + * always decompress directly into the output buffer, instead of decompressing + * into an internal buffer and copying to the output buffer. * - * Return: The digested dictionary emplaced into workspace. + * When this flag is enabled zstd won't allocate an output buffer, because + * it can write directly to the ZSTD_outBuffer. It will still allocate the + * input window buffer (see ZSTD_c_stableInBuffer). + * + * Zstd will check that (out.size - out.pos) never grows and return an error + * if it does. While not strictly necessary, this should prevent surprises. */ -ZSTD_CDict *ZSTD_initCDict(const void *dictBuffer, size_t dictSize, - ZSTD_parameters params, void *workspace, size_t workspaceSize); +#define ZSTD_c_stableOutBuffer ZSTD_c_experimentalParam10 -/** - * ZSTD_compress_usingCDict() - compress src into dst using a ZSTD_CDict - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(cParams) where - * cParams are the compression parameters used to initialize the - * cdict. - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @cdict: The digested dictionary to use for compression. - * @params: The parameters to use for compression. See ZSTD_getParams(). +/* ZSTD_c_blockDelimiters + * Default is 0 == ZSTD_sf_noBlockDelimiters. * - * Compression using a digested dictionary. The same dictionary must be used - * during decompression. + * For use with sequence compression API: ZSTD_compressSequences(). * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). + * Designates whether or not the given array of ZSTD_Sequence contains block delimiters + * and last literals, which are defined as sequences with offset == 0 and matchLength == 0. + * See the definition of ZSTD_Sequence for more specifics. */ -size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const ZSTD_CDict *cdict); - +#define ZSTD_c_blockDelimiters ZSTD_c_experimentalParam11 -/** - * ZSTD_DDictWorkspaceBound() - memory needed to initialize a ZSTD_DDict +/* ZSTD_c_validateSequences + * Default is 0 == disabled. Set to 1 to enable sequence validation. + * + * For use with sequence compression API: ZSTD_compressSequences(). + * Designates whether or not we validate sequences provided to ZSTD_compressSequences() + * during function execution. + * + * Without validation, providing a sequence that does not conform to the zstd spec will cause + * undefined behavior, and may produce a corrupted block. + * + * With validation enabled, a if sequence is invalid (see doc/zstd_compression_format.md for + * specifics regarding offset/matchlength requirements) then the function will bail out and + * return an error. * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDDict(). */ -size_t ZSTD_DDictWorkspaceBound(void); +#define ZSTD_c_validateSequences ZSTD_c_experimentalParam12 -/** - * struct ZSTD_DDict - a digested dictionary to be used for decompression +/*! ZSTD_CCtx_getParameter() : + * Get the requested compression parameter value, selected by enum ZSTD_cParameter, + * and store it into int* value. + * @return : 0, or an error code (which can be tested with ZSTD_isError()). */ -typedef struct ZSTD_DDict_s ZSTD_DDict; - -/** - * ZSTD_initDDict() - initialize a digested dictionary for decompression - * @dictBuffer: The dictionary to digest. The buffer is referenced by the - * ZSTD_DDict so it must outlive the returned ZSTD_DDict. - * @dictSize: The size of the dictionary. - * @workspace: The workspace. It must outlive the returned ZSTD_DDict. - * @workspaceSize: The workspace size. Must be at least - * ZSTD_DDictWorkspaceBound(). - * - * When decompressing multiple messages / blocks with the same dictionary it is - * recommended to load it just once. The ZSTD_DDict merely references the - * dictBuffer, so it must outlive the returned ZSTD_DDict. - * - * Return: The digested dictionary emplaced into workspace. - */ -ZSTD_DDict *ZSTD_initDDict(const void *dictBuffer, size_t dictSize, - void *workspace, size_t workspaceSize); - -/** - * ZSTD_decompress_usingDDict() - decompress src into dst using a ZSTD_DDict - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * @ddict: The digested dictionary to use for decompression. The same - * dictionary must've been used to compress the data. - * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, - size_t dstCapacity, const void *src, size_t srcSize, - const ZSTD_DDict *ddict); - - -/*-************************** - * Streaming - ***************************/ - -/** - * struct ZSTD_inBuffer - input buffer for streaming - * @src: Start of the input buffer. - * @size: Size of the input buffer. - * @pos: Position where reading stopped. Will be updated. - * Necessarily 0 <= pos <= size. +ZSTDLIB_API size_t ZSTD_CCtx_getParameter(const ZSTD_CCtx* cctx, ZSTD_cParameter param, int* value); + + +/*! ZSTD_CCtx_params : + * Quick howto : + * - ZSTD_createCCtxParams() : Create a ZSTD_CCtx_params structure + * - ZSTD_CCtxParams_setParameter() : Push parameters one by one into + * an existing ZSTD_CCtx_params structure. + * This is similar to + * ZSTD_CCtx_setParameter(). + * - ZSTD_CCtx_setParametersUsingCCtxParams() : Apply parameters to + * an existing CCtx. + * These parameters will be applied to + * all subsequent frames. + * - ZSTD_compressStream2() : Do compression using the CCtx. + * - ZSTD_freeCCtxParams() : Free the memory, accept NULL pointer. + * + * This can be used with ZSTD_estimateCCtxSize_advanced_usingCCtxParams() + * for static allocation of CCtx for single-threaded compression. */ -typedef struct ZSTD_inBuffer_s { - const void *src; - size_t size; - size_t pos; -} ZSTD_inBuffer; +ZSTDLIB_API ZSTD_CCtx_params* ZSTD_createCCtxParams(void); +ZSTDLIB_API size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params); /* accept NULL pointer */ -/** - * struct ZSTD_outBuffer - output buffer for streaming - * @dst: Start of the output buffer. - * @size: Size of the output buffer. - * @pos: Position where writing stopped. Will be updated. - * Necessarily 0 <= pos <= size. +/*! ZSTD_CCtxParams_reset() : + * Reset params to default values. */ -typedef struct ZSTD_outBuffer_s { - void *dst; - size_t size; - size_t pos; -} ZSTD_outBuffer; - - +ZSTDLIB_API size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params); -/*-***************************************************************************** - * Streaming compression - HowTo - * - * A ZSTD_CStream object is required to track streaming operation. - * Use ZSTD_initCStream() to initialize a ZSTD_CStream object. - * ZSTD_CStream objects can be reused multiple times on consecutive compression - * operations. It is recommended to re-use ZSTD_CStream in situations where many - * streaming operations will be achieved consecutively. Use one separate - * ZSTD_CStream per thread for parallel execution. - * - * Use ZSTD_compressStream() repetitively to consume input stream. - * The function will automatically update both `pos` fields. - * Note that it may not consume the entire input, in which case `pos < size`, - * and it's up to the caller to present again remaining data. - * It returns a hint for the preferred number of bytes to use as an input for - * the next function call. - * - * At any moment, it's possible to flush whatever data remains within internal - * buffer, using ZSTD_flushStream(). `output->pos` will be updated. There might - * still be some content left within the internal buffer if `output->size` is - * too small. It returns the number of bytes left in the internal buffer and - * must be called until it returns 0. - * - * ZSTD_endStream() instructs to finish a frame. It will perform a flush and - * write frame epilogue. The epilogue is required for decoders to consider a - * frame completed. Similar to ZSTD_flushStream(), it may not be able to flush - * the full content if `output->size` is too small. In which case, call again - * ZSTD_endStream() to complete the flush. It returns the number of bytes left - * in the internal buffer and must be called until it returns 0. - ******************************************************************************/ +/*! ZSTD_CCtxParams_init() : + * Initializes the compression parameters of cctxParams according to + * compression level. All other parameters are reset to their default values. + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel); -/** - * ZSTD_CStreamWorkspaceBound() - memory needed to initialize a ZSTD_CStream - * @cParams: The compression parameters to be used for compression. - * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCStream() and ZSTD_initCStream_usingCDict(). +/*! ZSTD_CCtxParams_init_advanced() : + * Initializes the compression and frame parameters of cctxParams according to + * params. All other parameters are reset to their default values. */ -size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams); +ZSTDLIB_API size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params); + +/*! ZSTD_CCtxParams_setParameter() : + * Similar to ZSTD_CCtx_setParameter. + * Set one compression parameter, selected by enum ZSTD_cParameter. + * Parameters must be applied to a ZSTD_CCtx using + * ZSTD_CCtx_setParametersUsingCCtxParams(). + * @result : a code representing success or failure (which can be tested with + * ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value); -/** - * struct ZSTD_CStream - the zstd streaming compression context +/*! ZSTD_CCtxParams_getParameter() : + * Similar to ZSTD_CCtx_getParameter. + * Get the requested value of one compression parameter, selected by enum ZSTD_cParameter. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_getParameter(const ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value); + +/*! ZSTD_CCtx_setParametersUsingCCtxParams() : + * Apply a set of ZSTD_CCtx_params to the compression context. + * This can be done even after compression is started, + * if nbWorkers==0, this will have no impact until a new compression is started. + * if nbWorkers>=1, new parameters will be picked up at next job, + * with a few restrictions (windowLog, pledgedSrcSize, nbWorkers, jobSize, and overlapLog are not updated). + */ +ZSTDLIB_API size_t ZSTD_CCtx_setParametersUsingCCtxParams( + ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params); + +/*! ZSTD_compressStream2_simpleArgs() : + * Same as ZSTD_compressStream2(), + * but using only integral types as arguments. + * This variant might be helpful for binders from dynamic languages + * which have troubles handling structures containing memory pointers. */ -typedef struct ZSTD_CStream_s ZSTD_CStream; +ZSTDLIB_API size_t ZSTD_compressStream2_simpleArgs ( + ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos, + ZSTD_EndDirective endOp); + + +/* ************************************* +* Advanced decompression functions +***************************************/ + +/*! ZSTD_isFrame() : + * Tells if the content of `buffer` starts with a valid Frame Identifier. + * Note : Frame Identifier is 4 bytes. If `size < 4`, @return will always be 0. + * Note 2 : Legacy Frame Identifiers are considered valid only if Legacy Support is enabled. + * Note 3 : Skippable Frame Identifiers are considered valid. */ +ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size); + +/*! ZSTD_createDDict_byReference() : + * Create a digested dictionary, ready to start decompression operation without startup delay. + * Dictionary content is referenced, and therefore stays in dictBuffer. + * It is important that dictBuffer outlives DDict, + * it must remain read accessible throughout the lifetime of DDict */ +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize); + +/*! ZSTD_DCtx_loadDictionary_byReference() : + * Same as ZSTD_DCtx_loadDictionary(), + * but references `dict` content instead of copying it into `dctx`. + * This saves memory if `dict` remains around., + * However, it's imperative that `dict` remains accessible (and unmodified) while being used, so it must outlive decompression. */ +ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary_byReference(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); + +/*! ZSTD_DCtx_loadDictionary_advanced() : + * Same as ZSTD_DCtx_loadDictionary(), + * but gives direct control over + * how to load the dictionary (by copy ? by reference ?) + * and how to interpret it (automatic ? force raw mode ? full mode only ?). */ +ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType); + +/*! ZSTD_DCtx_refPrefix_advanced() : + * Same as ZSTD_DCtx_refPrefix(), but gives finer control over + * how to interpret prefix content (automatic ? force raw mode (default) ? full mode only ?) */ +ZSTDLIB_API size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType); + +/*! ZSTD_DCtx_setMaxWindowSize() : + * Refuses allocating internal buffers for frames requiring a window size larger than provided limit. + * This protects a decoder context from reserving too much memory for itself (potential attack scenario). + * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode. + * By default, a decompression context accepts all window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) + * @return : 0, or an error code (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize); -/*===== ZSTD_CStream management functions =====*/ -/** - * ZSTD_initCStream() - initialize a zstd streaming compression context - * @params: The zstd compression parameters. - * @pledgedSrcSize: If params.fParams.contentSizeFlag == 1 then the caller must - * pass the source size (zero means empty source). Otherwise, - * the caller may optionally pass the source size, or zero if - * unknown. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_CStreamWorkspaceBound(params.cParams) to determine - * how large the workspace must be. - * - * Return: The zstd streaming compression context. - */ -ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, - unsigned long long pledgedSrcSize, void *workspace, - size_t workspaceSize); - -/** - * ZSTD_initCStream_usingCDict() - initialize a streaming compression context - * @cdict: The digested dictionary to use for compression. - * @pledgedSrcSize: Optionally the source size, or zero if unknown. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Call ZSTD_CStreamWorkspaceBound() - * with the cParams used to initialize the cdict to determine - * how large the workspace must be. - * - * Return: The zstd streaming compression context. - */ -ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, - unsigned long long pledgedSrcSize, void *workspace, - size_t workspaceSize); +/*! ZSTD_DCtx_getParameter() : + * Get the requested decompression parameter value, selected by enum ZSTD_dParameter, + * and store it into int* value. + * @return : 0, or an error code (which can be tested with ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int* value); -/*===== Streaming compression functions =====*/ -/** - * ZSTD_resetCStream() - reset the context using parameters from creation - * @zcs: The zstd streaming compression context to reset. - * @pledgedSrcSize: Optionally the source size, or zero if unknown. - * - * Resets the context using the parameters from creation. Skips dictionary - * loading, since it can be reused. If `pledgedSrcSize` is non-zero the frame - * content size is always written into the frame header. - * - * Return: Zero or an error, which can be checked using ZSTD_isError(). +/* ZSTD_d_format + * experimental parameter, + * allowing selection between ZSTD_format_e input compression formats */ -size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize); -/** - * ZSTD_compressStream() - streaming compress some of input into output - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. - * @input: Source buffer. `input->pos` is updated to indicate how much data was - * read. Note that it may not consume the entire input, in which case - * `input->pos < input->size`, and it's up to the caller to present - * remaining data again. - * - * The `input` and `output` buffers may be any size. Guaranteed to make some - * forward progress if `input` and `output` are not empty. - * - * Return: A hint for the number of bytes to use as the input for the next - * function call or an error, which can be checked using - * ZSTD_isError(). +#define ZSTD_d_format ZSTD_d_experimentalParam1 +/* ZSTD_d_stableOutBuffer + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable. + * + * Tells the decompressor that the ZSTD_outBuffer will ALWAYS be the same + * between calls, except for the modifications that zstd makes to pos (the + * caller must not modify pos). This is checked by the decompressor, and + * decompression will fail if it ever changes. Therefore the ZSTD_outBuffer + * MUST be large enough to fit the entire decompressed frame. This will be + * checked when the frame content size is known. The data in the ZSTD_outBuffer + * in the range [dst, dst + pos) MUST not be modified during decompression + * or you will get data corruption. + * + * When this flags is enabled zstd won't allocate an output buffer, because + * it can write directly to the ZSTD_outBuffer, but it will still allocate + * an input buffer large enough to fit any compressed block. This will also + * avoid the memcpy() from the internal output buffer to the ZSTD_outBuffer. + * If you need to avoid the input buffer allocation use the buffer-less + * streaming API. + * + * NOTE: So long as the ZSTD_outBuffer always points to valid memory, using + * this flag is ALWAYS memory safe, and will never access out-of-bounds + * memory. However, decompression WILL fail if you violate the preconditions. + * + * WARNING: The data in the ZSTD_outBuffer in the range [dst, dst + pos) MUST + * not be modified during decompression or you will get data corruption. This + * is because zstd needs to reference data in the ZSTD_outBuffer to regenerate + * matches. Normally zstd maintains its own buffer for this purpose, but passing + * this flag tells zstd to use the user provided buffer. */ -size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, - ZSTD_inBuffer *input); -/** - * ZSTD_flushStream() - flush internal buffers into output - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. - * - * ZSTD_flushStream() must be called until it returns 0, meaning all the data - * has been flushed. Since ZSTD_flushStream() causes a block to be ended, - * calling it too often will degrade the compression ratio. +#define ZSTD_d_stableOutBuffer ZSTD_d_experimentalParam2 + +/* ZSTD_d_forceIgnoreChecksum + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable * - * Return: The number of bytes still present within internal buffers or an - * error, which can be checked using ZSTD_isError(). + * Tells the decompressor to skip checksum validation during decompression, regardless + * of whether checksumming was specified during compression. This offers some + * slight performance benefits, and may be useful for debugging. + * Param has values of type ZSTD_forceIgnoreChecksum_e */ -size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); -/** - * ZSTD_endStream() - flush internal buffers into output and end the frame - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. +#define ZSTD_d_forceIgnoreChecksum ZSTD_d_experimentalParam3 + +/* ZSTD_d_refMultipleDDicts + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable * - * ZSTD_endStream() must be called until it returns 0, meaning all the data has - * been flushed and the frame epilogue has been written. + * If enabled and dctx is allocated on the heap, then additional memory will be allocated + * to store references to multiple ZSTD_DDict. That is, multiple calls of ZSTD_refDDict() + * using a given ZSTD_DCtx, rather than overwriting the previous DDict reference, will instead + * store all references. At decompression time, the appropriate dictID is selected + * from the set of DDicts based on the dictID in the frame. * - * Return: The number of bytes still present within internal buffers or an - * error, which can be checked using ZSTD_isError(). - */ -size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); - -/** - * ZSTD_CStreamInSize() - recommended size for the input buffer + * Usage is simply calling ZSTD_refDDict() on multiple dict buffers. * - * Return: The recommended size for the input buffer. - */ -size_t ZSTD_CStreamInSize(void); -/** - * ZSTD_CStreamOutSize() - recommended size for the output buffer + * Param has values of byte ZSTD_refMultipleDDicts_e * - * When the output buffer is at least this large, it is guaranteed to be large - * enough to flush at least one complete compressed block. + * WARNING: Enabling this parameter and calling ZSTD_DCtx_refDDict(), will trigger memory + * allocation for the hash table. ZSTD_freeDCtx() also frees this memory. + * Memory is allocated as per ZSTD_DCtx::customMem. * - * Return: The recommended size for the output buffer. + * Although this function allocates memory for the table, the user is still responsible for + * memory management of the underlying ZSTD_DDict* themselves. */ -size_t ZSTD_CStreamOutSize(void); - +#define ZSTD_d_refMultipleDDicts ZSTD_d_experimentalParam4 -/*-***************************************************************************** - * Streaming decompression - HowTo - * - * A ZSTD_DStream object is required to track streaming operations. - * Use ZSTD_initDStream() to initialize a ZSTD_DStream object. - * ZSTD_DStream objects can be re-used multiple times. - * - * Use ZSTD_decompressStream() repetitively to consume your input. - * The function will update both `pos` fields. - * If `input->pos < input->size`, some input has not been consumed. - * It's up to the caller to present again remaining data. - * If `output->pos < output->size`, decoder has flushed everything it could. - * Returns 0 iff a frame is completely decoded and fully flushed. - * Otherwise it returns a suggested next input size that will never load more - * than the current frame. - ******************************************************************************/ +/*! ZSTD_DCtx_setFormat() : + * Instruct the decoder context about what kind of data to decode next. + * This instruction is mandatory to decode data without a fully-formed header, + * such ZSTD_f_zstd1_magicless for example. + * @return : 0, or an error code (which can be tested using ZSTD_isError()). */ +ZSTDLIB_API size_t ZSTD_DCtx_setFormat(ZSTD_DCtx* dctx, ZSTD_format_e format); -/** - * ZSTD_DStreamWorkspaceBound() - memory needed to initialize a ZSTD_DStream - * @maxWindowSize: The maximum window size allowed for compressed frames. - * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDStream() and ZSTD_initDStream_usingDDict(). +/*! ZSTD_decompressStream_simpleArgs() : + * Same as ZSTD_decompressStream(), + * but using only integral types as arguments. + * This can be helpful for binders from dynamic languages + * which have troubles handling structures containing memory pointers. */ -size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize); +ZSTDLIB_API size_t ZSTD_decompressStream_simpleArgs ( + ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos); + + +/* ****************************************************************** +* Advanced streaming functions +* Warning : most of these functions are now redundant with the Advanced API. +* Once Advanced API reaches "stable" status, +* redundant functions will be deprecated, and then at some point removed. +********************************************************************/ + +/*===== Advanced Streaming compression functions =====*/ + +/*! ZSTD_initCStream_srcSize() : + * This function is deprecated, and equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any) + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * + * pledgedSrcSize must be correct. If it is not known at init time, use + * ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, + * "0" also disables frame content size field. It may be enabled in the future. + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t +ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, + int compressionLevel, + unsigned long long pledgedSrcSize); + +/*! ZSTD_initCStream_usingDict() : + * This function is deprecated, and is equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); + * + * Creates of an internal CDict (incompatible with static CCtx), except if + * dict == NULL or dictSize < 8, in which case no dict is used. + * Note: dict is loaded with ZSTD_dct_auto (treated as a full zstd dictionary if + * it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy. + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t +ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, + const void* dict, size_t dictSize, + int compressionLevel); + +/*! ZSTD_initCStream_advanced() : + * This function is deprecated, and is approximately equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * // Pseudocode: Set each zstd parameter and leave the rest as-is. + * for ((param, value) : params) { + * ZSTD_CCtx_setParameter(zcs, param, value); + * } + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); + * + * dict is loaded with ZSTD_dct_auto and ZSTD_dlm_byCopy. + * pledgedSrcSize must be correct. + * If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t +ZSTD_initCStream_advanced(ZSTD_CStream* zcs, + const void* dict, size_t dictSize, + ZSTD_parameters params, + unsigned long long pledgedSrcSize); + +/*! ZSTD_initCStream_usingCDict() : + * This function is deprecated, and equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, cdict); + * + * note : cdict will just be referenced, and must outlive compression session + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); + +/*! ZSTD_initCStream_usingCDict_advanced() : + * This function is DEPRECATED, and is approximately equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * // Pseudocode: Set each zstd frame parameter and leave the rest as-is. + * for ((fParam, value) : fParams) { + * ZSTD_CCtx_setParameter(zcs, fParam, value); + * } + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * ZSTD_CCtx_refCDict(zcs, cdict); + * + * same as ZSTD_initCStream_usingCDict(), with control over frame parameters. + * pledgedSrcSize must be correct. If srcSize is not known at init time, use + * value ZSTD_CONTENTSIZE_UNKNOWN. + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t +ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, + const ZSTD_CDict* cdict, + ZSTD_frameParameters fParams, + unsigned long long pledgedSrcSize); + +/*! ZSTD_resetCStream() : + * This function is deprecated, and is equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * + * start a new frame, using same parameters from previous frame. + * This is typically useful to skip dictionary loading stage, since it will re-use it in-place. + * Note that zcs must be init at least once before using ZSTD_resetCStream(). + * If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN. + * If pledgedSrcSize > 0, its value must be correct, as it will be written in header, and controlled at the end. + * For the time being, pledgedSrcSize==0 is interpreted as "srcSize unknown" for compatibility with older programs, + * but it will change to mean "empty" in future version, so use macro ZSTD_CONTENTSIZE_UNKNOWN instead. + * @return : 0, or an error code (which can be tested using ZSTD_isError()) + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize); -/** - * struct ZSTD_DStream - the zstd streaming decompression context + +typedef struct { + unsigned long long ingested; /* nb input bytes read and buffered */ + unsigned long long consumed; /* nb input bytes actually compressed */ + unsigned long long produced; /* nb of compressed bytes generated and buffered */ + unsigned long long flushed; /* nb of compressed bytes flushed : not provided; can be tracked from caller side */ + unsigned currentJobID; /* MT only : latest started job nb */ + unsigned nbActiveWorkers; /* MT only : nb of workers actively compressing at probe time */ +} ZSTD_frameProgression; + +/* ZSTD_getFrameProgression() : + * tells how much data has been ingested (read from input) + * consumed (input actually compressed) and produced (output) for current frame. + * Note : (ingested - consumed) is amount of input data buffered internally, not yet compressed. + * Aggregates progression inside active worker threads. */ -typedef struct ZSTD_DStream_s ZSTD_DStream; -/*===== ZSTD_DStream management functions =====*/ -/** - * ZSTD_initDStream() - initialize a zstd streaming decompression context - * @maxWindowSize: The maximum window size allowed for compressed frames. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine - * how large the workspace must be. - * - * Return: The zstd streaming decompression context. - */ -ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, - size_t workspaceSize); -/** - * ZSTD_initDStream_usingDDict() - initialize streaming decompression context - * @maxWindowSize: The maximum window size allowed for compressed frames. - * @ddict: The digested dictionary to use for decompression. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine - * how large the workspace must be. - * - * Return: The zstd streaming decompression context. - */ -ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, - const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize); +ZSTDLIB_API ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx); + +/*! ZSTD_toFlushNow() : + * Tell how many bytes are ready to be flushed immediately. + * Useful for multithreading scenarios (nbWorkers >= 1). + * Probe the oldest active job, defined as oldest job not yet entirely flushed, + * and check its output buffer. + * @return : amount of data stored in oldest job and ready to be flushed immediately. + * if @return == 0, it means either : + * + there is no active job (could be checked with ZSTD_frameProgression()), or + * + oldest job is still actively compressing data, + * but everything it has produced has also been flushed so far, + * therefore flush speed is limited by production speed of oldest job + * irrespective of the speed of concurrent (and newer) jobs. + */ +ZSTDLIB_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx); -/*===== Streaming decompression functions =====*/ -/** - * ZSTD_resetDStream() - reset the context using parameters from creation - * @zds: The zstd streaming decompression context to reset. + +/*===== Advanced Streaming decompression functions =====*/ + +/*! + * This function is deprecated, and is equivalent to: * - * Resets the context using the parameters from creation. Skips dictionary - * loading, since it can be reused. + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_loadDictionary(zds, dict, dictSize); * - * Return: Zero or an error, which can be checked using ZSTD_isError(). + * note: no dictionary will be used if dict == NULL or dictSize < 8 + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x */ -size_t ZSTD_resetDStream(ZSTD_DStream *zds); -/** - * ZSTD_decompressStream() - streaming decompress some of input into output - * @zds: The zstd streaming decompression context. - * @output: Destination buffer. `output.pos` is updated to indicate how much - * decompressed data was written. - * @input: Source buffer. `input.pos` is updated to indicate how much data was - * read. Note that it may not consume the entire input, in which case - * `input.pos < input.size`, and it's up to the caller to present - * remaining data again. +ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); + +/*! + * This function is deprecated, and is equivalent to: * - * The `input` and `output` buffers may be any size. Guaranteed to make some - * forward progress if `input` and `output` are not empty. - * ZSTD_decompressStream() will not consume the last byte of the frame until - * the entire frame is flushed. + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_refDDict(zds, ddict); * - * Return: Returns 0 iff a frame is completely decoded and fully flushed. - * Otherwise returns a hint for the number of bytes to use as the input - * for the next function call or an error, which can be checked using - * ZSTD_isError(). The size hint will never load more than the frame. + * note : ddict is referenced, it must outlive decompression session + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x */ -size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, - ZSTD_inBuffer *input); +ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); -/** - * ZSTD_DStreamInSize() - recommended size for the input buffer - * - * Return: The recommended size for the input buffer. - */ -size_t ZSTD_DStreamInSize(void); -/** - * ZSTD_DStreamOutSize() - recommended size for the output buffer +/*! + * This function is deprecated, and is equivalent to: * - * When the output buffer is at least this large, it is guaranteed to be large - * enough to flush at least one complete decompressed block. + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); * - * Return: The recommended size for the output buffer. + * re-use decompression parameters from previous init; saves dictionary loading + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x */ -size_t ZSTD_DStreamOutSize(void); +ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); -/* --- Constants ---*/ -#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ -#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U +/* ******************************************************************* +* Buffer-less and synchronous inner streaming functions +* +* This is an advanced API, giving full control over buffer management, for users which need direct control over memory. +* But it's also a complex one, with several restrictions, documented below. +* Prefer normal streaming API for an easier experience. +********************************************************************* */ -#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) -#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) +/* + Buffer-less streaming compression (synchronous mode) + + A ZSTD_CCtx object is required to track streaming operations. + Use ZSTD_createCCtx() / ZSTD_freeCCtx() to manage resource. + ZSTD_CCtx object can be re-used multiple times within successive compression operations. + + Start by initializing a context. + Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary compression, + or ZSTD_compressBegin_advanced(), for finer parameter control. + It's also possible to duplicate a reference context which has already been initialized, using ZSTD_copyCCtx() + + Then, consume your input using ZSTD_compressContinue(). + There are some important considerations to keep in mind when using this advanced function : + - ZSTD_compressContinue() has no internal buffer. It uses externally provided buffers only. + - Interface is synchronous : input is consumed entirely and produces 1+ compressed blocks. + - Caller must ensure there is enough space in `dst` to store compressed data under worst case scenario. + Worst case evaluation is provided by ZSTD_compressBound(). + ZSTD_compressContinue() doesn't guarantee recover after a failed compression. + - ZSTD_compressContinue() presumes prior input ***is still accessible and unmodified*** (up to maximum distance size, see WindowLog). + It remembers all previous contiguous blocks, plus one separated memory segment (which can itself consists of multiple contiguous blocks) + - ZSTD_compressContinue() detects that prior input has been overwritten when `src` buffer overlaps. + In which case, it will "discard" the relevant memory section from its history. + + Finish a frame with ZSTD_compressEnd(), which will write the last block(s) and optional checksum. + It's possible to use srcSize==0, in which case, it will write a final empty block to end the frame. + Without last block mark, frames are considered unfinished (hence corrupted) by compliant decoders. + + `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress again. +*/ -#define ZSTD_WINDOWLOG_MAX_32 27 -#define ZSTD_WINDOWLOG_MAX_64 27 -#define ZSTD_WINDOWLOG_MAX \ - ((unsigned int)(sizeof(size_t) == 4 \ - ? ZSTD_WINDOWLOG_MAX_32 \ - : ZSTD_WINDOWLOG_MAX_64)) -#define ZSTD_WINDOWLOG_MIN 10 -#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX -#define ZSTD_HASHLOG_MIN 6 -#define ZSTD_CHAINLOG_MAX (ZSTD_WINDOWLOG_MAX+1) -#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN -#define ZSTD_HASHLOG3_MAX 17 -#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) -#define ZSTD_SEARCHLOG_MIN 1 -/* only for ZSTD_fast, other strategies are limited to 6 */ -#define ZSTD_SEARCHLENGTH_MAX 7 -/* only for ZSTD_btopt, other strategies are limited to 4 */ -#define ZSTD_SEARCHLENGTH_MIN 3 -#define ZSTD_TARGETLENGTH_MIN 4 -#define ZSTD_TARGETLENGTH_MAX 999 - -/* for static allocation */ -#define ZSTD_FRAMEHEADERSIZE_MAX 18 -#define ZSTD_FRAMEHEADERSIZE_MIN 6 -#define ZSTD_frameHeaderSize_prefix 5 -#define ZSTD_frameHeaderSize_min ZSTD_FRAMEHEADERSIZE_MIN -#define ZSTD_frameHeaderSize_max ZSTD_FRAMEHEADERSIZE_MAX -/* magic number + skippable frame length */ -#define ZSTD_skippableHeaderSize 8 - - -/*-************************************* - * Compressed size functions - **************************************/ - -/** - * ZSTD_findFrameCompressedSize() - returns the size of a compressed frame - * @src: Source buffer. It should point to the start of a zstd encoded frame - * or a skippable frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * size of the frame. - * - * Return: The compressed size of the frame pointed to by `src` or an error, - * which can be check with ZSTD_isError(). - * Suitable to pass to ZSTD_decompress() or similar functions. - */ -size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize); - -/*-************************************* - * Decompressed size functions - **************************************/ -/** - * ZSTD_getFrameContentSize() - returns the content size in a zstd frame header - * @src: It should point to the start of a zstd encoded frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * frame header. `ZSTD_frameHeaderSize_max` is always large enough. - * - * Return: The frame content size stored in the frame header if known. - * `ZSTD_CONTENTSIZE_UNKNOWN` if the content size isn't stored in the - * frame header. `ZSTD_CONTENTSIZE_ERROR` on invalid input. - */ -unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); - -/** - * ZSTD_findDecompressedSize() - returns decompressed size of a series of frames - * @src: It should point to the start of a series of zstd encoded and/or - * skippable frames. - * @srcSize: The exact size of the series of frames. - * - * If any zstd encoded frame in the series doesn't have the frame content size - * set, `ZSTD_CONTENTSIZE_UNKNOWN` is returned. But frame content size is always - * set when using ZSTD_compress(). The decompressed size can be very large. - * If the source is untrusted, the decompressed size could be wrong or - * intentionally modified. Always ensure the result fits within the - * application's authorized limits. ZSTD_findDecompressedSize() handles multiple - * frames, and so it must traverse the input to read each frame header. This is - * efficient as most of the data is skipped, however it does mean that all frame - * data must be present and valid. - * - * Return: Decompressed size of all the data contained in the frames if known. - * `ZSTD_CONTENTSIZE_UNKNOWN` if the decompressed size is unknown. - * `ZSTD_CONTENTSIZE_ERROR` if an error occurred. - */ -unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize); - -/*-************************************* - * Advanced compression functions - **************************************/ -/** - * ZSTD_checkCParams() - ensure parameter values remain within authorized range - * @cParams: The zstd compression parameters. - * - * Return: Zero or an error, which can be checked using ZSTD_isError(). - */ -size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams); - -/** - * ZSTD_adjustCParams() - optimize parameters for a given srcSize and dictSize - * @srcSize: Optionally the estimated source size, or zero if unknown. - * @dictSize: Optionally the estimated dictionary size, or zero if unknown. - * - * Return: The optimized parameters. - */ -ZSTD_compressionParameters ZSTD_adjustCParams( - ZSTD_compressionParameters cParams, unsigned long long srcSize, - size_t dictSize); - -/*--- Advanced decompression functions ---*/ - -/** - * ZSTD_isFrame() - returns true iff the buffer starts with a valid frame - * @buffer: The source buffer to check. - * @size: The size of the source buffer, must be at least 4 bytes. - * - * Return: True iff the buffer starts with a zstd or skippable frame identifier. - */ -unsigned int ZSTD_isFrame(const void *buffer, size_t size); - -/** - * ZSTD_getDictID_fromDict() - returns the dictionary id stored in a dictionary - * @dict: The dictionary buffer. - * @dictSize: The size of the dictionary buffer. - * - * Return: The dictionary id stored within the dictionary or 0 if the - * dictionary is not a zstd dictionary. If it returns 0 the - * dictionary can still be loaded as a content-only dictionary. - */ -unsigned int ZSTD_getDictID_fromDict(const void *dict, size_t dictSize); +/*===== Buffer-less streaming compression functions =====*/ +ZSTDLIB_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel); +ZSTDLIB_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel); +ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /*< pledgedSrcSize : If srcSize is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN */ +ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); /*< note: fails if cdict==NULL */ +ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize); /* compression parameters are already set within cdict. pledgedSrcSize must be correct. If srcSize is not known, use macro ZSTD_CONTENTSIZE_UNKNOWN */ +ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /*< note: if pledgedSrcSize is not known, use ZSTD_CONTENTSIZE_UNKNOWN */ -/** - * ZSTD_getDictID_fromDDict() - returns the dictionary id stored in a ZSTD_DDict - * @ddict: The ddict to find the id of. - * - * Return: The dictionary id stored within `ddict` or 0 if the dictionary is not - * a zstd dictionary. If it returns 0 `ddict` will be loaded as a - * content-only dictionary. - */ -unsigned int ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict); +ZSTDLIB_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); -/** - * ZSTD_getDictID_fromFrame() - returns the dictionary id stored in a zstd frame - * @src: Source buffer. It must be a zstd encoded frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * frame header. `ZSTD_frameHeaderSize_max` is always large enough. - * - * Return: The dictionary id required to decompress the frame stored within - * `src` or 0 if the dictionary id could not be decoded. It can return - * 0 if the frame does not require a dictionary, the dictionary id - * wasn't stored in the frame, `src` is not a zstd frame, or `srcSize` - * is too small. - */ -unsigned int ZSTD_getDictID_fromFrame(const void *src, size_t srcSize); -/** - * struct ZSTD_frameParams - zstd frame parameters stored in the frame header - * @frameContentSize: The frame content size, or 0 if not present. - * @windowSize: The window size, or 0 if the frame is a skippable frame. - * @dictID: The dictionary id, or 0 if not present. - * @checksumFlag: Whether a checksum was used. - */ +/* + Buffer-less streaming decompression (synchronous mode) + + A ZSTD_DCtx object is required to track streaming operations. + Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it. + A ZSTD_DCtx object can be re-used multiple times. + + First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader(). + Frame header is extracted from the beginning of compressed frame, so providing only the frame's beginning is enough. + Data fragment must be large enough to ensure successful decoding. + `ZSTD_frameHeaderSize_max` bytes is guaranteed to always be large enough. + @result : 0 : successful decoding, the `ZSTD_frameHeader` structure is correctly filled. + >0 : `srcSize` is too small, please provide at least @result bytes on next attempt. + errorCode, which can be tested using ZSTD_isError(). + + It fills a ZSTD_frameHeader structure with important information to correctly decode the frame, + such as the dictionary ID, content size, or maximum back-reference distance (`windowSize`). + Note that these values could be wrong, either because of data corruption, or because a 3rd party deliberately spoofs false information. + As a consequence, check that values remain within valid application range. + For example, do not allocate memory blindly, check that `windowSize` is within expectation. + Each application can set its own limits, depending on local restrictions. + For extended interoperability, it is recommended to support `windowSize` of at least 8 MB. + + ZSTD_decompressContinue() needs previous data blocks during decompression, up to `windowSize` bytes. + ZSTD_decompressContinue() is very sensitive to contiguity, + if 2 blocks don't follow each other, make sure that either the compressor breaks contiguity at the same place, + or that previous contiguous segment is large enough to properly handle maximum back-reference distance. + There are multiple ways to guarantee this condition. + + The most memory efficient way is to use a round buffer of sufficient size. + Sufficient size is determined by invoking ZSTD_decodingBufferSize_min(), + which can @return an error code if required value is too large for current system (in 32-bits mode). + In a round buffer methodology, ZSTD_decompressContinue() decompresses each block next to previous one, + up to the moment there is not enough room left in the buffer to guarantee decoding another full block, + which maximum size is provided in `ZSTD_frameHeader` structure, field `blockSizeMax`. + At which point, decoding can resume from the beginning of the buffer. + Note that already decoded data stored in the buffer should be flushed before being overwritten. + + There are alternatives possible, for example using two or more buffers of size `windowSize` each, though they consume more memory. + + Finally, if you control the compression process, you can also ignore all buffer size rules, + as long as the encoder and decoder progress in "lock-step", + aka use exactly the same buffer sizes, break contiguity at the same place, etc. + + Once buffers are setup, start decompression, with ZSTD_decompressBegin(). + If decompression requires a dictionary, use ZSTD_decompressBegin_usingDict() or ZSTD_decompressBegin_usingDDict(). + + Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() alternatively. + ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' to ZSTD_decompressContinue(). + ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will fail. + + @result of ZSTD_decompressContinue() is the number of bytes regenerated within 'dst' (necessarily <= dstCapacity). + It can be zero : it just means ZSTD_decompressContinue() has decoded some metadata item. + It can also be an error code, which can be tested with ZSTD_isError(). + + A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. + Context can then be reset to start a new decompression. + + Note : it's possible to know if next input to present is a header or a block, using ZSTD_nextInputType(). + This information is not required to properly decode a frame. + + == Special case : skippable frames == + + Skippable frames allow integration of user-defined data into a flow of concatenated frames. + Skippable frames will be ignored (skipped) by decompressor. + The format of skippable frames is as follows : + a) Skippable frame ID - 4 Bytes, Little endian format, any value from 0x184D2A50 to 0x184D2A5F + b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits + c) Frame Content - any content (User Data) of length equal to Frame Size + For skippable frames ZSTD_getFrameHeader() returns zfhPtr->frameType==ZSTD_skippableFrame. + For skippable frames ZSTD_decompressContinue() always returns 0 : it only skips the content. +*/ + +/*===== Buffer-less streaming decompression functions =====*/ +typedef enum { ZSTD_frame, ZSTD_skippableFrame } ZSTD_frameType_e; typedef struct { - unsigned long long frameContentSize; - unsigned int windowSize; - unsigned int dictID; - unsigned int checksumFlag; -} ZSTD_frameParams; - -/** - * ZSTD_getFrameParams() - extracts parameters from a zstd or skippable frame - * @fparamsPtr: On success the frame parameters are written here. - * @src: The source buffer. It must point to a zstd or skippable frame. - * @srcSize: The size of the source buffer. `ZSTD_frameHeaderSize_max` is - * always large enough to succeed. - * - * Return: 0 on success. If more data is required it returns how many bytes - * must be provided to make forward progress. Otherwise it returns - * an error, which can be checked using ZSTD_isError(). - */ -size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, - size_t srcSize); - -/*-***************************************************************************** - * Buffer-less and synchronous inner streaming functions - * - * This is an advanced API, giving full control over buffer management, for - * users which need direct control over memory. - * But it's also a complex one, with many restrictions (documented below). - * Prefer using normal streaming API for an easier experience - ******************************************************************************/ + unsigned long long frameContentSize; /* if == ZSTD_CONTENTSIZE_UNKNOWN, it means this field is not available. 0 means "empty" */ + unsigned long long windowSize; /* can be very large, up to <= frameContentSize */ + unsigned blockSizeMax; + ZSTD_frameType_e frameType; /* if == ZSTD_skippableFrame, frameContentSize is the size of skippable content */ + unsigned headerSize; + unsigned dictID; + unsigned checksumFlag; +} ZSTD_frameHeader; + +/*! ZSTD_getFrameHeader() : + * decode Frame Header, or requires larger `srcSize`. + * @return : 0, `zfhPtr` is correctly filled, + * >0, `srcSize` is too small, value is wanted `srcSize` amount, + * or an error code, which can be tested using ZSTD_isError() */ +ZSTDLIB_API size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize); /*< doesn't consume input */ +/*! ZSTD_getFrameHeader_advanced() : + * same as ZSTD_getFrameHeader(), + * with added capability to select a format (like ZSTD_f_zstd1_magicless) */ +ZSTDLIB_API size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format); +ZSTDLIB_API size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize); /*< when frame content size is not known, pass in frameContentSize == ZSTD_CONTENTSIZE_UNKNOWN */ + +ZSTDLIB_API size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx); +ZSTDLIB_API size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); +ZSTDLIB_API size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); + +ZSTDLIB_API size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx); +ZSTDLIB_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); + +/* misc */ +ZSTDLIB_API void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx); +typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e; +ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); + + + + +/* ============================ */ +/* Block level API */ +/* ============================ */ + +/*! + Block functions produce and decode raw zstd blocks, without frame metadata. + Frame metadata cost is typically ~12 bytes, which can be non-negligible for very small blocks (< 100 bytes). + But users will have to take in charge needed metadata to regenerate data, such as compressed and content sizes. + + A few rules to respect : + - Compressing and decompressing require a context structure + + Use ZSTD_createCCtx() and ZSTD_createDCtx() + - It is necessary to init context before starting + + compression : any ZSTD_compressBegin*() variant, including with dictionary + + decompression : any ZSTD_decompressBegin*() variant, including with dictionary + + copyCCtx() and copyDCtx() can be used too + - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX == 128 KB + + If input is larger than a block size, it's necessary to split input data into multiple blocks + + For inputs larger than a single block, consider using regular ZSTD_compress() instead. + Frame metadata is not that costly, and quickly becomes negligible as source size grows larger than a block. + - When a block is considered not compressible enough, ZSTD_compressBlock() result will be 0 (zero) ! + ===> In which case, nothing is produced into `dst` ! + + User __must__ test for such outcome and deal directly with uncompressed data + + A block cannot be declared incompressible if ZSTD_compressBlock() return value was != 0. + Doing so would mess up with statistics history, leading to potential data corruption. + + ZSTD_decompressBlock() _doesn't accept uncompressed data as input_ !! + + In case of multiple successive blocks, should some of them be uncompressed, + decoder must be informed of their existence in order to follow proper history. + Use ZSTD_insertBlock() for such a case. +*/ -/*-***************************************************************************** - * Buffer-less streaming compression (synchronous mode) - * - * A ZSTD_CCtx object is required to track streaming operations. - * Use ZSTD_initCCtx() to initialize a context. - * ZSTD_CCtx object can be re-used multiple times within successive compression - * operations. - * - * Start by initializing a context. - * Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary - * compression, - * or ZSTD_compressBegin_advanced(), for finer parameter control. - * It's also possible to duplicate a reference context which has already been - * initialized, using ZSTD_copyCCtx() - * - * Then, consume your input using ZSTD_compressContinue(). - * There are some important considerations to keep in mind when using this - * advanced function : - * - ZSTD_compressContinue() has no internal buffer. It uses externally provided - * buffer only. - * - Interface is synchronous : input is consumed entirely and produce 1+ - * (or more) compressed blocks. - * - Caller must ensure there is enough space in `dst` to store compressed data - * under worst case scenario. Worst case evaluation is provided by - * ZSTD_compressBound(). - * ZSTD_compressContinue() doesn't guarantee recover after a failed - * compression. - * - ZSTD_compressContinue() presumes prior input ***is still accessible and - * unmodified*** (up to maximum distance size, see WindowLog). - * It remembers all previous contiguous blocks, plus one separated memory - * segment (which can itself consists of multiple contiguous blocks) - * - ZSTD_compressContinue() detects that prior input has been overwritten when - * `src` buffer overlaps. In which case, it will "discard" the relevant memory - * section from its history. - * - * Finish a frame with ZSTD_compressEnd(), which will write the last block(s) - * and optional checksum. It's possible to use srcSize==0, in which case, it - * will write a final empty block to end the frame. Without last block mark, - * frames will be considered unfinished (corrupted) by decoders. - * - * `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new - * frame. - ******************************************************************************/ +/*===== Raw zstd block functions =====*/ +ZSTDLIB_API size_t ZSTD_getBlockSize (const ZSTD_CCtx* cctx); +ZSTDLIB_API size_t ZSTD_compressBlock (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +ZSTDLIB_API size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +ZSTDLIB_API size_t ZSTD_insertBlock (ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize); /*< insert uncompressed block into `dctx` history. Useful for multi-blocks decompression. */ -/*===== Buffer-less streaming compression functions =====*/ -size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel); -size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, - size_t dictSize, int compressionLevel); -size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, - size_t dictSize, ZSTD_parameters params, - unsigned long long pledgedSrcSize); -size_t ZSTD_copyCCtx(ZSTD_CCtx *cctx, const ZSTD_CCtx *preparedCCtx, - unsigned long long pledgedSrcSize); -size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, - unsigned long long pledgedSrcSize); -size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); - - - -/*-***************************************************************************** - * Buffer-less streaming decompression (synchronous mode) - * - * A ZSTD_DCtx object is required to track streaming operations. - * Use ZSTD_initDCtx() to initialize a context. - * A ZSTD_DCtx object can be re-used multiple times. - * - * First typical operation is to retrieve frame parameters, using - * ZSTD_getFrameParams(). It fills a ZSTD_frameParams structure which provide - * important information to correctly decode the frame, such as the minimum - * rolling buffer size to allocate to decompress data (`windowSize`), and the - * dictionary ID used. - * Note: content size is optional, it may not be present. 0 means unknown. - * Note that these values could be wrong, either because of data malformation, - * or because an attacker is spoofing deliberate false information. As a - * consequence, check that values remain within valid application range, - * especially `windowSize`, before allocation. Each application can set its own - * limit, depending on local restrictions. For extended interoperability, it is - * recommended to support at least 8 MB. - * Frame parameters are extracted from the beginning of the compressed frame. - * Data fragment must be large enough to ensure successful decoding, typically - * `ZSTD_frameHeaderSize_max` bytes. - * Result: 0: successful decoding, the `ZSTD_frameParams` structure is filled. - * >0: `srcSize` is too small, provide at least this many bytes. - * errorCode, which can be tested using ZSTD_isError(). - * - * Start decompression, with ZSTD_decompressBegin() or - * ZSTD_decompressBegin_usingDict(). Alternatively, you can copy a prepared - * context, using ZSTD_copyDCtx(). - * - * Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() - * alternatively. - * ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' - * to ZSTD_decompressContinue(). - * ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will - * fail. - * - * The result of ZSTD_decompressContinue() is the number of bytes regenerated - * within 'dst' (necessarily <= dstCapacity). It can be zero, which is not an - * error; it just means ZSTD_decompressContinue() has decoded some metadata - * item. It can also be an error code, which can be tested with ZSTD_isError(). - * - * ZSTD_decompressContinue() needs previous data blocks during decompression, up - * to `windowSize`. They should preferably be located contiguously, prior to - * current block. Alternatively, a round buffer of sufficient size is also - * possible. Sufficient size is determined by frame parameters. - * ZSTD_decompressContinue() is very sensitive to contiguity, if 2 blocks don't - * follow each other, make sure that either the compressor breaks contiguity at - * the same place, or that previous contiguous segment is large enough to - * properly handle maximum back-reference. - * - * A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. - * Context can then be reset to start a new decompression. - * - * Note: it's possible to know if next input to present is a header or a block, - * using ZSTD_nextInputType(). This information is not required to properly - * decode a frame. - * - * == Special case: skippable frames == - * - * Skippable frames allow integration of user-defined data into a flow of - * concatenated frames. Skippable frames will be ignored (skipped) by a - * decompressor. The format of skippable frames is as follows: - * a) Skippable frame ID - 4 Bytes, Little endian format, any value from - * 0x184D2A50 to 0x184D2A5F - * b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits - * c) Frame Content - any content (User Data) of length equal to Frame Size - * For skippable frames ZSTD_decompressContinue() always returns 0. - * For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 - * what means that a frame is skippable. - * Note: If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might - * actually be a zstd encoded frame with no content. For purposes of - * decompression, it is valid in both cases to skip the frame using - * ZSTD_findFrameCompressedSize() to find its size in bytes. - * It also returns frame size as fparamsPtr->frameContentSize. - ******************************************************************************/ -/*===== Buffer-less streaming decompression functions =====*/ -size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx); -size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, - size_t dictSize); -void ZSTD_copyDCtx(ZSTD_DCtx *dctx, const ZSTD_DCtx *preparedDCtx); -size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx); -size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -typedef enum { - ZSTDnit_frameHeader, - ZSTDnit_blockHeader, - ZSTDnit_block, - ZSTDnit_lastBlock, - ZSTDnit_checksum, - ZSTDnit_skippableFrame -} ZSTD_nextInputType_e; -ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx); - -/*-***************************************************************************** - * Block functions - * - * Block functions produce and decode raw zstd blocks, without frame metadata. - * Frame metadata cost is typically ~18 bytes, which can be non-negligible for - * very small blocks (< 100 bytes). User will have to take in charge required - * information to regenerate data, such as compressed and content sizes. - * - * A few rules to respect: - * - Compressing and decompressing require a context structure - * + Use ZSTD_initCCtx() and ZSTD_initDCtx() - * - It is necessary to init context before starting - * + compression : ZSTD_compressBegin() - * + decompression : ZSTD_decompressBegin() - * + variants _usingDict() are also allowed - * + copyCCtx() and copyDCtx() work too - * - Block size is limited, it must be <= ZSTD_getBlockSizeMax() - * + If you need to compress more, cut data into multiple blocks - * + Consider using the regular ZSTD_compress() instead, as frame metadata - * costs become negligible when source size is large. - * - When a block is considered not compressible enough, ZSTD_compressBlock() - * result will be zero. In which case, nothing is produced into `dst`. - * + User must test for such outcome and deal directly with uncompressed data - * + ZSTD_decompressBlock() doesn't accept uncompressed data as input!!! - * + In case of multiple successive blocks, decoder must be informed of - * uncompressed block existence to follow proper history. Use - * ZSTD_insertBlock() in such a case. - ******************************************************************************/ +#endif /* ZSTD_H_ZSTD_STATIC_LINKING_ONLY */ -/* Define for static allocation */ -#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) -/*===== Raw zstd block functions =====*/ -size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx); -size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, - size_t blockSize); - -#endif /* ZSTD_H */ -- cgit v1.2.3 From 9ef4d0209cbadb63656a7aa29fde49c27ab2b9bf Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 9 Nov 2021 15:11:41 +0800 Subject: blk-mq: add one API for waiting until quiesce is done Some drivers(NVMe, SCSI) need to call quiesce and unquiesce in pair, but it is hard to switch to this style, so these drivers need one atomic flag for helping to balance quiesce and unquiesce. When quiesce is in-progress, the driver still needs to wait until the quiesce is done, so add API of blk_mq_wait_quiesce_done() for these drivers. Signed-off-by: Ming Lei Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20211109071144.181581-2-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b4039fdf1b04..d53ee59ba131 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -803,6 +803,7 @@ void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); +void blk_mq_wait_quiesce_done(struct request_queue *q); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); -- cgit v1.2.3 From 51b8c1fe250d1bd70c1722dc3c414f5cff2d7cca Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 8 Nov 2021 18:31:24 -0800 Subject: vfs: keep inodes with page cache off the inode shrinker LRU Historically (pre-2.5), the inode shrinker used to reclaim only empty inodes and skip over those that still contained page cache. This caused problems on highmem hosts: struct inode could put fill lowmem zones before the cache was getting reclaimed in the highmem zones. To address this, the inode shrinker started to strip page cache to facilitate reclaiming lowmem. However, this comes with its own set of problems: the shrinkers may drop actively used page cache just because the inodes are not currently open or dirty - think working with a large git tree. It further doesn't respect cgroup memory protection settings and can cause priority inversions between containers. Nowadays, the page cache also holds non-resident info for evicted cache pages in order to detect refaults. We've come to rely heavily on this data inside reclaim for protecting the cache workingset and driving swap behavior. We also use it to quantify and report workload health through psi. The latter in turn is used for fleet health monitoring, as well as driving automated memory sizing of workloads and containers, proactive reclaim and memory offloading schemes. The consequences of dropping page cache prematurely is that we're seeing subtle and not-so-subtle failures in all of the above-mentioned scenarios, with the workload generally entering unexpected thrashing states while losing the ability to reliably detect it. To fix this on non-highmem systems at least, going back to rotating inodes on the LRU isn't feasible. We've tried (commit a76cf1a474d7 ("mm: don't reclaim inodes with many attached pages")) and failed (commit 69056ee6a8a3 ("Revert "mm: don't reclaim inodes with many attached pages"")). The issue is mostly that shrinker pools attract pressure based on their size, and when objects get skipped the shrinkers remember this as deferred reclaim work. This accumulates excessive pressure on the remaining inodes, and we can quickly eat into heavily used ones, or dirty ones that require IO to reclaim, when there potentially is plenty of cold, clean cache around still. Instead, this patch keeps populated inodes off the inode LRU in the first place - just like an open file or dirty state would. An otherwise clean and unused inode then gets queued when the last cache entry disappears. This solves the problem without reintroducing the reclaim issues, and generally is a bit more scalable than having to wade through potentially hundreds of thousands of busy inodes. Locking is a bit tricky because the locks protecting the inode state (i_lock) and the inode LRU (lru_list.lock) don't nest inside the irq-safe page cache lock (i_pages.xa_lock). Page cache deletions are serialized through i_lock, taken before the i_pages lock, to make sure depopulated inodes are queued reliably. Additions may race with deletions, but we'll check again in the shrinker. If additions race with the shrinker itself, we're protected by the i_lock: if find_inode() or iput() win, the shrinker will bail on the elevated i_count or I_REFERENCED; if the shrinker wins and goes ahead with the inode, it will set I_FREEING and inhibit further igets(), which will cause the other side to create a new instance of the inode instead. Link: https://lkml.kernel.org/r/20210614211904.14420-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Cc: Roman Gushchin Cc: Tejun Heo Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + include/linux/pagemap.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 226de651f52e..de35a2640e70 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3193,6 +3193,7 @@ static inline void remove_inode_hash(struct inode *inode) } extern void inode_sb_list_add(struct inode *inode); +extern void inode_add_lru(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 62db6b0176b9..5c74a45ff97a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -23,6 +23,56 @@ static inline bool mapping_empty(struct address_space *mapping) return xa_empty(&mapping->i_pages); } +/* + * mapping_shrinkable - test if page cache state allows inode reclaim + * @mapping: the page cache mapping + * + * This checks the mapping's cache state for the pupose of inode + * reclaim and LRU management. + * + * The caller is expected to hold the i_lock, but is not required to + * hold the i_pages lock, which usually protects cache state. That's + * because the i_lock and the list_lru lock that protect the inode and + * its LRU state don't nest inside the irq-safe i_pages lock. + * + * Cache deletions are performed under the i_lock, which ensures that + * when an inode goes empty, it will reliably get queued on the LRU. + * + * Cache additions do not acquire the i_lock and may race with this + * check, in which case we'll report the inode as shrinkable when it + * has cache pages. This is okay: the shrinker also checks the + * refcount and the referenced bit, which will be elevated or set in + * the process of adding new cache pages to an inode. + */ +static inline bool mapping_shrinkable(struct address_space *mapping) +{ + void *head; + + /* + * On highmem systems, there could be lowmem pressure from the + * inodes before there is highmem pressure from the page + * cache. Make inodes shrinkable regardless of cache state. + */ + if (IS_ENABLED(CONFIG_HIGHMEM)) + return true; + + /* Cache completely empty? Shrink away. */ + head = rcu_access_pointer(mapping->i_pages.xa_head); + if (!head) + return true; + + /* + * The xarray stores single offset-0 entries directly in the + * head pointer, which allows non-resident page cache entries + * to escape the shadow shrinker's list of xarray nodes. The + * inode shrinker needs to pick them up under memory pressure. + */ + if (!xa_is_node(head) && xa_is_value(head)) + return true; + + return false; +} + /* * Bits in mapping->flags. */ -- cgit v1.2.3 From 83c1fd763b3220458652f7d656d5047292ebcde4 Mon Sep 17 00:00:00 2001 From: zhangyiru Date: Mon, 8 Nov 2021 18:31:27 -0800 Subject: mm,hugetlb: remove mlock ulimit for SHM_HUGETLB Commit 21a3c273f88c ("mm, hugetlb: add thread name and pid to SHM_HUGETLB mlock rlimit warning") marked this as deprecated in 2012, but it is not deleted yet. Mike says he still sees that message in log files on occasion, so maybe we should preserve this warning. Also remove hugetlbfs related user_shm_unlock in ipc/shm.c and remove the user_shm_unlock after out. Link: https://lkml.kernel.org/r/20211103105857.25041-1-zhangyiru3@huawei.com Signed-off-by: zhangyiru Reviewed-by: Mike Kravetz Cc: Hugh Dickins Cc: Liu Zixian Cc: Michal Hocko Cc: wuxu.wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 44c2ab0dfa59..00351ccb49a3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -477,8 +477,7 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, - struct ucounts **ucounts, int creat_flags, - int page_size_log); + int creat_flags, int page_size_log); static inline bool is_file_hugepages(struct file *file) { @@ -497,8 +496,7 @@ static inline struct hstate *hstate_inode(struct inode *i) #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, - struct ucounts **ucounts, int creat_flags, - int page_size_log) + int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); } -- cgit v1.2.3 From cc5f2704c93456e6f1c671c5cf7b582a55df5484 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 8 Nov 2021 18:31:48 -0800 Subject: proc/vmcore: convert oldmem_pfn_is_ram callback to more generic vmcore callbacks Let's support multiple registered callbacks, making sure that registering vmcore callbacks cannot fail. Make the callback return a bool instead of an int, handling how to deal with errors internally. Drop unused HAVE_OLDMEM_PFN_IS_RAM. We soon want to make use of this infrastructure from other drivers: virtio-mem, registering one callback for each virtio-mem device, to prevent reading unplugged virtio-mem memory. Handle it via a generic vmcore_cb structure, prepared for future extensions: for example, once we support virtio-mem on s390x where the vmcore is completely constructed in the second kernel, we want to detect and add plugged virtio-mem memory ranges to the vmcore in order for them to get dumped properly. Handle corner cases that are unexpected and shouldn't happen in sane setups: registering a callback after the vmcore has already been opened (warn only) and unregistering a callback after the vmcore has already been opened (warn and essentially read only zeroes from that point on). Link: https://lkml.kernel.org/r/20211005121430.30136-6-david@redhat.com Signed-off-by: David Hildenbrand Cc: Baoquan He Cc: Borislav Petkov Cc: Boris Ostrovsky Cc: Dave Young Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Juergen Gross Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: "Rafael J. Wysocki" Cc: Stefano Stabellini Cc: Thomas Gleixner Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 2618577a4d6d..0c547d866f1e 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -91,9 +91,29 @@ static inline void vmcore_unusable(void) elfcorehdr_addr = ELFCORE_ADDR_ERR; } -#define HAVE_OLDMEM_PFN_IS_RAM 1 -extern int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn)); -extern void unregister_oldmem_pfn_is_ram(void); +/** + * struct vmcore_cb - driver callbacks for /proc/vmcore handling + * @pfn_is_ram: check whether a PFN really is RAM and should be accessed when + * reading the vmcore. Will return "true" if it is RAM or if the + * callback cannot tell. If any callback returns "false", it's not + * RAM and the page must not be accessed; zeroes should be + * indicated in the vmcore instead. For example, a ballooned page + * contains no data and reading from such a page will cause high + * load in the hypervisor. + * @next: List head to manage registered callbacks internally; initialized by + * register_vmcore_cb(). + * + * vmcore callbacks allow drivers managing physical memory ranges to + * coordinate with vmcore handling code, for example, to prevent accessing + * physical memory ranges that should not be accessed when reading the vmcore, + * although included in the vmcore header as memory ranges to dump. + */ +struct vmcore_cb { + bool (*pfn_is_ram)(struct vmcore_cb *cb, unsigned long pfn); + struct list_head next; +}; +extern void register_vmcore_cb(struct vmcore_cb *cb); +extern void unregister_vmcore_cb(struct vmcore_cb *cb); #else /* !CONFIG_CRASH_DUMP */ static inline bool is_kdump_kernel(void) { return 0; } -- cgit v1.2.3 From f5d80614844a725cbf66fd6524e01c218ede2141 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:08 -0800 Subject: kernel.h: drop unneeded inclusion from other headers Patch series "kernel.h further split", v5. kernel.h is a set of something which is not related to each other and often used in non-crossed compilation units, especially when drivers need only one or two macro definitions from it. This patch (of 7): There is no evidence we need kernel.h inclusion in certain headers. Drop unneeded inclusion from other headers. [sfr@canb.auug.org.au: bottom_half.h needs kernel] Link: https://lkml.kernel.org/r/20211015202908.1c417ae2@canb.auug.org.au Link: https://lkml.kernel.org/r/20211013170417.87909-1-andriy.shevchenko@linux.intel.com Link: https://lkml.kernel.org/r/20211013170417.87909-2-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Stephen Rothwell Cc: Thomas Gleixner Cc: Brendan Higgins Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Cc: Boqun Feng Cc: Sakari Ailus Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Jonathan Cameron Cc: Rasmus Villemoes Cc: Thorsten Leemhuis Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bottom_half.h | 1 + include/linux/rwsem.h | 1 - include/linux/smp.h | 1 - include/linux/spinlock.h | 1 - 4 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h index eed86eb0a1de..11d107d88d03 100644 --- a/include/linux/bottom_half.h +++ b/include/linux/bottom_half.h @@ -2,6 +2,7 @@ #ifndef _LINUX_BH_H #define _LINUX_BH_H +#include #include #if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_TRACE_IRQFLAGS) diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 352c6127cb90..f9348769e558 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -11,7 +11,6 @@ #include #include -#include #include #include #include diff --git a/include/linux/smp.h b/include/linux/smp.h index 510519e8a1eb..a80ab58ae3f1 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -108,7 +108,6 @@ static inline void on_each_cpu_cond(smp_cond_func_t cond_func, #ifdef CONFIG_SMP #include -#include #include #include #include diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 45310ea1b1d7..22d672f81705 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -57,7 +57,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From d2a8ebbf8192b84b11f1b204c4f7c602df32aeac Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:12 -0800 Subject: kernel.h: split out container_of() and typeof_member() macros kernel.h is being used as a dump for all kinds of stuff for a long time. Here is the attempt cleaning it up by splitting out container_of() and typeof_member() macros. For time being include new header back to kernel.h to avoid twisted indirected includes for existing users. Note, there are _a lot_ of headers and modules that include kernel.h solely for one of these macros and this allows to unburden compiler for the twisted inclusion paths and to make new code cleaner in the future. Link: https://lkml.kernel.org/r/20211013170417.87909-3-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Boqun Feng Cc: Brendan Higgins Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Thomas Gleixner Cc: Thorsten Leemhuis Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/container_of.h | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/kernel.h | 33 +-------------------------------- 2 files changed, 41 insertions(+), 32 deletions(-) create mode 100644 include/linux/container_of.h (limited to 'include/linux') diff --git a/include/linux/container_of.h b/include/linux/container_of.h new file mode 100644 index 000000000000..dd56019838c6 --- /dev/null +++ b/include/linux/container_of.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CONTAINER_OF_H +#define _LINUX_CONTAINER_OF_H + +#include +#include + +#define typeof_member(T, m) typeof(((T*)0)->m) + +/** + * container_of - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + */ +#define container_of(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + ((type *)(__mptr - offsetof(type, member))); }) + +/** + * container_of_safe - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + * If IS_ERR_OR_NULL(ptr), ptr is returned unchanged. + */ +#define container_of_safe(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + IS_ERR_OR_NULL(__mptr) ? ERR_CAST(__mptr) : \ + ((type *)(__mptr - offsetof(type, member))); }) + +#endif /* _LINUX_CONTAINER_OF_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 471bc0593679..ed4465757cec 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -52,8 +53,6 @@ } \ ) -#define typeof_member(T, m) typeof(((T*)0)->m) - #define _RET_IP_ (unsigned long)__builtin_return_address(0) #define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) @@ -484,36 +483,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #define __CONCAT(a, b) a ## b #define CONCATENATE(a, b) __CONCAT(a, b) -/** - * container_of - cast a member of a structure out to the containing structure - * @ptr: the pointer to the member. - * @type: the type of the container struct this is embedded in. - * @member: the name of the member within the struct. - * - */ -#define container_of(ptr, type, member) ({ \ - void *__mptr = (void *)(ptr); \ - BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ - !__same_type(*(ptr), void), \ - "pointer type mismatch in container_of()"); \ - ((type *)(__mptr - offsetof(type, member))); }) - -/** - * container_of_safe - cast a member of a structure out to the containing structure - * @ptr: the pointer to the member. - * @type: the type of the container struct this is embedded in. - * @member: the name of the member within the struct. - * - * If IS_ERR_OR_NULL(ptr), ptr is returned unchanged. - */ -#define container_of_safe(ptr, type, member) ({ \ - void *__mptr = (void *)(ptr); \ - BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ - !__same_type(*(ptr), void), \ - "pointer type mismatch in container_of()"); \ - IS_ERR_OR_NULL(__mptr) ? ERR_CAST(__mptr) : \ - ((type *)(__mptr - offsetof(type, member))); }) - /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD -- cgit v1.2.3 From cd7187e112c91186185c0553b1f9d033ed399d3a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:19 -0800 Subject: include/linux/list.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Link: https://lkml.kernel.org/r/20211013170417.87909-5-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Boqun Feng Cc: Brendan Higgins Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Thomas Gleixner Cc: Thorsten Leemhuis Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index f2af4b4aa4e9..6636fc07f918 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -2,11 +2,13 @@ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H +#include #include #include #include #include -#include + +#include /* * Circular doubly linked list implementation. -- cgit v1.2.3 From 50b09d6145da04e19fa448670e4918ce496f1c77 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:22 -0800 Subject: include/linux/llist.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Link: https://lkml.kernel.org/r/20211013170417.87909-6-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Boqun Feng Cc: Brendan Higgins Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Thomas Gleixner Cc: Thorsten Leemhuis Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/llist.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index 24f207b0190b..85bda2d02d65 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -49,7 +49,9 @@ */ #include -#include +#include +#include +#include struct llist_head { struct llist_node *first; -- cgit v1.2.3 From c540f9595956ff3c4b2cca1145c893941f921bcd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:25 -0800 Subject: include/linux/plist.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Link: https://lkml.kernel.org/r/20211013170417.87909-7-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Boqun Feng Cc: Brendan Higgins Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Thomas Gleixner Cc: Thorsten Leemhuis Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/plist.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/plist.h b/include/linux/plist.h index 66bab1bca35c..0f352c1d3c80 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -73,8 +73,11 @@ #ifndef _LINUX_PLIST_H_ #define _LINUX_PLIST_H_ -#include +#include #include +#include + +#include struct plist_head { struct list_head node_list; -- cgit v1.2.3 From 5f6286a608107a68646241b57d2bd2a4fc139ef9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:32 -0800 Subject: include/linux/delay.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. [akpm@linux-foundation.org: cxd2880_common.h needs bits.h for GENMASK()] [andriy.shevchenko@linux.intel.com: delay.h: fix for removed kernel.h] Link: https://lkml.kernel.org/r/20211028170143.56523-1-andriy.shevchenko@linux.intel.com [akpm@linux-foundation.org: include/linux/fwnode.h needs bits.h for BIT()] Link: https://lkml.kernel.org/r/20211027150324.79827-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delay.h | 2 +- include/linux/fwnode.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/delay.h b/include/linux/delay.h index 1d0e2ce6b6d9..8eacf67eb212 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -19,7 +19,7 @@ * https://lists.openwall.net/linux-kernel/2011/01/09/56 */ -#include +#include extern unsigned long loops_per_jiffy; diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 9f4ad719bfe3..3a532ba66f6c 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -11,6 +11,7 @@ #include #include +#include #include struct fwnode_operations; -- cgit v1.2.3 From 1fcbd5deac51f30a7ed3f10bea422d08a2b3aba6 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:35 -0800 Subject: include/linux/sbitmap.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Link: https://lkml.kernel.org/r/20211027150437.79921-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sbitmap.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 2713e689ad66..8121034d1f13 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -9,8 +9,17 @@ #ifndef __LINUX_SCALE_BITMAP_H #define __LINUX_SCALE_BITMAP_H -#include +#include +#include +#include +#include +#include +#include +#include #include +#include +#include +#include struct seq_file; -- cgit v1.2.3 From 98e1385ef24bd607586fbf44e73decd5112d3d4a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:38 -0800 Subject: include/linux/radix-tree.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Link: https://lkml.kernel.org/r/20211027150528.80003-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 64ad900ac742..f7c1d21c2f39 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -9,8 +9,10 @@ #define _LINUX_RADIX_TREE_H #include -#include +#include #include +#include +#include #include #include #include -- cgit v1.2.3 From b4b87651104dd32ab258d097d47b97e243a95222 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:41 -0800 Subject: include/linux/generic-radix-tree.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. [akpm@linux-foundation.org: include math.h for round_up()] Link: https://lkml.kernel.org/r/20211027150548.80042-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/generic-radix-tree.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h index bfd00320c7f3..107613f7d792 100644 --- a/include/linux/generic-radix-tree.h +++ b/include/linux/generic-radix-tree.h @@ -38,8 +38,9 @@ #include #include -#include #include +#include +#include struct genradix_root; -- cgit v1.2.3 From e52340de11d8bca3ba35e5a72fea4f2a5b6abbbb Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Mon, 8 Nov 2021 18:32:43 -0800 Subject: kernel.h: split out instruction pointer accessors bottom_half.h needs _THIS_IP_ to be standalone, so split that and _RET_IP_ out from kernel.h into the new instruction_pointer.h. kernel.h directly needs them, so include it there and replace the include of kernel.h with this new file in bottom_half.h. Link: https://lkml.kernel.org/r/20211028161248.45232-1-andriy.shevchenko@linux.intel.com Signed-off-by: Stephen Rothwell Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bottom_half.h | 2 +- include/linux/instruction_pointer.h | 8 ++++++++ include/linux/kernel.h | 4 +--- 3 files changed, 10 insertions(+), 4 deletions(-) create mode 100644 include/linux/instruction_pointer.h (limited to 'include/linux') diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h index 11d107d88d03..fc53e0ad56d9 100644 --- a/include/linux/bottom_half.h +++ b/include/linux/bottom_half.h @@ -2,7 +2,7 @@ #ifndef _LINUX_BH_H #define _LINUX_BH_H -#include +#include #include #if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_TRACE_IRQFLAGS) diff --git a/include/linux/instruction_pointer.h b/include/linux/instruction_pointer.h new file mode 100644 index 000000000000..cda1f706eaeb --- /dev/null +++ b/include/linux/instruction_pointer.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_INSTRUCTION_POINTER_H +#define _LINUX_INSTRUCTION_POINTER_H + +#define _RET_IP_ (unsigned long)__builtin_return_address(0) +#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) + +#endif /* _LINUX_INSTRUCTION_POINTER_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index ed4465757cec..46ca4404fb93 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -53,9 +54,6 @@ } \ ) -#define _RET_IP_ (unsigned long)__builtin_return_address(0) -#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) - /** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing -- cgit v1.2.3 From e1edc277e6f6dfb372216522dfc57f9381c39e35 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 8 Nov 2021 18:32:46 -0800 Subject: linux/container_of.h: switch to static_assert _Static_assert() is evaluated already in the compiler's frontend, and gives a somehat more to-the-point error, compared to the BUILD_BUG_ON macro, which only fires after the optimizer has had a chance to eliminate calls to functions marked with __attribute__((error)). In theory, this might make builds a tiny bit faster. There's also a little less gunk in the error message emitted: lib/sort.c: In function `foo': include/linux/build_bug.h:78:41: error: static assertion failed: "pointer type mismatch in container_of()" 78 | #define __static_assert(expr, msg, ...) _Static_assert(expr, msg) compared to lib/sort.c: In function `foo': include/linux/compiler_types.h:322:38: error: call to `__compiletime_assert_2' declared with attribute error: pointer type mismatch in container_of() 322 | _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) While at it, fix the copy-pasto in container_of_safe(). Link: https://lkml.kernel.org/r/20211015090530.2774079-1-linux@rasmusvillemoes.dk Link: https://lore.kernel.org/lkml/20211014132331.GA4811@kernel.org/T/ Signed-off-by: Rasmus Villemoes Reviewed-by: Miguel Ojeda Acked-by: Andy Shevchenko Reviewed-by: Nick Desaulniers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/container_of.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/container_of.h b/include/linux/container_of.h index dd56019838c6..2f4944b791b8 100644 --- a/include/linux/container_of.h +++ b/include/linux/container_of.h @@ -16,9 +16,9 @@ */ #define container_of(ptr, type, member) ({ \ void *__mptr = (void *)(ptr); \ - BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ - !__same_type(*(ptr), void), \ - "pointer type mismatch in container_of()"); \ + static_assert(__same_type(*(ptr), ((type *)0)->member) || \ + __same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ ((type *)(__mptr - offsetof(type, member))); }) /** @@ -31,9 +31,9 @@ */ #define container_of_safe(ptr, type, member) ({ \ void *__mptr = (void *)(ptr); \ - BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ - !__same_type(*(ptr), void), \ - "pointer type mismatch in container_of()"); \ + static_assert(__same_type(*(ptr), ((type *)0)->member) || \ + __same_type(*(ptr), void), \ + "pointer type mismatch in container_of_safe()"); \ IS_ERR_OR_NULL(__mptr) ? ERR_CAST(__mptr) : \ ((type *)(__mptr - offsetof(type, member))); }) -- cgit v1.2.3 From 505be48165fa2f2cb795659b4fc61f35563d105e Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Mon, 8 Nov 2021 18:33:12 -0800 Subject: lib, stackdepot: add helper to print stack entries To print a stack entries, users of stackdepot, first use stack_depot_fetch to get a list of stack entries and then use stack_trace_print to print this list. Provide a helper in stackdepot to print stack entries based on stackdepot handle. Also change above mentioned users to use this helper. Link: https://lkml.kernel.org/r/20210915014806.3206938-3-imran.f.khan@oracle.com Signed-off-by: Imran Khan Suggested-by: Vlastimil Babka Acked-by: Vlastimil Babka Reviewed-by: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Daniel Vetter Cc: David Airlie Cc: Dmitry Vyukov Cc: Geert Uytterhoeven Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index d29860966bc9..8ab37500fcba 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -25,6 +25,8 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); +void stack_depot_print(depot_stack_handle_t stack); + #ifdef CONFIG_STACKDEPOT int stack_depot_init(void); #else -- cgit v1.2.3 From 0f68d45ef41abb618a9ca33996348ae73800a106 Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Mon, 8 Nov 2021 18:33:16 -0800 Subject: lib, stackdepot: add helper to print stack entries into buffer To print stack entries into a buffer, users of stackdepot, first get a list of stack entries using stack_depot_fetch and then print this list into a buffer using stack_trace_snprint. Provide a helper in stackdepot for this purpose. Also change above mentioned users to use this helper. [imran.f.khan@oracle.com: fix build error] Link: https://lkml.kernel.org/r/20210915175321.3472770-4-imran.f.khan@oracle.com [imran.f.khan@oracle.com: export stack_depot_snprint() to modules] Link: https://lkml.kernel.org/r/20210916133535.3592491-4-imran.f.khan@oracle.com Link: https://lkml.kernel.org/r/20210915014806.3206938-4-imran.f.khan@oracle.com Signed-off-by: Imran Khan Suggested-by: Vlastimil Babka Acked-by: Vlastimil Babka Acked-by: Jani Nikula [i915] Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Daniel Vetter Cc: David Airlie Cc: Dmitry Vyukov Cc: Geert Uytterhoeven Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 8ab37500fcba..c34b55a6e554 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -25,6 +25,9 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); +int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, + int spaces); + void stack_depot_print(depot_stack_handle_t stack); #ifdef CONFIG_STACKDEPOT -- cgit v1.2.3 From bfb3ba32061da1a9217ef6d02fbcffb528e4c8df Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Mon, 8 Nov 2021 18:33:19 -0800 Subject: include/linux/string_helpers.h: add linux/string.h for strlen() linux/string_helpers.h uses strlen(), so include the correponding header. Otherwise we get a compilation error if it's not also included by whoever included the helper. Link: https://lkml.kernel.org/r/20211005212634.3223113-1-lucas.demarchi@intel.com Signed-off-by: Lucas De Marchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string_helpers.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 68189c4a2eb1..4ba39e1403b2 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -4,6 +4,7 @@ #include #include +#include #include struct file; -- cgit v1.2.3 From 1b1ad288b8f1b11f83396e537003722897ecc12b Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:33:43 -0800 Subject: kallsyms: remove arch specific text and data check Patch series "sections: Unify kernel sections range check and use", v4. There are three head files(kallsyms.h, kernel.h and sections.h) which include the kernel sections range check, let's make some cleanup and unify them. 1. cleanup arch specific text/data check and fix address boundary check in kallsyms.h 2. make all the basic/core kernel range check function into sections.h 3. update all the callers, and use the helper in sections.h to simplify the code After this series, we have 5 APIs about kernel sections range check in sections.h * is_kernel_rodata() --- already in sections.h * is_kernel_core_data() --- come from core_kernel_data() in kernel.h * is_kernel_inittext() --- come from kernel.h and kallsyms.h * __is_kernel_text() --- add new internal helper * __is_kernel() --- add new internal helper Note: For the last two helpers, people should not use directly, consider to use corresponding function in kallsyms.h. This patch (of 11): Remove arch specific text and data check after commit 4ba66a976072 ("arch: remove blackfin port"), no need arch-specific text/data check. Link: https://lkml.kernel.org/r/20210930071143.63410-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20210930071143.63410-2-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Sergey Senozhatsky Cc: Arnd Bergmann Cc: Steven Rostedt Cc: Ingo Molnar Cc: David S. Miller Cc: Alexei Starovoitov Cc: Andrey Ryabinin Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Christophe Leroy Cc: Kefeng Wang Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Borislav Petkov Cc: Dmitry Vyukov Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michal Simek Cc: Petr Mladek Cc: Richard Henderson Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index a1d6fc82d7f0..bac340972670 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -34,8 +34,7 @@ static inline int is_kernel_inittext(unsigned long addr) static inline int is_kernel_text(unsigned long addr) { - if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) || - arch_is_kernel_text(addr)) + if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext)) return 1; return in_gate_area_no_mm(addr); } -- cgit v1.2.3 From e7d5c4b0eb9be6ea5c2cfb510a9d6f56925118eb Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:33:47 -0800 Subject: kallsyms: fix address-checks for kernel related range The is_kernel_inittext/is_kernel_text/is_kernel function should not include the end address(the labels _einittext, _etext and _end) when check the address range, the issue exists since Linux v2.6.12. Link: https://lkml.kernel.org/r/20210930071143.63410-3-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Petr Mladek Reviewed-by: Steven Rostedt (VMware) Acked-by: Sergey Senozhatsky Cc: Arnd Bergmann Cc: Alexander Potapenko Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: "David S. Miller" Cc: Dmitry Vyukov Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Paul Mackerras Cc: Richard Henderson Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index bac340972670..62ce22b27ea8 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -27,21 +27,21 @@ struct module; static inline int is_kernel_inittext(unsigned long addr) { if (addr >= (unsigned long)_sinittext - && addr <= (unsigned long)_einittext) + && addr < (unsigned long)_einittext) return 1; return 0; } static inline int is_kernel_text(unsigned long addr) { - if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext)) + if ((addr >= (unsigned long)_stext && addr < (unsigned long)_etext)) return 1; return in_gate_area_no_mm(addr); } static inline int is_kernel(unsigned long addr) { - if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end) + if (addr >= (unsigned long)_stext && addr < (unsigned long)_end) return 1; return in_gate_area_no_mm(addr); } -- cgit v1.2.3 From a20deb3a348719adaf8c12e1bf4b599bfc51836e Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:33:51 -0800 Subject: sections: move and rename core_kernel_data() to is_kernel_core_data() Move core_kernel_data() into sections.h and rename it to is_kernel_core_data(), also make it return bool value, then update all the callers. Link: https://lkml.kernel.org/r/20210930071143.63410-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Sergey Senozhatsky Cc: Arnd Bergmann Cc: Steven Rostedt Cc: Ingo Molnar Cc: "David S. Miller" Cc: Alexander Potapenko Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: Dmitry Vyukov Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Paul Mackerras Cc: Petr Mladek Cc: Richard Henderson Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 46ca4404fb93..23f57a2d5a13 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -227,7 +227,6 @@ extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); extern int init_kernel_text(unsigned long addr); -extern int core_kernel_data(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); extern int func_ptr_is_kernel_text(void *ptr); -- cgit v1.2.3 From b9ad8fe7b8cab3814d1de41e8ddca602b2646f4b Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:33:54 -0800 Subject: sections: move is_kernel_inittext() into sections.h The is_kernel_inittext() and init_kernel_text() are with same functionality, let's just keep is_kernel_inittext() and move it into sections.h, then update all the callers. Link: https://lkml.kernel.org/r/20210930071143.63410-5-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Sergey Senozhatsky Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Arnd Bergmann Cc: Alexander Potapenko Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: "David S. Miller" Cc: Dmitry Vyukov Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Paul Mackerras Cc: Petr Mladek Cc: Richard Henderson Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 8 -------- include/linux/kernel.h | 1 - 2 files changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 62ce22b27ea8..bb5d9ec78e13 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -24,14 +24,6 @@ struct cred; struct module; -static inline int is_kernel_inittext(unsigned long addr) -{ - if (addr >= (unsigned long)_sinittext - && addr < (unsigned long)_einittext) - return 1; - return 0; -} - static inline int is_kernel_text(unsigned long addr) { if ((addr >= (unsigned long)_stext && addr < (unsigned long)_etext)) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 23f57a2d5a13..be84ab369650 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -226,7 +226,6 @@ extern bool parse_option_str(const char *str, const char *option); extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); -extern int init_kernel_text(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); extern int func_ptr_is_kernel_text(void *ptr); -- cgit v1.2.3 From 8f6e42e83362650007ed298070a69d084f2c8baf Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:34:02 -0800 Subject: sections: provide internal __is_kernel() and __is_kernel_text() helper An internal __is_kernel() helper which only check the kernel address ranges, and an internal __is_kernel_text() helper which only check text section ranges. Link: https://lkml.kernel.org/r/20210930071143.63410-7-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Sergey Senozhatsky Cc: Alexander Potapenko Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: "David S. Miller" Cc: Dmitry Vyukov Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Paul Mackerras Cc: Petr Mladek Cc: Richard Henderson Cc: Steven Rostedt Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index bb5d9ec78e13..4176c7eca7b5 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -26,14 +26,14 @@ struct module; static inline int is_kernel_text(unsigned long addr) { - if ((addr >= (unsigned long)_stext && addr < (unsigned long)_etext)) + if (__is_kernel_text(addr)) return 1; return in_gate_area_no_mm(addr); } static inline int is_kernel(unsigned long addr) { - if (addr >= (unsigned long)_stext && addr < (unsigned long)_end) + if (__is_kernel(addr)) return 1; return in_gate_area_no_mm(addr); } -- cgit v1.2.3 From 5605f41917c6ad766814a8e417a4481e9157c991 Mon Sep 17 00:00:00 2001 From: Changcheng Deng Date: Mon, 8 Nov 2021 18:35:07 -0800 Subject: crash_dump: fix boolreturn.cocci warning ./include/linux/crash_dump.h: 119: 50-51: WARNING: return of 0/1 in function 'is_kdump_kernel' with return type bool Return statements in functions returning bool should use true/false instead of 1/0. Link: https://lkml.kernel.org/r/20211020083905.1037952-1-deng.changcheng@zte.com.cn Signed-off-by: Changcheng Deng Reported-by: Zeal Robot Reviewed-by: Simon Horman Acked-by: Baoquan He Cc: Dave Young Cc: Mike Rapoport Cc: Vivek Goyal Cc: Ye Guojin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 0c547d866f1e..979c26176c1d 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -116,7 +116,7 @@ extern void register_vmcore_cb(struct vmcore_cb *cb); extern void unregister_vmcore_cb(struct vmcore_cb *cb); #else /* !CONFIG_CRASH_DUMP */ -static inline bool is_kdump_kernel(void) { return 0; } +static inline bool is_kdump_kernel(void) { return false; } #endif /* CONFIG_CRASH_DUMP */ /* Device Dump information to be filled by drivers */ -- cgit v1.2.3 From a10677a028b853c25054a4b8be04013ccb55682f Mon Sep 17 00:00:00 2001 From: Ye Guojin Date: Mon, 8 Nov 2021 18:35:10 -0800 Subject: crash_dump: remove duplicate include in crash_dump.h In crash_dump.h, header file is included twice. This duplication was introduced in commit 65fddcfca8ad("mm: reorder includes after introduction of linux/pgtable.h") where the order of the header files is adjusted, while the old one was not removed. Clean it up here. Link: https://lkml.kernel.org/r/20211020090659.1038877-1-ye.guojin@zte.com.cn Signed-off-by: Ye Guojin Reported-by: Zeal Robot Acked-by: Baoquan He Cc: Dave Young Cc: Mike Rapoport Cc: Vivek Goyal Cc: Changcheng Deng Cc: Simon Horman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 979c26176c1d..620821549b23 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -8,8 +8,6 @@ #include #include -#include /* for pgprot_t */ - /* For IS_ENABLED(CONFIG_CRASH_DUMP) */ #define ELFCORE_ADDR_MAX (-1ULL) #define ELFCORE_ADDR_ERR (-2ULL) -- cgit v1.2.3 From f26663684e76773ea86e2df13fb18f9d66c91151 Mon Sep 17 00:00:00 2001 From: Ye Guojin Date: Mon, 8 Nov 2021 18:35:13 -0800 Subject: signal: remove duplicate include in signal.h 'linux/string.h' included in 'signal.h' is duplicated. it's also included at line 7. Link: https://lkml.kernel.org/r/20211019024934.973008-1-ye.guojin@zte.com.cn Signed-off-by: Ye Guojin Reported-by: Zeal Robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 3f96a6374e4f..37f5080c070a 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -126,7 +126,6 @@ static inline int sigequalsets(const sigset_t *set1, const sigset_t *set2) #define sigmask(sig) (1UL << ((sig) - 1)) #ifndef __HAVE_ARCH_SIG_SETOPS -#include #define _SIG_SET_BINOP(name, op) \ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ -- cgit v1.2.3 From 372904c080be44629d84bb15ed5e12eed44b5f9f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:35:16 -0800 Subject: seq_file: move seq_escape() to a header Move seq_escape() to the header as inliner, for a small kernel text size reduction. Link: https://lkml.kernel.org/r/20211001122917.67228-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index dd99569595fd..103776e18555 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -4,6 +4,7 @@ #include #include +#include #include #include #include @@ -135,7 +136,21 @@ static inline void seq_escape_str(struct seq_file *m, const char *src, seq_escape_mem(m, src, strlen(src), flags, esc); } -void seq_escape(struct seq_file *m, const char *s, const char *esc); +/** + * seq_escape - print string into buffer, escaping some characters + * @m: target buffer + * @s: NULL-terminated string + * @esc: set of characters that need escaping + * + * Puts string into buffer, replacing each occurrence of character from + * @esc with usual octal escape. + * + * Use seq_has_overflowed() to check for errors. + */ +static inline void seq_escape(struct seq_file *m, const char *s, const char *esc) +{ + seq_escape_str(m, s, ESCAPE_OCTAL, esc); +} void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, -- cgit v1.2.3 From 10a6de19cad6efb9b49883513afb810dc265fca2 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Mon, 8 Nov 2021 18:35:19 -0800 Subject: seq_file: fix passing wrong private data DEFINE_PROC_SHOW_ATTRIBUTE() is supposed to be used to define a series of functions and variables to register proc file easily. And the users can use proc_create_data() to pass their own private data and get it via seq->private in the callback. Unfortunately, the proc file system use PDE_DATA() to get private data instead of inode->i_private. So fix it. Fortunately, there only one user of it which does not pass any private data, so this bug does not break any in-tree codes. Link: https://lkml.kernel.org/r/20211029032638.84884-1-songmuchun@bytedance.com Fixes: 97a32539b956 ("proc: convert everything to "struct proc_ops"") Signed-off-by: Muchun Song Cc: Andy Shevchenko Cc: Stephen Rothwell Cc: Florent Revest Cc: Alexey Dobriyan Cc: Christian Brauner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 103776e18555..72dbb44a4573 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -209,7 +209,7 @@ static const struct file_operations __name ## _fops = { \ #define DEFINE_PROC_SHOW_ATTRIBUTE(__name) \ static int __name ## _open(struct inode *inode, struct file *file) \ { \ - return single_open(file, __name ## _show, inode->i_private); \ + return single_open(file, __name ## _show, PDE_DATA(inode)); \ } \ \ static const struct proc_ops __name ## _proc_ops = { \ -- cgit v1.2.3 From 278167fd2f8ffe679351605fe03e29ff3ab8db18 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Tue, 9 Nov 2021 16:29:49 -0800 Subject: block: add __must_check for *add_disk*() callers Now that we have done a spring cleaning on all drivers and added error checking / handling, let's keep it that way and ensure no new drivers fail to stick with it. Reviewed-by: Christoph Hellwig Signed-off-by: Luis Chamberlain Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20211110002949.999380-1-mcgrof@kernel.org Signed-off-by: Jens Axboe --- include/linux/genhd.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 462634b4b48f..74c410263113 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -205,9 +205,9 @@ static inline dev_t disk_devt(struct gendisk *disk) void disk_uevent(struct gendisk *disk, enum kobject_action action); /* block/genhd.c */ -int device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups); -static inline int add_disk(struct gendisk *disk) +int __must_check device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups); +static inline int __must_check add_disk(struct gendisk *disk) { return device_add_disk(NULL, disk, NULL); } -- cgit v1.2.3 From 5d5e4522a7f404d1a96fd6c703989d32a9c9568d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sun, 7 Nov 2021 14:51:16 +1000 Subject: printk: restore flushing of NMI buffers on remote CPUs after NMI backtraces printk from NMI context relies on irq work being raised on the local CPU to print to console. This can be a problem if the NMI was raised by a lockup detector to print lockup stack and regs, because the CPU may not enable irqs (because it is locked up). Introduce printk_trigger_flush() that can be called another CPU to try to get those messages to the console, call that where printk_safe_flush was previously called. Fixes: 93d102f094be ("printk: remove safe buffers") Cc: stable@vger.kernel.org # 5.15 Signed-off-by: Nicholas Piggin Reviewed-by: Petr Mladek Reviewed-by: John Ogness Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20211107045116.1754411-1-npiggin@gmail.com --- include/linux/printk.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index a1379df43251..596ad6fa0336 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -206,6 +206,7 @@ void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; +void printk_trigger_flush(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -282,6 +283,9 @@ static inline void dump_stack_lvl(const char *log_lvl) static inline void dump_stack(void) { } +static inline void printk_trigger_flush(void) +{ +} #endif #ifdef CONFIG_SMP -- cgit v1.2.3 From a19672f6b9718df247a9087a266150dbe833022e Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 12 Aug 2021 21:54:58 +0100 Subject: folio: Add a function to change the private data attached to a folio Add a function, folio_change_private(), that will change the private data attached to a folio, without the need to twiddle the private bit or the refcount. It assumes that folio_add_private() has already been called on the page. Signed-off-by: David Howells Reviewed-by: Matthew Wilcox (Oracle) Tested-by: Jeff Layton Tested-by: Dominique Martinet Tested-by: kafs-testing@auristor.com Link: https://lore.kernel.org/r/162981149911.1901565.17776700811659843340.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005743485.2472992.5100702469503007023.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584180781.4023316.5037526301198034310.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649324326.309189.17817587229450840783.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657848531.834781.14269656212269187893.stgit@warthog.procyon.org.uk/ # v5 --- include/linux/pagemap.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 6a30916b76e5..1f560aecd9b5 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -279,6 +279,25 @@ static inline void folio_attach_private(struct folio *folio, void *data) folio_set_private(folio); } +/** + * folio_change_private - Change private data on a folio. + * @folio: Folio to change the data on. + * @data: Data to set on the folio. + * + * Change the private data attached to a folio and return the old + * data. The page must previously have had data attached and the data + * must be detached before the folio will be freed. + * + * Return: Data that was previously attached to the folio. + */ +static inline void *folio_change_private(struct folio *folio, void *data) +{ + void *old = folio_get_private(folio); + + folio->private = data; + return old; +} + /** * folio_detach_private - Detach private data from a folio. * @folio: Folio to detach data from. -- cgit v1.2.3 From 452c472e26348df1e7052544130aa98eebbd2331 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 12 Aug 2021 22:09:57 +0100 Subject: folio: Add a function to get the host inode for a folio Add a convenience function, folio_inode() that will get the host inode from a folio's mapping. Changes: ver #3: - Fix mistake in function description[2]. ver #2: - Fix contradiction between doc and implementation by disallowing use with swap caches[1]. Signed-off-by: David Howells Reviewed-by: Matthew Wilcox (Oracle) Tested-by: Jeff Layton Tested-by: Dominique Martinet Tested-by: kafs-testing@auristor.com Link: https://lore.kernel.org/r/YST8OcVNy02Rivbm@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/YYKLkBwQdtn4ja+i@casper.infradead.org/ [2] Link: https://lore.kernel.org/r/162880453171.3369675.3704943108660112470.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162981151155.1901565.7010079316994382707.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005744370.2472992.18324470937328925723.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584184628.4023316.9386282630968981869.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649325519.309189.15072332908703129455.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657850401.834781.1031963517399283294.stgit@warthog.procyon.org.uk/ # v5 --- include/linux/pagemap.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1f560aecd9b5..1a0c646eb6ff 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -253,6 +253,20 @@ static inline struct address_space *page_mapping_file(struct page *page) return folio_mapping(folio); } +/** + * folio_inode - Get the host inode for this folio. + * @folio: The folio. + * + * For folios which are in the page cache, return the inode that this folio + * belongs to. + * + * Do not call this for folios which aren't in the page cache. + */ +static inline struct inode *folio_inode(struct folio *folio) +{ + return folio->mapping->host; +} + static inline bool page_cache_add_speculative(struct page *page, int count) { VM_BUG_ON_PAGE(PageTail(page), page); -- cgit v1.2.3 From 78525c74d9e7d1a6ce69bd4388f045f6e474a20b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 11 Aug 2021 09:49:13 +0100 Subject: netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells Reviewed-by: Jeff Layton Tested-by: Jeff Layton Tested-by: Dominique Martinet Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) cc: Marc Dionne cc: Ilya Dryomov cc: Dominique Martinet cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5 --- include/linux/netfs.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 12c4177f7703..ca0683b9e3d1 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -166,13 +166,13 @@ struct netfs_read_request { short error; /* 0 or error that occurred */ loff_t i_size; /* Size of the file */ loff_t start; /* Start position */ - pgoff_t no_unlock_page; /* Don't unlock this page after read */ + pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ refcount_t usage; unsigned long flags; #define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ #define NETFS_RREQ_WRITE_TO_CACHE 1 /* Need to write to the cache */ -#define NETFS_RREQ_NO_UNLOCK_PAGE 2 /* Don't unlock no_unlock_page on completion */ -#define NETFS_RREQ_DONT_UNLOCK_PAGES 3 /* Don't unlock the pages on completion */ +#define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ +#define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ const struct netfs_read_request_ops *netfs_ops; @@ -190,7 +190,7 @@ struct netfs_read_request_ops { void (*issue_op)(struct netfs_read_subrequest *subreq); bool (*is_still_valid)(struct netfs_read_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, - struct page *page, void **_fsdata); + struct folio *folio, void **_fsdata); void (*done)(struct netfs_read_request *rreq); void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; @@ -240,11 +240,11 @@ extern void netfs_readahead(struct readahead_control *, const struct netfs_read_request_ops *, void *); extern int netfs_readpage(struct file *, - struct page *, + struct folio *, const struct netfs_read_request_ops *, void *); extern int netfs_write_begin(struct file *, struct address_space *, - loff_t, unsigned int, unsigned int, struct page **, + loff_t, unsigned int, unsigned int, struct folio **, void **, const struct netfs_read_request_ops *, void *); -- cgit v1.2.3 From 68dbbe7d5b4fde736d104cbbc9a2fce875562012 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 4 Nov 2021 17:31:58 +0900 Subject: libata: fix read log timeout value Some ATA drives are very slow to respond to READ_LOG_EXT and READ_LOG_DMA_EXT commands issued from ata_dev_configure() when the device is revalidated right after resuming a system or inserting the ATA adapter driver (e.g. ahci). The default 5s timeout (ATA_EH_CMD_DFL_TIMEOUT) used for these commands is too short, causing errors during the device configuration. Ex: ... ata9: SATA max UDMA/133 abar m524288@0x9d200000 port 0x9d200400 irq 209 ata9: SATA link up 6.0 Gbps (SStatus 133 SControl 300) ata9.00: ATA-9: XXX XXXXXXXXXXXXXXX, XXXXXXXX, max UDMA/133 ata9.00: qc timeout (cmd 0x2f) ata9.00: Read log page 0x00 failed, Emask 0x4 ata9.00: Read log page 0x00 failed, Emask 0x40 ata9.00: NCQ Send/Recv Log not supported ata9.00: Read log page 0x08 failed, Emask 0x40 ata9.00: 27344764928 sectors, multi 16: LBA48 NCQ (depth 32), AA ata9.00: Read log page 0x00 failed, Emask 0x40 ata9.00: ATA Identify Device Log not supported ata9.00: failed to set xfermode (err_mask=0x40) ata9: SATA link up 6.0 Gbps (SStatus 133 SControl 300) ata9.00: configured for UDMA/133 ... The timeout error causes a soft reset of the drive link, followed in most cases by a successful revalidation as that give enough time to the drive to become fully ready to quickly process the read log commands. However, in some cases, this also fails resulting in the device being dropped. Fix this by using adding the ata_eh_revalidate_timeouts entries for the READ_LOG_EXT and READ_LOG_DMA_EXT commands. This defines a timeout increased to 15s, retriable one time. Reported-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 2884383f1718..5331557316e8 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -394,7 +394,7 @@ enum { /* This should match the actual table size of * ata_eh_cmd_timeout_table in libata-eh.c. */ - ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 6, + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 7, /* Horkage types. May be set by libata or controller on drives (some horkage may be drive/controller pair dependent */ -- cgit v1.2.3 From 9c8e9c9681a0f3f1ae90a90230d059c7a1dece5a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 4 Nov 2021 00:27:29 +0100 Subject: PCI/MSI: Move non-mask check back into low level accessors The recent rework of PCI/MSI[X] masking moved the non-mask checks from the low level accessors into the higher level mask/unmask functions. This missed the fact that these accessors can be invoked from other places as well. The missing checks break XEN-PV which sets pci_msi_ignore_mask and also violates the virtual MSIX and the msi_attrib.maskbit protections. Instead of sprinkling checks all over the place, lift them back into the low level accessor functions. To avoid checking three different conditions combine them into one property of msi_desc::msi_attrib. [ josef: Fixed the missed conversion in the core code ] Fixes: fcacdfbef5a1 ("PCI/MSI: Provide a new set of mask and unmask functions") Reported-by: Josef Johansson Signed-off-by: Thomas Gleixner Tested-by: Josef Johansson Cc: Bjorn Helgaas Cc: stable@vger.kernel.org --- include/linux/msi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 49cf6eb222e7..e616f94c7c58 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -148,7 +148,7 @@ struct msi_desc { u8 is_msix : 1; u8 multiple : 3; u8 multi_cap : 3; - u8 maskbit : 1; + u8 can_mask : 1; u8 is_64 : 1; u8 is_virtual : 1; u16 entry_nr; -- cgit v1.2.3 From 2226667a145db2e1f314d7f57fd644fe69863ab9 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 4 Nov 2021 18:01:29 +0000 Subject: PCI/MSI: Deal with devices lying about their MSI mask capability It appears that some devices are lying about their mask capability, pretending that they don't have it, while they actually do. The net result is that now that we don't enable MSIs on such endpoint. Add a new per-device flag to deal with this. Further patches will make use of it, sadly. Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20211104180130.3825416-2-maz@kernel.org Cc: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c8afbee5da4b..d0dba7fd9848 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -233,6 +233,8 @@ enum pci_dev_flags { PCI_DEV_FLAGS_NO_FLR_RESET = (__force pci_dev_flags_t) (1 << 10), /* Don't use Relaxed Ordering for TLPs directed at this device */ PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 11), + /* Device does honor MSI masking despite saying otherwise */ + PCI_DEV_FLAGS_HAS_MSI_MASKING = (__force pci_dev_flags_t) (1 << 12), }; enum pci_irq_reroute_variant { -- cgit v1.2.3 From a8b76910e465d718effce0cad306a21fa4f3526b Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 10 Nov 2021 20:24:44 +0000 Subject: preempt: Restore preemption model selection configs Commit c597bfddc9e9 ("sched: Provide Kconfig support for default dynamic preempt mode") changed the selectable config names for the preemption model. This means a config file must now select CONFIG_PREEMPT_BEHAVIOUR=y rather than CONFIG_PREEMPT=y to get a preemptible kernel. This means all arch config files would need to be updated - right now they'll all end up with the default CONFIG_PREEMPT_NONE_BEHAVIOUR. Rather than touch a good hundred of config files, restore usage of CONFIG_PREEMPT{_NONE, _VOLUNTARY}. Make them configure: o The build-time preemption model when !PREEMPT_DYNAMIC o The default boot-time preemption model when PREEMPT_DYNAMIC Add siblings of those configs with the _BUILD suffix to unconditionally designate the build-time preemption model (PREEMPT_DYNAMIC is built with the "highest" preemption model it supports, aka PREEMPT). Downstream configs should by now all be depending / selected by CONFIG_PREEMPTION rather than CONFIG_PREEMPT, so only a few sites need patching up. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Acked-by: Marco Elver Link: https://lore.kernel.org/r/20211110202448.4054153-2-valentin.schneider@arm.com --- include/linux/kernel.h | 2 +- include/linux/vermagic.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 968b4c4fe65b..77755ac3e189 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -85,7 +85,7 @@ struct completion; struct user; -#ifdef CONFIG_PREEMPT_VOLUNTARY +#ifdef CONFIG_PREEMPT_VOLUNTARY_BUILD extern int __cond_resched(void); # define might_resched() __cond_resched() diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 1eaaa93c37bf..329d63babaeb 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -15,7 +15,7 @@ #else #define MODULE_VERMAGIC_SMP "" #endif -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPT_BUILD #define MODULE_VERMAGIC_PREEMPT "preempt " #elif defined(CONFIG_PREEMPT_RT) #define MODULE_VERMAGIC_PREEMPT "preempt_rt " -- cgit v1.2.3 From 2f70ddb1f71814aae525c58086fcb2f6974e6591 Mon Sep 17 00:00:00 2001 From: Ashish Kalra Date: Tue, 24 Aug 2021 11:06:40 +0000 Subject: EFI: Introduce the new AMD Memory Encryption GUID. Introduce a new AMD Memory Encryption GUID which is currently used for defining a new UEFI environment variable which indicates UEFI/OVMF support for the SEV live migration feature. This variable is setup when UEFI/OVMF detects host/hypervisor support for SEV live migration and later this variable is read by the kernel using EFI runtime services to verify if OVMF supports the live migration feature. Signed-off-by: Ashish Kalra Acked-by: Ard Biesheuvel Message-Id: <1cea22976d2208f34d47e0c1ce0ecac816c13111.1629726117.git.ashish.kalra@amd.com> Signed-off-by: Paolo Bonzini --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 6b5d36babfcc..dbd39b20e034 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -362,6 +362,7 @@ void efi_native_runtime_setup(void); /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) +#define AMD_SEV_MEM_ENCRYPT_GUID EFI_GUID(0x0cf29b71, 0x9e51, 0x433a, 0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75) typedef struct { efi_guid_t guid; -- cgit v1.2.3 From f4d316537059b274452727e86f46ff3bdefdde4d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Nov 2021 10:13:38 -0500 Subject: KVM: generalize "bugged" VM to "dead" VM Generalize KVM_REQ_VM_BUGGED so that it can be called even in cases where it is by design that the VM cannot be operated upon. In this case any KVM_BUG_ON should still warn, so introduce a new flag kvm->vm_dead that is separate from kvm->vm_bugged. Suggested-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 60a35d9fe259..9e0667e3723e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -150,7 +150,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 -#define KVM_REQ_VM_BUGGED (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_VM_DEAD (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ @@ -617,6 +617,7 @@ struct kvm { unsigned int max_halt_poll_ns; u32 dirty_ring_size; bool vm_bugged; + bool vm_dead; #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; @@ -650,12 +651,19 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline void kvm_vm_dead(struct kvm *kvm) +{ + kvm->vm_dead = true; + kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD); +} + static inline void kvm_vm_bugged(struct kvm *kvm) { kvm->vm_bugged = true; - kvm_make_all_cpus_request(kvm, KVM_REQ_VM_BUGGED); + kvm_vm_dead(kvm); } + #define KVM_BUG(cond, kvm, fmt...) \ ({ \ int __ret = (cond); \ -- cgit v1.2.3 From 0093de693fe7baf31641d1863793e6db93a43b6e Mon Sep 17 00:00:00 2001 From: Yixuan Cao Date: Wed, 10 Nov 2021 20:32:30 -0800 Subject: mm/page_owner.c: modify the type of argument "order" in some functions The type of "order" in struct page_owner is unsigned short. However, it is unsigned int in the following 3 functions: __reset_page_owner __set_page_owner_handle __set_page_owner_handle The type of "order" in argument list is unsigned int, which is inconsistent. [akpm@linux-foundation.org: update include/linux/page_owner.h] Link: https://lkml.kernel.org/r/20211020125945.47792-1-caoyixuan2019@email.szu.edu.cn Signed-off-by: Yixuan Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_owner.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 43c638c51c1f..119a0c9d2a8b 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -8,9 +8,9 @@ extern struct static_key_false page_owner_inited; extern struct page_ext_operations page_owner_ops; -extern void __reset_page_owner(struct page *page, unsigned int order); +extern void __reset_page_owner(struct page *page, unsigned short order); extern void __set_page_owner(struct page *page, - unsigned int order, gfp_t gfp_mask); + unsigned short order, gfp_t gfp_mask); extern void __split_page_owner(struct page *page, unsigned int nr); extern void __folio_copy_owner(struct folio *newfolio, struct folio *old); extern void __set_page_owner_migrate_reason(struct page *page, int reason); @@ -18,14 +18,14 @@ extern void __dump_page_owner(const struct page *page); extern void pagetypeinfo_showmixedcount_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone); -static inline void reset_page_owner(struct page *page, unsigned int order) +static inline void reset_page_owner(struct page *page, unsigned short order) { if (static_branch_unlikely(&page_owner_inited)) __reset_page_owner(page, order); } static inline void set_page_owner(struct page *page, - unsigned int order, gfp_t gfp_mask) + unsigned short order, gfp_t gfp_mask) { if (static_branch_unlikely(&page_owner_inited)) __set_page_owner(page, order, gfp_mask); @@ -52,7 +52,7 @@ static inline void dump_page_owner(const struct page *page) __dump_page_owner(page); } #else -static inline void reset_page_owner(struct page *page, unsigned int order) +static inline void reset_page_owner(struct page *page, unsigned short order) { } static inline void set_page_owner(struct page *page, @@ -60,7 +60,7 @@ static inline void set_page_owner(struct page *page, { } static inline void split_page_owner(struct page *page, - unsigned int order) + unsigned short order) { } static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio) -- cgit v1.2.3 From ab09243aa95a72bac5c71e852773de34116f8d0f Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 10 Nov 2021 20:32:40 -0800 Subject: mm/migrate.c: remove MIGRATE_PFN_LOCKED MIGRATE_PFN_LOCKED is used to indicate to migrate_vma_prepare() that a source page was already locked during migrate_vma_collect(). If it wasn't then the a second attempt is made to lock the page. However if the first attempt failed it's unlikely a second attempt will succeed, and the retry adds complexity. So clean this up by removing the retry and MIGRATE_PFN_LOCKED flag. Destination pages are also meant to have the MIGRATE_PFN_LOCKED flag set, but nothing actually checks that. Link: https://lkml.kernel.org/r/20211025041608.289017-1-apopple@nvidia.com Signed-off-by: Alistair Popple Reviewed-by: Ralph Campbell Acked-by: Felix Kuehling Cc: Alex Deucher Cc: Jerome Glisse Cc: John Hubbard Cc: Zi Yan Cc: Christoph Hellwig Cc: Ben Skeggs Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index eeb818c4fc78..4850cc5bf813 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -110,7 +110,6 @@ static inline int migrate_misplaced_page(struct page *page, */ #define MIGRATE_PFN_VALID (1UL << 0) #define MIGRATE_PFN_MIGRATE (1UL << 1) -#define MIGRATE_PFN_LOCKED (1UL << 2) #define MIGRATE_PFN_WRITE (1UL << 3) #define MIGRATE_PFN_SHIFT 6 -- cgit v1.2.3 From 68da4e0eaaab421f228eac57cbe7505b136464af Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 10 Nov 2021 12:01:14 -0600 Subject: Revert "PCI: Remove struct pci_dev->driver" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit b5f9c644eb1baafcd349ad134e2110773f8d0a38. Revert b5f9c644eb1b ("PCI: Remove struct pci_dev->driver"), which is needed to revert 2a4d9408c9e8 ("PCI: Use to_pci_driver() instead of pci_dev->driver"). 2a4d9408c9e8 caused a NULL pointer dereference reported by Robert Święcki. Details in the revert of that commit. Fixes: 2a4d9408c9e8 ("PCI: Use to_pci_driver() instead of pci_dev->driver") Link: https://lore.kernel.org/linux-i2c/CAP145pgdrdiMAT7=-iB1DMgA7t_bMqTcJL4N0=6u8kNY3EU0dw@mail.gmail.com/ Reported-by: Robert Święcki Tested-by: Robert Święcki Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b4dbcc86b3f1..e58888e21ab7 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -342,6 +342,7 @@ struct pci_dev { u16 pcie_flags_reg; /* Cached PCIe Capabilities Register */ unsigned long *dma_alias_mask;/* Mask of enabled devfn aliases */ + struct pci_driver *driver; /* Driver bound to this device */ u64 dma_mask; /* Mask of the bits of bus address this device implements. Normally this is 0xffffffff. You only need to change -- cgit v1.2.3 From 636f6e2af4fb916b9f1b432964294b6979c34002 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 9 Nov 2021 08:45:25 +0900 Subject: libata: add horkage for missing Identify Device log ACS-3 introduced the ATA Identify Device Data log as mandatory. A warning message currently signals to the user if a device does not report supporting this log page in the log directory page, regardless of the ATA version of the device. Furthermore, this warning will appear for all attempts at accessing this missing log page during device revalidation. Since it is useless to constantly access the log directory and warn about this lack of support once we have discovered that the device does not support this log page, introduce the horkage flag ATA_HORKAGE_NO_ID_DEV_LOG to mark a device as lacking support for the Identify Device Data log page. Set this flag when ata_log_supported() returns false in ata_identify_page_supported(). The warning is printed only if the device ATA level is 10 or above (ACS-3 or above), and only once on device scan. With this flag set, the log directory page is not accessed again to test for Identify Device Data log page support. Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 5331557316e8..2a8404b26083 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -427,6 +427,7 @@ enum { ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ + ATA_HORKAGE_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 32a370abf12f82c8383e430c21365f5355d8b288 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 12 Nov 2021 12:07:02 -0500 Subject: net,lsm,selinux: revert the security_sctp_assoc_established() hook This patch reverts two prior patches, e7310c94024c ("security: implement sctp_assoc_established hook in selinux") and 7c2ef0240e6a ("security: add sctp_assoc_established hook"), which create the security_sctp_assoc_established() LSM hook and provide a SELinux implementation. Unfortunately these two patches were merged without proper review (the Reviewed-by and Tested-by tags from Richard Haines were for previous revisions of these patches that were significantly different) and there are outstanding objections from the SELinux maintainers regarding these patches. Work is currently ongoing to correct the problems identified in the reverted patches, as well as others that have come up during review, but it is unclear at this point in time when that work will be ready for inclusion in the mainline kernel. In the interest of not keeping objectionable code in the kernel for multiple weeks, and potentially a kernel release, we are reverting the two problematic patches. Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 2 -- include/linux/lsm_hooks.h | 5 ----- include/linux/security.h | 7 ------- 3 files changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 442a611fa0fb..df8de62f4710 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -335,8 +335,6 @@ LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) -LSM_HOOK(void, LSM_RET_VOID, sctp_assoc_established, struct sctp_association *asoc, - struct sk_buff *skb) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d6823214d5c1..d45b6f6e27fd 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1050,11 +1050,6 @@ * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. * @newsk pointer to new sock structure. - * @sctp_assoc_established: - * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet - * to the security module. - * @asoc pointer to sctp association structure. - * @skb pointer to skbuff of association packet. * * Security hooks for Infiniband * diff --git a/include/linux/security.h b/include/linux/security.h index 06eac4e61a13..bbf44a466832 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1430,8 +1430,6 @@ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); -void security_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb); #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, @@ -1651,11 +1649,6 @@ static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *newsk) { } - -static inline void security_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb) -{ -} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND -- cgit v1.2.3 From 1aa3b2207e889a948049c9a8016cedb0218c2389 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 12 Nov 2021 18:18:10 -0500 Subject: net,lsm,selinux: revert the security_sctp_assoc_established() hook This patch reverts two prior patches, e7310c94024c ("security: implement sctp_assoc_established hook in selinux") and 7c2ef0240e6a ("security: add sctp_assoc_established hook"), which create the security_sctp_assoc_established() LSM hook and provide a SELinux implementation. Unfortunately these two patches were merged without proper review (the Reviewed-by and Tested-by tags from Richard Haines were for previous revisions of these patches that were significantly different) and there are outstanding objections from the SELinux maintainers regarding these patches. Work is currently ongoing to correct the problems identified in the reverted patches, as well as others that have come up during review, but it is unclear at this point in time when that work will be ready for inclusion in the mainline kernel. In the interest of not keeping objectionable code in the kernel for multiple weeks, and potentially a kernel release, we are reverting the two problematic patches. Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- include/linux/lsm_hook_defs.h | 2 -- include/linux/lsm_hooks.h | 5 ----- include/linux/security.h | 7 ------- 3 files changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 442a611fa0fb..df8de62f4710 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -335,8 +335,6 @@ LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) -LSM_HOOK(void, LSM_RET_VOID, sctp_assoc_established, struct sctp_association *asoc, - struct sk_buff *skb) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d6823214d5c1..d45b6f6e27fd 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1050,11 +1050,6 @@ * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. * @newsk pointer to new sock structure. - * @sctp_assoc_established: - * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet - * to the security module. - * @asoc pointer to sctp association structure. - * @skb pointer to skbuff of association packet. * * Security hooks for Infiniband * diff --git a/include/linux/security.h b/include/linux/security.h index 06eac4e61a13..bbf44a466832 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1430,8 +1430,6 @@ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); -void security_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb); #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, @@ -1651,11 +1649,6 @@ static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *newsk) { } - -static inline void security_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb) -{ -} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND -- cgit v1.2.3 From 938aa33f14657c9ed9deea348b7d6f14b6d69cb7 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 14 Nov 2021 13:28:34 -0500 Subject: tracing: Add length protection to histogram string copies The string copies to the histogram storage has a max size of 256 bytes (defined by MAX_FILTER_STR_VAL). Only the string size of the event field needs to be copied to the event storage, but no more than what is in the event storage. Although nothing should be bigger than 256 bytes, there's no protection against overwriting of the storage if one day there is. Copy no more than the destination size, and enforce it. Also had to turn MAX_FILTER_STR_VAL into an unsigned int, to keep the min() comparison of the string sizes of comparable types. Link: https://lore.kernel.org/all/CAHk-=wjREUihCGrtRBwfX47y_KrLCGjiq3t6QtoNJpmVrAEb1w@mail.gmail.com/ Link: https://lkml.kernel.org/r/20211114132834.183429a4@rorschach.local.home Cc: Ingo Molnar Cc: Andrew Morton Cc: Tom Zanussi Reported-by: Linus Torvalds Reviewed-by: Masami Hiramatsu Fixes: 63f84ae6b82b ("tracing/histogram: Do not copy the fixed-size char array field over the field size") Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 50453b287615..2d167ac3452c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -673,7 +673,7 @@ struct trace_event_file { #define PERF_MAX_TRACE_SIZE 8192 -#define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ +#define MAX_FILTER_STR_VAL 256U /* Should handle KSYM_SYMBOL_LEN */ enum event_trigger_type { ETT_NONE = (0), -- cgit v1.2.3 From 10a2308ffb8cf262e473eb324fde42ae31b6da04 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Fri, 12 Nov 2021 18:16:34 +0800 Subject: net: Clean up some inconsistent indenting Eliminate the follow smatch warning: ./include/linux/skbuff.h:4229 skb_remcsum_process() warn: inconsistent indenting. Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 686a666d073d..c8cb7e697d47 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4226,7 +4226,7 @@ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, return; } - if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { + if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } -- cgit v1.2.3 From a0ddee65c527d877e798205c1391c6170e580c66 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 12 Nov 2021 16:07:49 +0200 Subject: printk: Remove printk.h inclusion in percpu.h After the commit 42a0bb3f7138 ("printk/nmi: generic solution for safe printk in NMI") the printk.h is not needed anymore in percpu.h. Moreover `make headerdep` complains (an excerpt) In file included from linux/printk.h, from linux/dynamic_debug.h:188 from linux/printk.h:559 <-- here from linux/percpu.h:9 from linux/idr.h:17 include/net/9p/client.h:13: warning: recursive header inclusion Yeah, it's not a root cause of this, but removing will help to reduce the noise. Fixes: 42a0bb3f7138 ("printk/nmi: generic solution for safe printk in NMI") Signed-off-by: Andy Shevchenko Acked-by: Dennis Zhou Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20211112140749.80042-1-andriy.shevchenko@linux.intel.com --- include/linux/percpu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 5e76af742c80..4fa3000f9c22 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -6,7 +6,6 @@ #include #include #include -#include #include #include -- cgit v1.2.3 From e9380df851878cee71df5a1c7611584421527f7e Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Sun, 31 Oct 2021 20:48:52 -0500 Subject: ACPI: Add stubs for wakeup handler functions The commit ddfd9dcf270c ("ACPI: PM: Add acpi_[un]register_wakeup_handler()") added new functions for drivers to use during the s2idle wakeup path, but didn't add stubs for when CONFIG_ACPI wasn't set. Add those stubs in for other drivers to be able to use. Fixes: ddfd9dcf270c ("ACPI: PM: Add acpi_[un]register_wakeup_handler()") Acked-by: Rafael J. Wysocki Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20211101014853.6177-1-mario.limonciello@amd.com Signed-off-by: Linus Walleij --- include/linux/acpi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 143ce7e0bee1..668d007f0917 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -974,6 +974,15 @@ static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) return -ENODEV; } +static inline int acpi_register_wakeup_handler(int wake_irq, + bool (*wakeup)(void *context), void *context) +{ + return -ENXIO; +} + +static inline void acpi_unregister_wakeup_handler( + bool (*wakeup)(void *context), void *context) { } + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- cgit v1.2.3 From a3143f7822a9eeb38f0e046080ae8f79f6c7122d Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 2 Nov 2021 16:01:58 -0600 Subject: Remove unused header Commit 6a80b30086b8 ("fmc: Delete the FMC subsystem") removed the last user of , but left the header file behind. Nothing uses this file, delete it now. Cc: Linus Walleij Cc: Alessandro Rubini Signed-off-by: Jonathan Corbet Acked-by: Alessandro Rubini Link: https://lore.kernel.org/r/20211102220203.940290-5-corbet@lwn.net Signed-off-by: Linus Walleij --- include/linux/sdb.h | 160 ---------------------------------------------------- 1 file changed, 160 deletions(-) delete mode 100644 include/linux/sdb.h (limited to 'include/linux') diff --git a/include/linux/sdb.h b/include/linux/sdb.h deleted file mode 100644 index a2404a2bbd10..000000000000 --- a/include/linux/sdb.h +++ /dev/null @@ -1,160 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This is the official version 1.1 of sdb.h - */ -#ifndef __SDB_H__ -#define __SDB_H__ -#ifdef __KERNEL__ -#include -#else -#include -#endif - -/* - * All structures are 64 bytes long and are expected - * to live in an array, one for each interconnect. - * Most fields of the structures are shared among the - * various types, and most-specific fields are at the - * beginning (for alignment reasons, and to keep the - * magic number at the head of the interconnect record - */ - -/* Product, 40 bytes at offset 24, 8-byte aligned - * - * device_id is vendor-assigned; version is device-specific, - * date is hex (e.g 0x20120501), name is UTF-8, blank-filled - * and not terminated with a 0 byte. - */ -struct sdb_product { - uint64_t vendor_id; /* 0x18..0x1f */ - uint32_t device_id; /* 0x20..0x23 */ - uint32_t version; /* 0x24..0x27 */ - uint32_t date; /* 0x28..0x2b */ - uint8_t name[19]; /* 0x2c..0x3e */ - uint8_t record_type; /* 0x3f */ -}; - -/* - * Component, 56 bytes at offset 8, 8-byte aligned - * - * The address range is first to last, inclusive - * (for example 0x100000 - 0x10ffff) - */ -struct sdb_component { - uint64_t addr_first; /* 0x08..0x0f */ - uint64_t addr_last; /* 0x10..0x17 */ - struct sdb_product product; /* 0x18..0x3f */ -}; - -/* Type of the SDB record */ -enum sdb_record_type { - sdb_type_interconnect = 0x00, - sdb_type_device = 0x01, - sdb_type_bridge = 0x02, - sdb_type_integration = 0x80, - sdb_type_repo_url = 0x81, - sdb_type_synthesis = 0x82, - sdb_type_empty = 0xFF, -}; - -/* Type 0: interconnect (first of the array) - * - * sdb_records is the length of the table including this first - * record, version is 1. The bus type is enumerated later. - */ -#define SDB_MAGIC 0x5344422d /* "SDB-" */ -struct sdb_interconnect { - uint32_t sdb_magic; /* 0x00-0x03 */ - uint16_t sdb_records; /* 0x04-0x05 */ - uint8_t sdb_version; /* 0x06 */ - uint8_t sdb_bus_type; /* 0x07 */ - struct sdb_component sdb_component; /* 0x08-0x3f */ -}; - -/* Type 1: device - * - * class is 0 for "custom device", other values are - * to be standardized; ABI version is for the driver, - * bus-specific bits are defined by each bus (see below) - */ -struct sdb_device { - uint16_t abi_class; /* 0x00-0x01 */ - uint8_t abi_ver_major; /* 0x02 */ - uint8_t abi_ver_minor; /* 0x03 */ - uint32_t bus_specific; /* 0x04-0x07 */ - struct sdb_component sdb_component; /* 0x08-0x3f */ -}; - -/* Type 2: bridge - * - * child is the address of the nested SDB table - */ -struct sdb_bridge { - uint64_t sdb_child; /* 0x00-0x07 */ - struct sdb_component sdb_component; /* 0x08-0x3f */ -}; - -/* Type 0x80: integration - * - * all types with bit 7 set are meta-information, so - * software can ignore the types it doesn't know. Here we - * just provide product information for an aggregate device - */ -struct sdb_integration { - uint8_t reserved[24]; /* 0x00-0x17 */ - struct sdb_product product; /* 0x08-0x3f */ -}; - -/* Type 0x81: Top module repository url - * - * again, an informative field that software can ignore - */ -struct sdb_repo_url { - uint8_t repo_url[63]; /* 0x00-0x3e */ - uint8_t record_type; /* 0x3f */ -}; - -/* Type 0x82: Synthesis tool information - * - * this informative record - */ -struct sdb_synthesis { - uint8_t syn_name[16]; /* 0x00-0x0f */ - uint8_t commit_id[16]; /* 0x10-0x1f */ - uint8_t tool_name[8]; /* 0x20-0x27 */ - uint32_t tool_version; /* 0x28-0x2b */ - uint32_t date; /* 0x2c-0x2f */ - uint8_t user_name[15]; /* 0x30-0x3e */ - uint8_t record_type; /* 0x3f */ -}; - -/* Type 0xff: empty - * - * this allows keeping empty slots during development, - * so they can be filled later with minimal efforts and - * no misleading description is ever shipped -- hopefully. - * It can also be used to pad a table to a desired length. - */ -struct sdb_empty { - uint8_t reserved[63]; /* 0x00-0x3e */ - uint8_t record_type; /* 0x3f */ -}; - -/* The type of bus, for bus-specific flags */ -enum sdb_bus_type { - sdb_wishbone = 0x00, - sdb_data = 0x01, -}; - -#define SDB_WB_WIDTH_MASK 0x0f -#define SDB_WB_ACCESS8 0x01 -#define SDB_WB_ACCESS16 0x02 -#define SDB_WB_ACCESS32 0x04 -#define SDB_WB_ACCESS64 0x08 -#define SDB_WB_LITTLE_ENDIAN 0x80 - -#define SDB_DATA_READ 0x04 -#define SDB_DATA_WRITE 0x02 -#define SDB_DATA_EXEC 0x01 - -#endif /* __SDB_H__ */ -- cgit v1.2.3 From 353050be4c19e102178ccc05988101887c25ae53 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Nov 2021 18:48:08 +0000 Subject: bpf: Fix toctou on read-only map's constant scalar tracking Commit a23740ec43ba ("bpf: Track contents of read-only maps as scalars") is checking whether maps are read-only both from BPF program side and user space side, and then, given their content is constant, reading out their data via map->ops->map_direct_value_addr() which is then subsequently used as known scalar value for the register, that is, it is marked as __mark_reg_known() with the read value at verification time. Before a23740ec43ba, the register content was marked as an unknown scalar so the verifier could not make any assumptions about the map content. The current implementation however is prone to a TOCTOU race, meaning, the value read as known scalar for the register is not guaranteed to be exactly the same at a later point when the program is executed, and as such, the prior made assumptions of the verifier with regards to the program will be invalid which can cause issues such as OOB access, etc. While the BPF_F_RDONLY_PROG map flag is always fixed and required to be specified at map creation time, the map->frozen property is initially set to false for the map given the map value needs to be populated, e.g. for global data sections. Once complete, the loader "freezes" the map from user space such that no subsequent updates/deletes are possible anymore. For the rest of the lifetime of the map, this freeze one-time trigger cannot be undone anymore after a successful BPF_MAP_FREEZE cmd return. Meaning, any new BPF_* cmd calls which would update/delete map entries will be rejected with -EPERM since map_get_sys_perms() removes the FMODE_CAN_WRITE permission. This also means that pending update/delete map entries must still complete before this guarantee is given. This corner case is not an issue for loaders since they create and prepare such program private map in successive steps. However, a malicious user is able to trigger this TOCTOU race in two different ways: i) via userfaultfd, and ii) via batched updates. For i) userfaultfd is used to expand the competition interval, so that map_update_elem() can modify the contents of the map after map_freeze() and bpf_prog_load() were executed. This works, because userfaultfd halts the parallel thread which triggered a map_update_elem() at the time where we copy key/value from the user buffer and this already passed the FMODE_CAN_WRITE capability test given at that time the map was not "frozen". Then, the main thread performs the map_freeze() and bpf_prog_load(), and once that had completed successfully, the other thread is woken up to complete the pending map_update_elem() which then changes the map content. For ii) the idea of the batched update is similar, meaning, when there are a large number of updates to be processed, it can increase the competition interval between the two. It is therefore possible in practice to modify the contents of the map after executing map_freeze() and bpf_prog_load(). One way to fix both i) and ii) at the same time is to expand the use of the map's map->writecnt. The latter was introduced in fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY") and further refined in 1f6cb19be2e2 ("bpf: Prevent re-mmap()'ing BPF map as writable for initially r/o mapping") with the rationale to make a writable mmap()'ing of a map mutually exclusive with read-only freezing. The counter indicates writable mmap() mappings and then prevents/fails the freeze operation. Its semantics can be expanded beyond just mmap() by generally indicating ongoing write phases. This would essentially span any parallel regular and batched flavor of update/delete operation and then also have map_freeze() fail with -EBUSY. For the check_mem_access() in the verifier we expand upon the bpf_map_is_rdonly() check ensuring that all last pending writes have completed via bpf_map_write_active() test. Once the map->frozen is set and bpf_map_write_active() indicates a map->writecnt of 0 only then we are really guaranteed to use the map's data as known constants. For map->frozen being set and pending writes in process of still being completed we fall back to marking that register as unknown scalar so we don't end up making assumptions about it. With this, both TOCTOU reproducers from i) and ii) are fixed. Note that the map->writecnt has been converted into a atomic64 in the fix in order to avoid a double freeze_mutex mutex_{un,}lock() pair when updating map->writecnt in the various map update/delete BPF_* cmd flavors. Spanning the freeze_mutex over entire map update/delete operations in syscall side would not be possible due to then causing everything to be serialized. Similarly, something like synchronize_rcu() after setting map->frozen to wait for update/deletes to complete is not possible either since it would also have to span the user copy which can sleep. On the libbpf side, this won't break d66562fba1ce ("libbpf: Add BPF object skeleton support") as the anonymous mmap()-ed "map initialization image" is remapped as a BPF map-backed mmap()-ed memory where for .rodata it's non-writable. Fixes: a23740ec43ba ("bpf: Track contents of read-only maps as scalars") Reported-by: w1tcher.bupt@gmail.com Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f715e8863f4d..e7a163a3146b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -193,7 +193,7 @@ struct bpf_map { atomic64_t usercnt; struct work_struct work; struct mutex freeze_mutex; - u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */ + atomic64_t writecnt; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -1419,6 +1419,7 @@ void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); +bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, -- cgit v1.2.3 From d7751d6476185ff754b9dad2cba0c0a6e43ecadc Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 20 May 2021 17:09:58 +0300 Subject: net/mlx5: E-Switch, Fix resetting of encap mode when entering switchdev E-Switch encap mode is relevant only when in switchdev mode. The RDMA driver can query the encap configuration via mlx5_eswitch_get_encap_mode(). Make sure it returns the currently used mode and not the set one. This reverts the cited commit which reset the encap mode on entering switchdev and fixes the original issue properly. Fixes: 9a64144d683a ("net/mlx5: E-Switch, Fix default encap mode") Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 97afcea39a7b..8b18fe9771f9 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -145,13 +145,13 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \ ESW_TUN_OPTS_OFFSET + 1) -u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); +u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ -static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) +static inline u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { return MLX5_ESWITCH_NONE; } -- cgit v1.2.3 From cf9acc90c80ecbee00334aa85d92f4e74014bcff Mon Sep 17 00:00:00 2001 From: Jonathan Davies Date: Tue, 16 Nov 2021 17:42:42 +0000 Subject: net: virtio_net_hdr_to_skb: count transport header in UFO virtio_net_hdr_to_skb does not set the skb's gso_size and gso_type correctly for UFO packets received via virtio-net that are a little over the GSO size. This can lead to problems elsewhere in the networking stack, e.g. ovs_vport_send dropping over-sized packets if gso_size is not set. This is due to the comparison if (skb->len - p_off > gso_size) not properly accounting for the transport layer header. p_off includes the size of the transport layer header (thlen), so skb->len - p_off is the size of the TCP/UDP payload. gso_size is read from the virtio-net header. For UFO, fragmentation happens at the IP level so does not need to include the UDP header. Hence the calculation could be comparing a TCP/UDP payload length with an IP payload length, causing legitimate virtio-net packets to have lack gso_type/gso_size information. Example: a UDP packet with payload size 1473 has IP payload size 1481. If the guest used UFO, it is not fragmented and the virtio-net header's flags indicate that it is a GSO frame (VIRTIO_NET_HDR_GSO_UDP), with gso_size = 1480 for an MTU of 1500. skb->len will be 1515 and p_off will be 42, so skb->len - p_off = 1473. Hence the comparison fails, and shinfo->gso_size and gso_type are not set as they should be. Instead, add the UDP header length before comparing to gso_size when using UFO. In this way, it is the size of the IP payload that is compared to gso_size. Fixes: 6dd912f82680 ("net: check untrusted gso_size at kernel entry") Signed-off-by: Jonathan Davies Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index b465f8f3e554..04e87f4b9417 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -120,10 +120,15 @@ retry: if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); + unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); + /* UFO may not include transport header in gso_size. */ + if (gso_type & SKB_GSO_UDP) + nh_off -= thlen; + /* Too small packets are not really GSO ones. */ - if (skb->len - p_off > gso_size) { + if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; shinfo->gso_type = gso_type; -- cgit v1.2.3 From 357a18ad230f0867791b788d2b1d6f280f6f6e61 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 15 Nov 2021 16:50:27 +0000 Subject: KVM: Kill kvm_map_gfn() / kvm_unmap_gfn() and gfn_to_pfn_cache In commit 7e2175ebd695 ("KVM: x86: Fix recording of guest steal time / preempted status") I removed the only user of these functions because it was basically impossible to use them safely. There are two stages to the GFN->PFN mapping; first through the KVM memslots to a userspace HVA and then through the page tables to translate that HVA to an underlying PFN. Invalidations of the former were being handled correctly, but no attempt was made to use the MMU notifiers to invalidate the cache when the HVA->GFN mapping changed. As a prelude to reinventing the gfn_to_pfn_cache with more usable semantics, rip it out entirely and untangle the implementation of the unsafe kvm_vcpu_map()/kvm_vcpu_unmap() functions from it. All current users of kvm_vcpu_map() also look broken right now, and will be dealt with separately. They broadly fall into two classes: * Those which map, access the data and immediately unmap. This is mostly gratuitous and could just as well use the existing user HVA, and could probably benefit from a gfn_to_hva_cache as they do so. * Those which keep the mapping around for a longer time, perhaps even using the PFN directly from the guest. These will need to be converted to the new gfn_to_pfn_cache and then kvm_vcpu_map() can be removed too. Signed-off-by: David Woodhouse Message-Id: <20211115165030.7422-8-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 6 +----- include/linux/kvm_types.h | 7 ------- 2 files changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 60a35d9fe259..eb625af4fc5e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -866,7 +866,7 @@ void kvm_release_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_accessed(kvm_pfn_t pfn); -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache); +void kvm_release_pfn(kvm_pfn_t pfn, bool dirty); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); @@ -942,12 +942,8 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool atomic); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool dirty, bool atomic); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 2237abb93ccd..234eab059839 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -53,13 +53,6 @@ struct gfn_to_hva_cache { struct kvm_memory_slot *memslot; }; -struct gfn_to_pfn_cache { - u64 generation; - gfn_t gfn; - kvm_pfn_t pfn; - bool dirty; -}; - #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE /* * Memory caches are used to preallocate memory ahead of various MMU flows, -- cgit v1.2.3 From f915b75bffb7257bd8d26376b8e1cc67771927f8 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 17 Nov 2021 15:56:52 +0800 Subject: page_pool: Revert "page_pool: disable dma mapping support..." This reverts commit d00e60ee54b12de945b8493cf18c1ada9e422514. As reported by Guillaume in [1]: Enabling LPAE always enables CONFIG_ARCH_DMA_ADDR_T_64BIT in 32-bit systems, which breaks the bootup proceess when a ethernet driver is using page pool with PP_FLAG_DMA_MAP flag. As we were hoping we had no active consumers for such system when we removed the dma mapping support, and LPAE seems like a common feature for 32 bits system, so revert it. 1. https://www.spinics.net/lists/netdev/msg779890.html Fixes: d00e60ee54b1 ("page_pool: disable dma mapping support for 32-bit arch with 64-bit DMA") Signed-off-by: Yunsheng Lin Reported-by: "kernelci.org bot" Tested-by: "kernelci.org bot" Acked-by: Jesper Dangaard Brouer Acked-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/linux/mm_types.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bb8c6f5f19bc..c3a6e6209600 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -105,7 +105,18 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - atomic_long_t pp_frag_count; + union { + /** + * dma_addr_upper: might require a 64-bit + * value on 32-bit architectures. + */ + unsigned long dma_addr_upper; + /** + * For frag page support, not supported in + * 32-bit architectures with 64-bit DMA. + */ + atomic_long_t pp_frag_count; + }; }; struct { /* slab, slob and slub */ union { -- cgit v1.2.3 From fcb116bc43c8c37c052530ead79872f8b2615711 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 18 Nov 2021 14:23:21 -0600 Subject: signal: Replace force_fatal_sig with force_exit_sig when in doubt Recently to prevent issues with SECCOMP_RET_KILL and similar signals being changed before they are delivered SA_IMMUTABLE was added. Unfortunately this broke debuggers[1][2] which reasonably expect to be able to trap synchronous SIGTRAP and SIGSEGV even when the target process is not configured to handle those signals. Add force_exit_sig and use it instead of force_fatal_sig where historically the code has directly called do_exit. This has the implementation benefits of going through the signal exit path (including generating core dumps) without the danger of allowing userspace to ignore or change these signals. This avoids userspace regressions as older kernels exited with do_exit which debuggers also can not intercept. In the future is should be possible to improve the quality of implementation of the kernel by changing some of these force_exit_sig calls to force_fatal_sig. That can be done where it matters on a case-by-case basis with careful analysis. Reported-by: Kyle Huey Reported-by: kernel test robot [1] https://lkml.kernel.org/r/CAP045AoMY4xf8aC_4QU_-j7obuEPYgTcnQQP3Yxk=2X90jtpjw@mail.gmail.com [2] https://lkml.kernel.org/r/20211117150258.GB5403@xsang-OptiPlex-9020 Fixes: 00b06da29cf9 ("signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed") Fixes: a3616a3c0272 ("signal/m68k: Use force_sigsegv(SIGSEGV) in fpsp040_die") Fixes: 83a1f27ad773 ("signal/powerpc: On swapcontext failure force SIGSEGV") Fixes: 9bc508cf0791 ("signal/s390: Use force_sigsegv in default_trap_handler") Fixes: 086ec444f866 ("signal/sparc32: In setup_rt_frame and setup_fram use force_fatal_sig") Fixes: c317d306d550 ("signal/sparc32: Exit with a fatal signal when try_to_clear_window_buffer fails") Fixes: 695dd0d634df ("signal/x86: In emulate_vsyscall force a signal instead of calling do_exit") Fixes: 1fbd60df8a85 ("signal/vm86_32: Properly send SIGSEGV when the vm86 state cannot be saved.") Fixes: 941edc5bf174 ("exit/syscall_user_dispatch: Send ordinary signals on failure") Link: https://lkml.kernel.org/r/871r3dqfv8.fsf_-_@email.froward.int.ebiederm.org Reviewed-by: Kees Cook Tested-by: Kees Cook Tested-by: Kyle Huey Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 23505394ef70..33a50642cf41 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -352,6 +352,7 @@ extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); extern void force_fatal_sig(int); +extern void force_exit_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); -- cgit v1.2.3 From 85b6d24646e4125c591639841169baa98a2da503 Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Fri, 19 Nov 2021 16:43:21 -0800 Subject: shm: extend forced shm destroy to support objects from several IPC nses Currently, the exit_shm() function not designed to work properly when task->sysvshm.shm_clist holds shm objects from different IPC namespaces. This is a real pain when sysctl kernel.shm_rmid_forced = 1, because it leads to use-after-free (reproducer exists). This is an attempt to fix the problem by extending exit_shm mechanism to handle shm's destroy from several IPC ns'es. To achieve that we do several things: 1. add a namespace (non-refcounted) pointer to the struct shmid_kernel 2. during new shm object creation (newseg()/shmget syscall) we initialize this pointer by current task IPC ns 3. exit_shm() fully reworked such that it traverses over all shp's in task->sysvshm.shm_clist and gets IPC namespace not from current task as it was before but from shp's object itself, then call shm_destroy(shp, ns). Note: We need to be really careful here, because as it was said before (1), our pointer to IPC ns non-refcnt'ed. To be on the safe side we using special helper get_ipc_ns_not_zero() which allows to get IPC ns refcounter only if IPC ns not in the "state of destruction". Q/A Q: Why can we access shp->ns memory using non-refcounted pointer? A: Because shp object lifetime is always shorther than IPC namespace lifetime, so, if we get shp object from the task->sysvshm.shm_clist while holding task_lock(task) nobody can steal our namespace. Q: Does this patch change semantics of unshare/setns/clone syscalls? A: No. It's just fixes non-covered case when process may leave IPC namespace without getting task->sysvshm.shm_clist list cleaned up. Link: https://lkml.kernel.org/r/67bb03e5-f79c-1815-e2bf-949c67047418@colorfullife.com Link: https://lkml.kernel.org/r/20211109151501.4921-1-manfred@colorfullife.com Fixes: ab602f79915 ("shm: make exit_shm work proportional to task activity") Co-developed-by: Manfred Spraul Signed-off-by: Manfred Spraul Signed-off-by: Alexander Mikhalitsyn Cc: "Eric W. Biederman" Cc: Davidlohr Bueso Cc: Greg KH Cc: Andrei Vagin Cc: Pavel Tikhomirov Cc: Vasily Averin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 15 +++++++++++++++ include/linux/sched/task.h | 2 +- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 05e22770af51..b75395ec8d52 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -131,6 +131,16 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) return ns; } +static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) +{ + if (ns) { + if (refcount_inc_not_zero(&ns->ns.count)) + return ns; + } + + return NULL; +} + extern void put_ipc_ns(struct ipc_namespace *ns); #else static inline struct ipc_namespace *copy_ipcs(unsigned long flags, @@ -147,6 +157,11 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) return ns; } +static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) +{ + return ns; +} + static inline void put_ipc_ns(struct ipc_namespace *ns) { } diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index ba88a6987400..058d7f371e25 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -158,7 +158,7 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and - * ->cgroup.subsys[]. And ->vfork_done. + * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), -- cgit v1.2.3 From afe041c2d0febd83698b8b0164e6b3b1dfae0b66 Mon Sep 17 00:00:00 2001 From: Bui Quang Minh Date: Fri, 19 Nov 2021 16:43:40 -0800 Subject: hugetlb: fix hugetlb cgroup refcounting during mremap When hugetlb_vm_op_open() is called during copy_vma(), we may take the reference to resv_map->css. Later, when clearing the reservation pointer of old_vma after transferring it to new_vma, we forget to drop the reference to resv_map->css. This leads to a reference leak of css. Fixes this by adding a check to drop reservation css reference in clear_vma_resv_huge_pages() Link: https://lkml.kernel.org/r/20211113154412.91134-1-minhquangbui99@gmail.com Fixes: 550a7d60bd5e35 ("mm, hugepages: add mremap() support for hugepage backed vma") Signed-off-by: Bui Quang Minh Reviewed-by: Mike Kravetz Reviewed-by: Mina Almasry Cc: Miaohe Lin Cc: Michal Hocko Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb_cgroup.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index c137396129db..ba025ae27882 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -128,6 +128,13 @@ static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( css_get(resv_map->css); } +static inline void resv_map_put_hugetlb_cgroup_uncharge_info( + struct resv_map *resv_map) +{ + if (resv_map->css) + css_put(resv_map->css); +} + extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, @@ -211,6 +218,11 @@ static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( { } +static inline void resv_map_put_hugetlb_cgroup_uncharge_info( + struct resv_map *resv_map) +{ +} + static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { -- cgit v1.2.3 From 9e3562080950b6e3fe38a5e34ddd5b1c618f2019 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 2 Dec 2021 10:53:33 +0100 Subject: HID: add suspend/resume helpers There is a lot of duplication of code in the HID low level drivers. Better have everything in one place so we can eventually extend it in a generic way. Signed-off-by: Benjamin Tissoires Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20211202095334.14399-4-benjamin.tissoires@redhat.com --- include/linux/hid.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 9e067f937dbc..ebe3ec98db6b 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -923,6 +923,16 @@ s32 hid_snto32(__u32 value, unsigned n); __u32 hid_field_extract(const struct hid_device *hid, __u8 *report, unsigned offset, unsigned n); +#ifdef CONFIG_PM +int hid_driver_suspend(struct hid_device *hdev, pm_message_t state); +int hid_driver_reset_resume(struct hid_device *hdev); +int hid_driver_resume(struct hid_device *hdev); +#else +static inline int hid_driver_suspend(struct hid_device *hdev, pm_message_t state) { return 0; } +static inline int hid_driver_reset_resume(struct hid_device *hdev) { return 0; } +static inline int hid_driver_resume(struct hid_device *hdev) { return 0; } +#endif + /** * hid_device_io_start - enable HID input during probe, remove * -- cgit v1.2.3 From f65a0b1f3e79444bba9ac56435eeb32db85ab2c9 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 2 Dec 2021 10:53:34 +0100 Subject: HID: do not inline some hid_hw_ functions We don't gain much by having them as inline, and it actually prevents us to attach a probe to those helpers. Signed-off-by: Benjamin Tissoires Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20211202095334.14399-5-benjamin.tissoires@redhat.com --- include/linux/hid.h | 68 +++++------------------------------------------------ 1 file changed, 6 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index ebe3ec98db6b..b2fea7fc54a1 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1066,6 +1066,12 @@ int __must_check hid_hw_start(struct hid_device *hdev, void hid_hw_stop(struct hid_device *hdev); int __must_check hid_hw_open(struct hid_device *hdev); void hid_hw_close(struct hid_device *hdev); +void hid_hw_request(struct hid_device *hdev, + struct hid_report *report, int reqtype); +int hid_hw_raw_request(struct hid_device *hdev, + unsigned char reportnum, __u8 *buf, + size_t len, unsigned char rtype, int reqtype); +int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len); /** * hid_hw_power - requests underlying HW to go into given power mode @@ -1083,68 +1089,6 @@ static inline int hid_hw_power(struct hid_device *hdev, int level) } -/** - * hid_hw_request - send report request to device - * - * @hdev: hid device - * @report: report to send - * @reqtype: hid request type - */ -static inline void hid_hw_request(struct hid_device *hdev, - struct hid_report *report, int reqtype) -{ - if (hdev->ll_driver->request) - return hdev->ll_driver->request(hdev, report, reqtype); - - __hid_request(hdev, report, reqtype); -} - -/** - * hid_hw_raw_request - send report request to device - * - * @hdev: hid device - * @reportnum: report ID - * @buf: in/out data to transfer - * @len: length of buf - * @rtype: HID report type - * @reqtype: HID_REQ_GET_REPORT or HID_REQ_SET_REPORT - * - * Return: count of data transferred, negative if error - * - * Same behavior as hid_hw_request, but with raw buffers instead. - */ -static inline int hid_hw_raw_request(struct hid_device *hdev, - unsigned char reportnum, __u8 *buf, - size_t len, unsigned char rtype, int reqtype) -{ - if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf) - return -EINVAL; - - return hdev->ll_driver->raw_request(hdev, reportnum, buf, len, - rtype, reqtype); -} - -/** - * hid_hw_output_report - send output report to device - * - * @hdev: hid device - * @buf: raw data to transfer - * @len: length of buf - * - * Return: count of data transferred, negative if error - */ -static inline int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, - size_t len) -{ - if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf) - return -EINVAL; - - if (hdev->ll_driver->output_report) - return hdev->ll_driver->output_report(hdev, buf, len); - - return -ENOSYS; -} - /** * hid_hw_idle - send idle request to device * -- cgit v1.2.3 From 8aa45b544db9788b0fcc7a300eba8a3ade5d3d50 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 10 Dec 2021 13:11:34 +0200 Subject: HID: Add map_msc() to avoid boilerplate code Since we are going to have more MSC events too, add map_msc() that can be used to fill in necessary fields and avoid boilerplate code. Signed-off-by: Mika Westerberg Reviewed-by: Benjamin Tissoires Signed-off-by: Tero Kristo Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20211210111138.1248187-2-tero.kristo@linux.intel.com --- include/linux/hid.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index b2fea7fc54a1..f18e2cf5d74d 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1010,6 +1010,10 @@ static inline void hid_map_usage(struct hid_input *hidinput, bmap = input->ledbit; limit = LED_MAX; break; + case EV_MSC: + bmap = input->mscbit; + limit = MSC_MAX; + break; } if (unlikely(c > limit || !bmap)) { -- cgit v1.2.3 From ae7fafa6896ae762ff489a5e71c8e5fabfeb61ee Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 10 Dec 2021 13:11:36 +0200 Subject: HID: Add hid usages for USI style pens Add usage codes for USI style pens, based on the USB-HID usage table: https://usb.org/document-library/hid-usage-tables-122 See chapter 16, Digitizers Page (0x0D) Signed-off-by: Tero Kristo Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20211210111138.1248187-4-tero.kristo@linux.intel.com --- include/linux/hid.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index f18e2cf5d74d..fa2ddda84a53 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -241,6 +241,7 @@ struct hid_item { #define HID_DG_TOUCH 0x000d0033 #define HID_DG_UNTOUCH 0x000d0034 #define HID_DG_TAP 0x000d0035 +#define HID_DG_TRANSDUCER_INDEX 0x000d0038 #define HID_DG_TABLETFUNCTIONKEY 0x000d0039 #define HID_DG_PROGRAMCHANGEKEY 0x000d003a #define HID_DG_BATTERYSTRENGTH 0x000d003b @@ -253,6 +254,15 @@ struct hid_item { #define HID_DG_BARRELSWITCH 0x000d0044 #define HID_DG_ERASER 0x000d0045 #define HID_DG_TABLETPICK 0x000d0046 +#define HID_DG_PEN_COLOR 0x000d005c +#define HID_DG_PEN_LINE_WIDTH 0x000d005e +#define HID_DG_PEN_LINE_STYLE 0x000d0070 +#define HID_DG_PEN_LINE_STYLE_INK 0x000d0072 +#define HID_DG_PEN_LINE_STYLE_PENCIL 0x000d0073 +#define HID_DG_PEN_LINE_STYLE_HIGHLIGHTER 0x000d0074 +#define HID_DG_PEN_LINE_STYLE_CHISEL_MARKER 0x000d0075 +#define HID_DG_PEN_LINE_STYLE_BRUSH 0x000d0076 +#define HID_DG_PEN_LINE_STYLE_NO_PREFERENCE 0x000d0077 #define HID_CP_CONSUMERCONTROL 0x000c0001 #define HID_CP_NUMERICKEYPAD 0x000c0002 -- cgit v1.2.3 From 5904a3f9d756f108279f8c5b8f17ca6ddfb28d24 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 10 Dec 2021 13:11:37 +0200 Subject: HID: input: Make hidinput_find_field() static This function is not called outside of hid-input.c so we can make it static. Signed-off-by: Mika Westerberg Reviewed-by: Benjamin Tissoires Signed-off-by: Tero Kristo Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20211210111138.1248187-5-tero.kristo@linux.intel.com --- include/linux/hid.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index fa2ddda84a53..ff8b6973022a 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -899,7 +899,6 @@ extern void hidinput_disconnect(struct hid_device *); int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *, int type, u8 *, u32, int); -int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field); struct hid_field *hidinput_get_led_field(struct hid_device *hid); unsigned int hidinput_count_leds(struct hid_device *hid); __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code); -- cgit v1.2.3 From fd8d135b2c5e88662f2729e034913f183455a667 Mon Sep 17 00:00:00 2001 From: Alistair Francis Date: Wed, 8 Dec 2021 22:40:43 +1000 Subject: HID: quirks: Allow inverting the absolute X/Y values Add a HID_QUIRK_X_INVERT/HID_QUIRK_Y_INVERT quirk that can be used to invert the X/Y values. Signed-off-by: Alistair Francis [bentiss: silence checkpatch warning] Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20211208124045.61815-2-alistair@alistair23.me --- include/linux/hid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index ff8b6973022a..a14c089eb0c1 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -359,6 +359,8 @@ struct hid_item { /* BIT(9) reserved for backward compatibility, was NO_INIT_INPUT_REPORTS */ #define HID_QUIRK_ALWAYS_POLL BIT(10) #define HID_QUIRK_INPUT_PER_APP BIT(11) +#define HID_QUIRK_X_INVERT BIT(12) +#define HID_QUIRK_Y_INVERT BIT(13) #define HID_QUIRK_SKIP_OUTPUT_REPORTS BIT(16) #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID BIT(17) #define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP BIT(18) -- cgit v1.2.3