diff options
| author | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2023-08-30 16:06:38 -0700 |
|---|---|---|
| committer | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2023-08-30 16:06:38 -0700 |
| commit | 1ac731c529cd4d6adbce134754b51ff7d822b145 (patch) | |
| tree | 143ab3f35ca5f3b69f583c84e6964b17139c2ec1 /include/linux | |
| parent | 07b4c950f27bef0362dc6ad7ee713aab61d58149 (diff) | |
| parent | 54116d442e001e1b6bd482122043b1870998a1f3 (diff) | |
Merge branch 'next' into for-linus
Prepare input updates for 6.6 merge window.
Diffstat (limited to 'include/linux')
334 files changed, 7797 insertions, 4637 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index efff750f326d..7b71dd74baeb 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -10,12 +10,15 @@ #include <linux/errno.h> #include <linux/ioport.h> /* for struct resource */ -#include <linux/irqdomain.h> #include <linux/resource_ext.h> #include <linux/device.h> +#include <linux/mod_devicetable.h> #include <linux/property.h> #include <linux/uuid.h> +struct irq_domain; +struct irq_domain_ops; + #ifndef _LINUX #define _LINUX #endif @@ -24,7 +27,6 @@ #ifdef CONFIG_ACPI #include <linux/list.h> -#include <linux/mod_devicetable.h> #include <linux/dynamic_debug.h> #include <linux/module.h> #include <linux/mutex.h> @@ -1075,6 +1077,11 @@ static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) return 0; } +static inline bool acpi_sleep_state_supported(u8 sleep_state) +{ + return false; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC diff --git a/include/linux/acpi_mdio.h b/include/linux/acpi_mdio.h index 0a24ab7cb66f..8e2eefa9fbc0 100644 --- a/include/linux/acpi_mdio.h +++ b/include/linux/acpi_mdio.h @@ -9,7 +9,14 @@ #include <linux/phy.h> #if IS_ENABLED(CONFIG_ACPI_MDIO) -int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode); +int __acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode, + struct module *owner); + +static inline int +acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *handle) +{ + return __acpi_mdiobus_register(mdio, handle, THIS_MODULE); +} #else /* CONFIG_ACPI_MDIO */ static inline int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 17fa26215292..fe0760ce34c8 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -37,7 +37,7 @@ struct ahci_host_priv *ahci_platform_get_resources( int ahci_platform_init_host(struct platform_device *pdev, struct ahci_host_priv *hpriv, const struct ata_port_info *pi_template, - struct scsi_host_template *sht); + const struct scsi_host_template *sht); void ahci_platform_shutdown(struct platform_device *pdev); diff --git a/include/linux/alcor_pci.h b/include/linux/alcor_pci.h index 8274ed525e9f..c4a0b23846d8 100644 --- a/include/linux/alcor_pci.h +++ b/include/linux/alcor_pci.h @@ -268,13 +268,6 @@ struct alcor_pci_priv { unsigned long id; /* idr id */ struct alcor_dev_cfg *cfg; - - /* PCI ASPM related vars */ - int pdev_cap_off; - u8 pdev_aspm_cap; - int parent_cap_off; - u8 parent_aspm_cap; - u8 ext_config_dev_aspm; }; void alcor_write8(struct alcor_pci_priv *priv, u8 val, unsigned int addr); diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index f5f22418e64b..c10ebf8c42e6 100644 --- a/include/linux/amd-pstate.h +++ b/include/linux/amd-pstate.h @@ -97,6 +97,7 @@ enum amd_pstate_mode { AMD_PSTATE_DISABLE = 0, AMD_PSTATE_PASSIVE, AMD_PSTATE_ACTIVE, + AMD_PSTATE_GUIDED, AMD_PSTATE_MAX, }; @@ -104,6 +105,7 @@ static const char * const amd_pstate_mode_string[] = { [AMD_PSTATE_DISABLE] = "disable", [AMD_PSTATE_PASSIVE] = "passive", [AMD_PSTATE_ACTIVE] = "active", + [AMD_PSTATE_GUIDED] = "guided", NULL, }; #endif /* _LINUX_AMD_PSTATE_H */ diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h index 1f68b49bcd68..206d97ffda79 100644 --- a/include/linux/apple-gmux.h +++ b/include/linux/apple-gmux.h @@ -34,8 +34,20 @@ #define GMUX_PORT_READ 0xd0 #define GMUX_PORT_WRITE 0xd4 +#define GMUX_MMIO_PORT_SELECT 0x0e +#define GMUX_MMIO_COMMAND_SEND 0x0f + +#define GMUX_MMIO_READ 0x00 +#define GMUX_MMIO_WRITE 0x40 + #define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4) +enum apple_gmux_type { + APPLE_GMUX_TYPE_PIO, + APPLE_GMUX_TYPE_INDEXED, + APPLE_GMUX_TYPE_MMIO, +}; + #if IS_ENABLED(CONFIG_APPLE_GMUX) static inline bool apple_gmux_is_indexed(unsigned long iostart) { @@ -52,11 +64,29 @@ static inline bool apple_gmux_is_indexed(unsigned long iostart) return false; } +static inline bool apple_gmux_is_mmio(unsigned long iostart) +{ + u8 __iomem *iomem_base = ioremap(iostart, 16); + u8 val; + + if (!iomem_base) + return false; + + /* + * If this is 0xff, then gmux must not be present, as the gmux would + * reset it to 0x00, or it would be one of 0x1, 0x4, 0x41, 0x44 if a + * command is currently being processed. + */ + val = ioread8(iomem_base + GMUX_MMIO_COMMAND_SEND); + iounmap(iomem_base); + return (val != 0xff); +} + /** * apple_gmux_detect() - detect if gmux is built into the machine * * @pnp_dev: Device to probe or NULL to use the first matching device - * @indexed_ret: Returns (by reference) if the gmux is indexed or not + * @type_ret: Returns (by reference) the apple_gmux_type of the device * * Detect if a supported gmux device is present by actually probing it. * This avoids the false positives returned on some models by @@ -65,13 +95,13 @@ static inline bool apple_gmux_is_indexed(unsigned long iostart) * Return: %true if a supported gmux ACPI device is detected and the kernel * was configured with CONFIG_APPLE_GMUX, %false otherwise. */ -static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret) +static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, enum apple_gmux_type *type_ret) { u8 ver_major, ver_minor, ver_release; struct device *dev = NULL; struct acpi_device *adev; struct resource *res; - bool indexed = false; + enum apple_gmux_type type = APPLE_GMUX_TYPE_PIO; bool ret = false; if (!pnp_dev) { @@ -88,24 +118,30 @@ static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret) } res = pnp_get_resource(pnp_dev, IORESOURCE_IO, 0); - if (!res || resource_size(res) < GMUX_MIN_IO_LEN) - goto out; - - /* - * Invalid version information may indicate either that the gmux - * device isn't present or that it's a new one that uses indexed io. - */ - ver_major = inb(res->start + GMUX_PORT_VERSION_MAJOR); - ver_minor = inb(res->start + GMUX_PORT_VERSION_MINOR); - ver_release = inb(res->start + GMUX_PORT_VERSION_RELEASE); - if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) { - indexed = apple_gmux_is_indexed(res->start); - if (!indexed) + if (res && resource_size(res) >= GMUX_MIN_IO_LEN) { + /* + * Invalid version information may indicate either that the gmux + * device isn't present or that it's a new one that uses indexed io. + */ + ver_major = inb(res->start + GMUX_PORT_VERSION_MAJOR); + ver_minor = inb(res->start + GMUX_PORT_VERSION_MINOR); + ver_release = inb(res->start + GMUX_PORT_VERSION_RELEASE); + if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) { + if (apple_gmux_is_indexed(res->start)) + type = APPLE_GMUX_TYPE_INDEXED; + else + goto out; + } + } else { + res = pnp_get_resource(pnp_dev, IORESOURCE_MEM, 0); + if (res && apple_gmux_is_mmio(res->start)) + type = APPLE_GMUX_TYPE_MMIO; + else goto out; } - if (indexed_ret) - *indexed_ret = indexed; + if (type_ret) + *type_ret = type; ret = true; out: diff --git a/include/linux/apple_bl.h b/include/linux/apple_bl.h deleted file mode 100644 index 445af2e3cc21..000000000000 --- a/include/linux/apple_bl.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * apple_bl exported symbols - */ - -#ifndef _LINUX_APPLE_BL_H -#define _LINUX_APPLE_BL_H - -#if defined(CONFIG_BACKLIGHT_APPLE) || defined(CONFIG_BACKLIGHT_APPLE_MODULE) - -extern int apple_bl_register(void); -extern void apple_bl_unregister(void); - -#else /* !CONFIG_BACKLIGHT_APPLE */ - -static inline int apple_bl_register(void) -{ - return 0; -} - -static inline void apple_bl_unregister(void) -{ -} - -#endif /* !CONFIG_BACKLIGHT_APPLE */ - -#endif /* _LINUX_APPLE_BL_H */ diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 220c8c60e021..f196c19f8e55 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -227,6 +227,24 @@ void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit); extern u64 smccc_has_sve_hint; /** + * arm_smccc_get_soc_id_version() + * + * Returns the SOC ID version. + * + * When ARM_SMCCC_ARCH_SOC_ID is not present, returns SMCCC_RET_NOT_SUPPORTED. + */ +s32 arm_smccc_get_soc_id_version(void); + +/** + * arm_smccc_get_soc_id_revision() + * + * Returns the SOC ID revision. + * + * When ARM_SMCCC_ARCH_SOC_ID is not present, returns SMCCC_RET_NOT_SUPPORTED. + */ +s32 arm_smccc_get_soc_id_revision(void); + +/** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 */ diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index c87aeecaa9b2..583fe3b49a49 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -96,6 +96,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { + u32 id; int vm_id; bool mode_32bit; uuid_t uuid; diff --git a/include/linux/ata.h b/include/linux/ata.h index 0c18499f60b6..c224dbddb9b2 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -16,7 +16,6 @@ #include <linux/bits.h> #include <linux/string.h> #include <linux/types.h> -#include <asm/byteorder.h> /* defines only for the constants which don't work well as enums */ #define ATA_DMA_BOUNDARY 0xffffUL @@ -1017,76 +1016,6 @@ static inline bool atapi_id_dmadir(const u16 *dev_id) return ata_id_major_version(dev_id) >= 7 && (dev_id[62] & 0x8000); } -/* - * ata_id_is_lba_capacity_ok() performs a sanity check on - * the claimed LBA capacity value for the device. - * - * Returns 1 if LBA capacity looks sensible, 0 otherwise. - * - * It is called only once for each device. - */ -static inline bool ata_id_is_lba_capacity_ok(u16 *id) -{ - unsigned long lba_sects, chs_sects, head, tail; - - /* No non-LBA info .. so valid! */ - if (id[ATA_ID_CYLS] == 0) - return true; - - lba_sects = ata_id_u32(id, ATA_ID_LBA_CAPACITY); - - /* - * The ATA spec tells large drives to return - * C/H/S = 16383/16/63 independent of their size. - * Some drives can be jumpered to use 15 heads instead of 16. - * Some drives can be jumpered to use 4092 cyls instead of 16383. - */ - if ((id[ATA_ID_CYLS] == 16383 || - (id[ATA_ID_CYLS] == 4092 && id[ATA_ID_CUR_CYLS] == 16383)) && - id[ATA_ID_SECTORS] == 63 && - (id[ATA_ID_HEADS] == 15 || id[ATA_ID_HEADS] == 16) && - (lba_sects >= 16383 * 63 * id[ATA_ID_HEADS])) - return true; - - chs_sects = id[ATA_ID_CYLS] * id[ATA_ID_HEADS] * id[ATA_ID_SECTORS]; - - /* perform a rough sanity check on lba_sects: within 10% is OK */ - if (lba_sects - chs_sects < chs_sects/10) - return true; - - /* some drives have the word order reversed */ - head = (lba_sects >> 16) & 0xffff; - tail = lba_sects & 0xffff; - lba_sects = head | (tail << 16); - - if (lba_sects - chs_sects < chs_sects/10) { - *(__le32 *)&id[ATA_ID_LBA_CAPACITY] = __cpu_to_le32(lba_sects); - return true; /* LBA capacity is (now) good */ - } - - return false; /* LBA capacity value may be bad */ -} - -static inline void ata_id_to_hd_driveid(u16 *id) -{ -#ifdef __BIG_ENDIAN - /* accessed in struct hd_driveid as 8-bit values */ - id[ATA_ID_MAX_MULTSECT] = __cpu_to_le16(id[ATA_ID_MAX_MULTSECT]); - id[ATA_ID_CAPABILITY] = __cpu_to_le16(id[ATA_ID_CAPABILITY]); - id[ATA_ID_OLD_PIO_MODES] = __cpu_to_le16(id[ATA_ID_OLD_PIO_MODES]); - id[ATA_ID_OLD_DMA_MODES] = __cpu_to_le16(id[ATA_ID_OLD_DMA_MODES]); - id[ATA_ID_MULTSECT] = __cpu_to_le16(id[ATA_ID_MULTSECT]); - - /* as 32-bit values */ - *(u32 *)&id[ATA_ID_LBA_CAPACITY] = ata_id_u32(id, ATA_ID_LBA_CAPACITY); - *(u32 *)&id[ATA_ID_SPG] = ata_id_u32(id, ATA_ID_SPG); - - /* as 64-bit value */ - *(u64 *)&id[ATA_ID_LBA_CAPACITY_2] = - ata_id_u64(id, ATA_ID_LBA_CAPACITY_2); -#endif -} - static inline bool ata_ok(u8 status) { return ((status & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ | ATA_ERR)) diff --git a/include/linux/ata_platform.h b/include/linux/ata_platform.h index 9cafec92282d..b9745cc08e38 100644 --- a/include/linux/ata_platform.h +++ b/include/linux/ata_platform.h @@ -19,7 +19,7 @@ extern int __pata_platform_probe(struct device *dev, struct resource *irq_res, unsigned int ioport_shift, int __pio_mask, - struct scsi_host_template *sht, + const struct scsi_host_template *sht, bool use16bit); /* diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 77bc5522e61c..a6e4437c5f36 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -217,6 +217,28 @@ #endif /* arch_try_cmpxchg64_relaxed */ +#ifndef arch_try_cmpxchg_local +#define arch_try_cmpxchg_local(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg_local((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg_local */ + +#ifndef arch_try_cmpxchg64_local +#define arch_try_cmpxchg64_local(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_local((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_local */ + #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) @@ -1208,15 +1230,21 @@ arch_atomic_inc_and_test(atomic_t *v) #define arch_atomic_inc_and_test arch_atomic_inc_and_test #endif +#ifndef arch_atomic_add_negative_relaxed +#ifdef arch_atomic_add_negative +#define arch_atomic_add_negative_acquire arch_atomic_add_negative +#define arch_atomic_add_negative_release arch_atomic_add_negative +#define arch_atomic_add_negative_relaxed arch_atomic_add_negative +#endif /* arch_atomic_add_negative */ + #ifndef arch_atomic_add_negative /** - * arch_atomic_add_negative - add and test if negative + * arch_atomic_add_negative - Add and test if negative * @i: integer value to add * @v: pointer of type atomic_t * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. */ static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) @@ -1226,6 +1254,95 @@ arch_atomic_add_negative(int i, atomic_t *v) #define arch_atomic_add_negative arch_atomic_add_negative #endif +#ifndef arch_atomic_add_negative_acquire +/** + * arch_atomic_add_negative_acquire - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic_add_negative_acquire(int i, atomic_t *v) +{ + return arch_atomic_add_return_acquire(i, v) < 0; +} +#define arch_atomic_add_negative_acquire arch_atomic_add_negative_acquire +#endif + +#ifndef arch_atomic_add_negative_release +/** + * arch_atomic_add_negative_release - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic_add_negative_release(int i, atomic_t *v) +{ + return arch_atomic_add_return_release(i, v) < 0; +} +#define arch_atomic_add_negative_release arch_atomic_add_negative_release +#endif + +#ifndef arch_atomic_add_negative_relaxed +/** + * arch_atomic_add_negative_relaxed - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic_add_negative_relaxed(int i, atomic_t *v) +{ + return arch_atomic_add_return_relaxed(i, v) < 0; +} +#define arch_atomic_add_negative_relaxed arch_atomic_add_negative_relaxed +#endif + +#else /* arch_atomic_add_negative_relaxed */ + +#ifndef arch_atomic_add_negative_acquire +static __always_inline bool +arch_atomic_add_negative_acquire(int i, atomic_t *v) +{ + bool ret = arch_atomic_add_negative_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_add_negative_acquire arch_atomic_add_negative_acquire +#endif + +#ifndef arch_atomic_add_negative_release +static __always_inline bool +arch_atomic_add_negative_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_add_negative_relaxed(i, v); +} +#define arch_atomic_add_negative_release arch_atomic_add_negative_release +#endif + +#ifndef arch_atomic_add_negative +static __always_inline bool +arch_atomic_add_negative(int i, atomic_t *v) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic_add_negative_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_add_negative arch_atomic_add_negative +#endif + +#endif /* arch_atomic_add_negative_relaxed */ + #ifndef arch_atomic_fetch_add_unless /** * arch_atomic_fetch_add_unless - add unless the number is already a given value @@ -2329,15 +2446,21 @@ arch_atomic64_inc_and_test(atomic64_t *v) #define arch_atomic64_inc_and_test arch_atomic64_inc_and_test #endif +#ifndef arch_atomic64_add_negative_relaxed +#ifdef arch_atomic64_add_negative +#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative +#define arch_atomic64_add_negative_release arch_atomic64_add_negative +#define arch_atomic64_add_negative_relaxed arch_atomic64_add_negative +#endif /* arch_atomic64_add_negative */ + #ifndef arch_atomic64_add_negative /** - * arch_atomic64_add_negative - add and test if negative + * arch_atomic64_add_negative - Add and test if negative * @i: integer value to add * @v: pointer of type atomic64_t * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. */ static __always_inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v) @@ -2347,6 +2470,95 @@ arch_atomic64_add_negative(s64 i, atomic64_t *v) #define arch_atomic64_add_negative arch_atomic64_add_negative #endif +#ifndef arch_atomic64_add_negative_acquire +/** + * arch_atomic64_add_negative_acquire - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic64_add_negative_acquire(s64 i, atomic64_t *v) +{ + return arch_atomic64_add_return_acquire(i, v) < 0; +} +#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative_acquire +#endif + +#ifndef arch_atomic64_add_negative_release +/** + * arch_atomic64_add_negative_release - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic64_add_negative_release(s64 i, atomic64_t *v) +{ + return arch_atomic64_add_return_release(i, v) < 0; +} +#define arch_atomic64_add_negative_release arch_atomic64_add_negative_release +#endif + +#ifndef arch_atomic64_add_negative_relaxed +/** + * arch_atomic64_add_negative_relaxed - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic64_add_negative_relaxed(s64 i, atomic64_t *v) +{ + return arch_atomic64_add_return_relaxed(i, v) < 0; +} +#define arch_atomic64_add_negative_relaxed arch_atomic64_add_negative_relaxed +#endif + +#else /* arch_atomic64_add_negative_relaxed */ + +#ifndef arch_atomic64_add_negative_acquire +static __always_inline bool +arch_atomic64_add_negative_acquire(s64 i, atomic64_t *v) +{ + bool ret = arch_atomic64_add_negative_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative_acquire +#endif + +#ifndef arch_atomic64_add_negative_release +static __always_inline bool +arch_atomic64_add_negative_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_add_negative_relaxed(i, v); +} +#define arch_atomic64_add_negative_release arch_atomic64_add_negative_release +#endif + +#ifndef arch_atomic64_add_negative +static __always_inline bool +arch_atomic64_add_negative(s64 i, atomic64_t *v) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_add_negative_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_add_negative arch_atomic64_add_negative +#endif + +#endif /* arch_atomic64_add_negative_relaxed */ + #ifndef arch_atomic64_fetch_add_unless /** * arch_atomic64_fetch_add_unless - add unless the number is already a given value @@ -2456,4 +2668,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// b5e87bdd5ede61470c29f7a7e4de781af3770f09 +// ad2e2b4d168dbc60a73922616047a9bfa446af36 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 7a139ec030b0..03a232a1fa57 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -592,6 +592,28 @@ atomic_add_negative(int i, atomic_t *v) return arch_atomic_add_negative(i, v); } +static __always_inline bool +atomic_add_negative_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_negative_acquire(i, v); +} + +static __always_inline bool +atomic_add_negative_release(int i, atomic_t *v) +{ + kcsan_release(); + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_negative_release(i, v); +} + +static __always_inline bool +atomic_add_negative_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_negative_relaxed(i, v); +} + static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { @@ -1211,6 +1233,28 @@ atomic64_add_negative(s64 i, atomic64_t *v) return arch_atomic64_add_negative(i, v); } +static __always_inline bool +atomic64_add_negative_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_negative_acquire(i, v); +} + +static __always_inline bool +atomic64_add_negative_release(s64 i, atomic64_t *v) +{ + kcsan_release(); + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_negative_release(i, v); +} + +static __always_inline bool +atomic64_add_negative_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_negative_relaxed(i, v); +} + static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { @@ -1830,6 +1874,28 @@ atomic_long_add_negative(long i, atomic_long_t *v) return arch_atomic_long_add_negative(i, v); } +static __always_inline bool +atomic_long_add_negative_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_negative_acquire(i, v); +} + +static __always_inline bool +atomic_long_add_negative_release(long i, atomic_long_t *v) +{ + kcsan_release(); + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_negative_release(i, v); +} + +static __always_inline bool +atomic_long_add_negative_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_negative_relaxed(i, v); +} + static __always_inline long atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { @@ -1882,14 +1948,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg(__ai_ptr, __VA_ARGS__); \ }) #define xchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_acquire(__ai_ptr, __VA_ARGS__); \ }) @@ -1897,14 +1963,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_release(__ai_ptr, __VA_ARGS__); \ }) #define xchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) @@ -1912,14 +1978,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \ }) @@ -1927,14 +1993,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) @@ -1942,14 +2008,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \ }) @@ -1957,14 +2023,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \ }) @@ -1973,8 +2039,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -1982,8 +2048,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -1992,8 +2058,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2001,8 +2067,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2011,8 +2077,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2020,8 +2086,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2030,8 +2096,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2039,22 +2105,22 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_local(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \ }) @@ -2062,15 +2128,33 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) +#define try_cmpxchg_local(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_local(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + #define cmpxchg_double(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \ }) @@ -2078,9 +2162,9 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg_double_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \ }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 764f741eb77a7ad565dc8d99ce2837d5542e8aee +// 6b513a42e1a1b5962532a019b7fc91eaa044ad5e diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index 800b8c35992d..2fc51ba66beb 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -479,6 +479,24 @@ arch_atomic_long_add_negative(long i, atomic_long_t *v) return arch_atomic64_add_negative(i, v); } +static __always_inline bool +arch_atomic_long_add_negative_acquire(long i, atomic_long_t *v) +{ + return arch_atomic64_add_negative_acquire(i, v); +} + +static __always_inline bool +arch_atomic_long_add_negative_release(long i, atomic_long_t *v) +{ + return arch_atomic64_add_negative_release(i, v); +} + +static __always_inline bool +arch_atomic_long_add_negative_relaxed(long i, atomic_long_t *v) +{ + return arch_atomic64_add_negative_relaxed(i, v); +} + static __always_inline long arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { @@ -973,6 +991,24 @@ arch_atomic_long_add_negative(long i, atomic_long_t *v) return arch_atomic_add_negative(i, v); } +static __always_inline bool +arch_atomic_long_add_negative_acquire(long i, atomic_long_t *v) +{ + return arch_atomic_add_negative_acquire(i, v); +} + +static __always_inline bool +arch_atomic_long_add_negative_release(long i, atomic_long_t *v) +{ + return arch_atomic_add_negative_release(i, v); +} + +static __always_inline bool +arch_atomic_long_add_negative_relaxed(long i, atomic_long_t *v) +{ + return arch_atomic_add_negative_relaxed(i, v); +} + static __always_inline long arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { @@ -1011,4 +1047,4 @@ arch_atomic_long_dec_if_positive(atomic_long_t *v) #endif /* CONFIG_64BIT */ #endif /* _LINUX_ATOMIC_LONG_H */ -// e8f0e08ff072b74d180eabe2ad001282b38c2c88 +// a194c07d7d2f4b0e178d3c118c919775d5d65f50 diff --git a/include/linux/bio.h b/include/linux/bio.h index d766be7152e1..b3e7529ff55e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -500,6 +500,7 @@ void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_clone_blkg_association(struct bio *dst, struct bio *src); +void blkcg_punt_bio_submit(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, @@ -507,6 +508,10 @@ static inline void bio_associate_blkg_from_css(struct bio *bio, { } static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } +static inline void blkcg_punt_bio_submit(struct bio *bio) +{ + submit_bio(bio); +} #endif /* CONFIG_BLK_CGROUP */ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev) diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index 1e3e5d0adf12..5e5822c18ee4 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -95,8 +95,8 @@ int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, int blk_crypto_start_using_key(struct block_device *bdev, const struct blk_crypto_key *key); -int blk_crypto_evict_key(struct block_device *bdev, - const struct blk_crypto_key *key); +void blk_crypto_evict_key(struct block_device *bdev, + const struct blk_crypto_key *key); bool blk_crypto_config_supported_natively(struct block_device *bdev, const struct blk_crypto_config *cfg); diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h deleted file mode 100644 index 53b58c610e76..000000000000 --- a/include/linux/blk-mq-rdma.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_BLK_MQ_RDMA_H -#define _LINUX_BLK_MQ_RDMA_H - -struct blk_mq_tag_set; -struct ib_device; - -void blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, - struct ib_device *dev, int first_vec); - -#endif /* _LINUX_BLK_MQ_RDMA_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index dd5ce1137f04..06caacd77ed6 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -57,8 +57,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) /* The per-zone write lock is held for this request */ #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) -/* already slept for hybrid poll */ -#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) /* queue has elevator attached */ @@ -228,6 +226,12 @@ static inline unsigned short req_get_ioprio(struct request *req) *(listptr) = rq; \ } while (0) +#define rq_list_add_tail(lastpptr, rq) do { \ + (rq)->rq_next = NULL; \ + **(lastpptr) = rq; \ + *(lastpptr) = &rq->rq_next; \ +} while (0) + #define rq_list_pop(listptr) \ ({ \ struct request *__req = NULL; \ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 99be590f952f..740afe80f297 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -40,26 +40,26 @@ struct bio_crypt_ctx; struct block_device { sector_t bd_start_sect; sector_t bd_nr_sectors; + struct gendisk * bd_disk; + struct request_queue * bd_queue; struct disk_stats __percpu *bd_stats; unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ + u8 bd_partno; + bool bd_write_holder; + bool bd_has_submit_bio; dev_t bd_dev; atomic_t bd_openers; + spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct inode * bd_inode; /* will die */ struct super_block * bd_super; void * bd_claiming; - struct device bd_device; void * bd_holder; + /* The counter of freeze processes */ + int bd_fsfreeze_count; int bd_holders; - bool bd_write_holder; struct kobject *bd_holder_dir; - u8 bd_partno; - spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ - struct gendisk * bd_disk; - struct request_queue * bd_queue; - /* The counter of freeze processes */ - int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; struct super_block *bd_fsfreeze_sb; @@ -68,6 +68,11 @@ struct block_device { #ifdef CONFIG_FAIL_MAKE_REQUEST bool bd_make_it_fail; #endif + /* + * keep this out-of-line as it's both big and not needed in the fast + * path + */ + struct device bd_device; } __randomize_layout; #define bdev_whole(_bdev) \ @@ -404,18 +409,11 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ - /* - * When a shared kthread needs to issue a bio for a cgroup, doing - * so synchronously can lead to priority inversions as the kthread - * can be trapped waiting for that cgroup. CGROUP_PUNT flag makes - * submit_bio() punt the actual issuing to a dedicated per-blkcg - * work item to avoid such priority inversions. - */ - __REQ_CGROUP_PUNT, __REQ_POLLED, /* caller polls for completion using bio_poll */ __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ __REQ_SWAP, /* swap I/O */ __REQ_DRV, /* for driver use */ + __REQ_FS_PRIVATE, /* for file system (submitter) use */ /* * Command specific flags, keep last: @@ -443,14 +441,13 @@ enum req_flag_bits { #define REQ_RAHEAD (__force blk_opf_t)(1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (__force blk_opf_t)(1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (__force blk_opf_t)(1ULL << __REQ_NOWAIT) -#define REQ_CGROUP_PUNT (__force blk_opf_t)(1ULL << __REQ_CGROUP_PUNT) - -#define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) #define REQ_POLLED (__force blk_opf_t)(1ULL << __REQ_POLLED) #define REQ_ALLOC_CACHE (__force blk_opf_t)(1ULL << __REQ_ALLOC_CACHE) - -#define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) #define REQ_SWAP (__force blk_opf_t)(1ULL << __REQ_SWAP) +#define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) +#define REQ_FS_PRIVATE (__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE) + +#define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d1aee08f8c18..c0ffe203a602 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -44,12 +44,6 @@ extern const struct device_type disk_type; extern struct device_type part_type; extern struct class block_class; -/* Must be consistent with blk_mq_poll_stats_bkt() */ -#define BLK_MQ_POLL_STATS_BKTS 16 - -/* Doing classic polling */ -#define BLK_MQ_POLL_CLASSIC -1 - /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. @@ -163,9 +157,6 @@ struct gendisk { struct timer_rand_state *random; atomic_t sync_io; /* RAID */ struct disk_events *ev; -#ifdef CONFIG_BLK_DEV_INTEGRITY - struct kobject integrity_kobj; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ #ifdef CONFIG_BLK_DEV_ZONED /* @@ -468,10 +459,6 @@ struct request_queue { #endif unsigned int rq_timeout; - int poll_nsec; - - struct blk_stat_callback *poll_cb; - struct blk_rq_stat *poll_stat; struct timer_list timeout; struct work_struct timeout_work; @@ -870,8 +857,6 @@ blk_status_t errno_to_blk_status(int errno); /* only poll the hardware once, don't continue until a completion was found */ #define BLK_POLL_ONESHOT (1 << 0) -/* do not sleep to wait for the expected completion time */ -#define BLK_POLL_NOSLEEP (1 << 1) int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags); int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob, unsigned int flags); @@ -1391,8 +1376,6 @@ enum blk_unique_id { BLK_UID_NAA = 3, }; -#define NFL4_UFLG_MASK 0x0000003F - struct block_device_operations { void (*submit_bio)(struct bio *bio); int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, @@ -1446,11 +1429,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, enum req_op op, +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, - unsigned long start_time); + unsigned int sectors, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 520b238abd5a..e53ceee1df37 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -96,11 +96,11 @@ struct bpf_map_ops { /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); - int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); - int (*map_delete_elem)(struct bpf_map *map, void *key); - int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); - int (*map_pop_elem)(struct bpf_map *map, void *value); - int (*map_peek_elem)(struct bpf_map *map, void *value); + long (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); + long (*map_delete_elem)(struct bpf_map *map, void *key); + long (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); + long (*map_pop_elem)(struct bpf_map *map, void *value); + long (*map_peek_elem)(struct bpf_map *map, void *value); void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); /* funcs called by prog_array and perf_event_array map */ @@ -139,7 +139,7 @@ struct bpf_map_ops { struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ - int (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); + long (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); /* map_meta_equal must be implemented for maps that can be * used as an inner map. It is a runtime check to ensure @@ -157,10 +157,12 @@ struct bpf_map_ops { int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); - int (*map_for_each_callback)(struct bpf_map *map, + long (*map_for_each_callback)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags); + u64 (*map_mem_usage)(const struct bpf_map *map); + /* BTF id of struct allocated by map_alloc */ int *map_btf_id; @@ -185,11 +187,17 @@ enum btf_field_type { BPF_RB_NODE = (1 << 7), BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD | BPF_RB_NODE | BPF_RB_ROOT, + BPF_REFCOUNT = (1 << 8), }; +typedef void (*btf_dtor_kfunc_t)(void *); + struct btf_field_kptr { struct btf *btf; struct module *module; + /* dtor used if btf_is_kernel(btf), otherwise the type is + * program-allocated, dtor is NULL, and __bpf_obj_drop_impl is used + */ btf_dtor_kfunc_t dtor; u32 btf_id; }; @@ -203,6 +211,7 @@ struct btf_field_graph_root { struct btf_field { u32 offset; + u32 size; enum btf_field_type type; union { struct btf_field_kptr kptr; @@ -215,15 +224,10 @@ struct btf_record { u32 field_mask; int spin_lock_off; int timer_off; + int refcount_off; struct btf_field fields[]; }; -struct btf_field_offs { - u32 cnt; - u32 field_off[BTF_FIELDS_MAX]; - u8 field_sz[BTF_FIELDS_MAX]; -}; - struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -250,7 +254,6 @@ struct bpf_map { struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; - struct btf_field_offs *field_offs; /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ @@ -292,6 +295,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "bpf_rb_root"; case BPF_RB_NODE: return "bpf_rb_node"; + case BPF_REFCOUNT: + return "bpf_refcount"; default: WARN_ON_ONCE(1); return "unknown"; @@ -316,6 +321,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_rb_root); case BPF_RB_NODE: return sizeof(struct bpf_rb_node); + case BPF_REFCOUNT: + return sizeof(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; @@ -340,12 +347,42 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_rb_root); case BPF_RB_NODE: return __alignof__(struct bpf_rb_node); + case BPF_REFCOUNT: + return __alignof__(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; } } +static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) +{ + memset(addr, 0, field->size); + + switch (field->type) { + case BPF_REFCOUNT: + refcount_set((refcount_t *)addr, 1); + break; + case BPF_RB_NODE: + RB_CLEAR_NODE((struct rb_node *)addr); + break; + case BPF_LIST_HEAD: + case BPF_LIST_NODE: + INIT_LIST_HEAD((struct list_head *)addr); + break; + case BPF_RB_ROOT: + /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ + case BPF_SPIN_LOCK: + case BPF_TIMER: + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + break; + default: + WARN_ON_ONCE(1); + return; + } +} + static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type) { if (IS_ERR_OR_NULL(rec)) @@ -353,14 +390,14 @@ static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_f return rec->field_mask & type; } -static inline void bpf_obj_init(const struct btf_field_offs *foffs, void *obj) +static inline void bpf_obj_init(const struct btf_record *rec, void *obj) { int i; - if (!foffs) + if (IS_ERR_OR_NULL(rec)) return; - for (i = 0; i < foffs->cnt; i++) - memset(obj + foffs->field_off[i], 0, foffs->field_sz[i]); + for (i = 0; i < rec->cnt; i++) + bpf_obj_init_field(&rec->fields[i], obj + rec->fields[i].offset); } /* 'dst' must be a temporary buffer and should not point to memory that is being @@ -372,7 +409,7 @@ static inline void bpf_obj_init(const struct btf_field_offs *foffs, void *obj) */ static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { - bpf_obj_init(map->field_offs, dst); + bpf_obj_init(map->record, dst); } /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and @@ -392,14 +429,14 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ -static inline void bpf_obj_memcpy(struct btf_field_offs *foffs, +static inline void bpf_obj_memcpy(struct btf_record *rec, void *dst, void *src, u32 size, bool long_memcpy) { u32 curr_off = 0; int i; - if (likely(!foffs)) { + if (IS_ERR_OR_NULL(rec)) { if (long_memcpy) bpf_long_memcpy(dst, src, round_up(size, 8)); else @@ -407,49 +444,49 @@ static inline void bpf_obj_memcpy(struct btf_field_offs *foffs, return; } - for (i = 0; i < foffs->cnt; i++) { - u32 next_off = foffs->field_off[i]; + for (i = 0; i < rec->cnt; i++) { + u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memcpy(dst + curr_off, src + curr_off, sz); - curr_off += foffs->field_sz[i] + sz; + curr_off += rec->fields[i].size + sz; } memcpy(dst + curr_off, src + curr_off, size - curr_off); } static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { - bpf_obj_memcpy(map->field_offs, dst, src, map->value_size, false); + bpf_obj_memcpy(map->record, dst, src, map->value_size, false); } static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src) { - bpf_obj_memcpy(map->field_offs, dst, src, map->value_size, true); + bpf_obj_memcpy(map->record, dst, src, map->value_size, true); } -static inline void bpf_obj_memzero(struct btf_field_offs *foffs, void *dst, u32 size) +static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size) { u32 curr_off = 0; int i; - if (likely(!foffs)) { + if (IS_ERR_OR_NULL(rec)) { memset(dst, 0, size); return; } - for (i = 0; i < foffs->cnt; i++) { - u32 next_off = foffs->field_off[i]; + for (i = 0; i < rec->cnt; i++) { + u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memset(dst + curr_off, 0, sz); - curr_off += foffs->field_sz[i] + sz; + curr_off += rec->fields[i].size + sz; } memset(dst + curr_off, 0, size - curr_off); } static inline void zero_map_value(struct bpf_map *map, void *dst) { - bpf_obj_memzero(map->field_offs, dst, map->value_size); + bpf_obj_memzero(map->record, dst, map->value_size); } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, @@ -607,11 +644,18 @@ enum bpf_type_flag { */ NON_OWN_REF = BIT(14 + BPF_BASE_TYPE_BITS), + /* DYNPTR points to sk_buff */ + DYNPTR_TYPE_SKB = BIT(15 + BPF_BASE_TYPE_BITS), + + /* DYNPTR points to xdp_buff */ + DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; -#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF) +#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \ + | DYNPTR_TYPE_XDP) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -879,8 +923,7 @@ struct bpf_verifier_ops { struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag); + int off, int size); }; struct bpf_prog_offload_ops { @@ -1089,6 +1132,7 @@ struct bpf_trampoline { struct bpf_attach_target_info { struct btf_func_model fmodel; long tgt_addr; + struct module *tgt_mod; const char *tgt_name; const struct btf_type *tgt_type; }; @@ -1124,6 +1168,37 @@ static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( return bpf_func(ctx, insnsi); } +/* the implementation of the opaque uapi struct bpf_dynptr */ +struct bpf_dynptr_kern { + void *data; + /* Size represents the number of usable bytes of dynptr data. + * If for example the offset is at 4 for a local dynptr whose data is + * of type u64, the number of usable bytes is 4. + * + * The upper 8 bits are reserved. It is as follows: + * Bits 0 - 23 = size + * Bits 24 - 30 = dynptr type + * Bit 31 = whether dynptr is read-only + */ + u32 size; + u32 offset; +} __aligned(8); + +enum bpf_dynptr_type { + BPF_DYNPTR_TYPE_INVALID, + /* Points to memory that is local to the bpf program */ + BPF_DYNPTR_TYPE_LOCAL, + /* Underlying data is a ringbuf record */ + BPF_DYNPTR_TYPE_RINGBUF, + /* Underlying data is a sk_buff */ + BPF_DYNPTR_TYPE_SKB, + /* Underlying data is a xdp_buff */ + BPF_DYNPTR_TYPE_XDP, +}; + +int bpf_dynptr_check_size(u32 size); +u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr); + #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); @@ -1361,6 +1436,7 @@ struct bpf_prog_aux { * main prog always has linfo_idx == 0 */ u32 linfo_idx; + struct module *mod; u32 num_exentries; struct exception_table_entry *extable; union { @@ -1429,6 +1505,8 @@ struct bpf_link_ops { void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); int (*fill_link_info)(const struct bpf_link *link, struct bpf_link_info *info); + int (*update_map)(struct bpf_link *link, struct bpf_map *new_map, + struct bpf_map *old_map); }; struct bpf_tramp_link { @@ -1471,6 +1549,8 @@ struct bpf_struct_ops { void *kdata, const void *udata); int (*reg)(void *kdata); void (*unreg)(void *kdata); + int (*update)(void *kdata, void *old_kdata); + int (*validate)(void *kdata); const struct btf_type *type; const struct btf_type *value_type; const char *name; @@ -1505,6 +1585,7 @@ static inline void bpf_module_put(const void *data, struct module *owner) else module_put(owner); } +int bpf_struct_ops_link_create(union bpf_attr *attr); #ifdef CONFIG_NET /* Define it here to avoid the use of forward declaration */ @@ -1545,6 +1626,11 @@ static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, { return -EINVAL; } +static inline int bpf_struct_ops_link_create(union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} + #endif #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) @@ -1577,8 +1663,12 @@ struct bpf_array { #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 33 -/* Maximum number of loops for bpf_loop */ -#define BPF_MAX_LOOPS BIT(23) +/* Maximum number of loops for bpf_loop and bpf_iter_num. + * It's enum to expose it (and thus make it discoverable) through BTF. + */ +enum { + BPF_MAX_LOOPS = 8 * 1024 * 1024, +}; #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ @@ -1881,7 +1971,7 @@ void bpf_prog_free_id(struct bpf_prog *prog); void bpf_map_free_id(struct bpf_map *map); struct btf_field *btf_record_find(const struct btf_record *rec, - u32 offset, enum btf_field_type type); + u32 offset, u32 field_mask); void btf_record_free(struct btf_record *rec); void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); @@ -1894,6 +1984,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); +struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref); struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); @@ -2114,7 +2205,7 @@ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); @@ -2173,6 +2264,9 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +int bpf_prog_test_run_nf(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -2202,7 +2296,7 @@ static inline bool bpf_tracing_btf_ctx_access(int off, int size, int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag); + u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id, @@ -2234,6 +2328,9 @@ bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); +int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, + u16 btf_fd_idx, u8 **func_addr); + struct bpf_core_ctx { struct bpf_verifier_log *log; const struct btf *btf; @@ -2241,7 +2338,7 @@ struct bpf_core_ctx { bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off); + const char *field_name, u32 btf_id, const char *suffix); bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, const struct btf *reg_btf, u32 reg_id, @@ -2266,6 +2363,11 @@ static inline bool has_current_bpf_ctx(void) } void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog); + +void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, + enum bpf_dynptr_type type, u32 offset, u32 size); +void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); +void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -2451,7 +2553,8 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id) static inline int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag) + u32 *next_btf_id, enum bpf_type_flag *flag, + const char **field_name) { return -EACCES; } @@ -2478,6 +2581,13 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog, return NULL; } +static inline int +bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, + u16 btf_fd_idx, u8 **func_addr) +{ + return -ENOTSUPP; +} + static inline bool unprivileged_ebpf_enabled(void) { return false; @@ -2495,6 +2605,19 @@ static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog) static inline void bpf_cgrp_storage_free(struct cgroup *cgroup) { } + +static inline void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, + enum bpf_dynptr_type type, u32 offset, u32 size) +{ +} + +static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) +{ +} + +static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) +{ +} #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, @@ -2566,6 +2689,7 @@ static inline bool bpf_map_is_offloaded(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); +u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map); int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); @@ -2637,6 +2761,11 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) { } +static inline u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map) +{ + return 0; +} + static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) @@ -2801,6 +2930,8 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); +int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, + struct bpf_dynptr_kern *ptr); #else static inline bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, @@ -2822,6 +2953,11 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, { return 0; } +static inline int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, + struct bpf_dynptr_kern *ptr) +{ + return -EOPNOTSUPP; +} #endif #ifdef CONFIG_INET @@ -2913,36 +3049,6 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 num_args, struct bpf_bprintf_data *data); void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); -/* the implementation of the opaque uapi struct bpf_dynptr */ -struct bpf_dynptr_kern { - void *data; - /* Size represents the number of usable bytes of dynptr data. - * If for example the offset is at 4 for a local dynptr whose data is - * of type u64, the number of usable bytes is 4. - * - * The upper 8 bits are reserved. It is as follows: - * Bits 0 - 23 = size - * Bits 24 - 30 = dynptr type - * Bit 31 = whether dynptr is read-only - */ - u32 size; - u32 offset; -} __aligned(8); - -enum bpf_dynptr_type { - BPF_DYNPTR_TYPE_INVALID, - /* Points to memory that is local to the bpf program */ - BPF_DYNPTR_TYPE_LOCAL, - /* Underlying data is a kernel-produced ringbuf record */ - BPF_DYNPTR_TYPE_RINGBUF, -}; - -void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, - enum bpf_dynptr_type type, u32 offset, u32 size); -void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); -int bpf_dynptr_check_size(u32 size); -u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr); - #ifdef CONFIG_BPF_LSM void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); void bpf_cgroup_atype_put(int cgroup_atype); diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 6d37a40cd90e..173ec7f43ed1 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -13,6 +13,7 @@ #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> +#include <linux/bpf_mem_alloc.h> #include <uapi/linux/btf.h> #define BPF_LOCAL_STORAGE_CACHE_SIZE 16 @@ -55,6 +56,9 @@ struct bpf_local_storage_map { u32 bucket_log; u16 elem_size; u16 cache_idx; + struct bpf_mem_alloc selem_ma; + struct bpf_mem_alloc storage_ma; + bool bpf_ma; }; struct bpf_local_storage_data { @@ -83,6 +87,7 @@ struct bpf_local_storage_elem { struct bpf_local_storage { struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; + struct bpf_local_storage_map __rcu *smap; struct hlist_head list; /* List of bpf_local_storage_elem */ void *owner; /* The object that owns the above "list" of * bpf_local_storage_elem. @@ -121,14 +126,15 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr); struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, - struct bpf_local_storage_cache *cache); + struct bpf_local_storage_cache *cache, + bool bpf_ma); struct bpf_local_storage_data * bpf_local_storage_lookup(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, bool cacheit_lockit); -bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage); +void bpf_local_storage_destroy(struct bpf_local_storage *local_storage); void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache, @@ -142,17 +148,19 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map, void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem); -void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu); +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now); void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem); -void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); - struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, bool charge_mem, gfp_t gfp_flags); +void bpf_selem_free(struct bpf_local_storage_elem *selem, + struct bpf_local_storage_map *smap, + bool reuse_now); + int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, @@ -163,6 +171,6 @@ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, void *value, u64 map_flags, gfp_t gfp_flags); -void bpf_local_storage_free_rcu(struct rcu_head *rcu); +u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map); #endif /* _BPF_LOCAL_STORAGE_H */ diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index 3e164b8efaa9..3929be5743f4 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -14,6 +14,13 @@ struct bpf_mem_alloc { struct work_struct work; }; +/* 'size != 0' is for bpf_mem_alloc which manages fixed-size objects. + * Alloc and free are done with bpf_mem_cache_{alloc,free}(). + * + * 'size = 0' is for bpf_mem_alloc which manages many fixed-size objects. + * Alloc and free are done with bpf_mem_{alloc,free}() and the size of + * the returned object is given by the size argument of bpf_mem_alloc(). + */ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); @@ -24,5 +31,7 @@ void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); /* kmem_cache_alloc/free equivalent: */ void *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma); void bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr); +void bpf_mem_cache_raw_free(void *ptr); +void *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags); #endif /* _BPF_MEM_ALLOC_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index d4ee3ccd3753..fc0d6f32c687 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -79,6 +79,10 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LSM, lsm, #endif BPF_PROG_TYPE(BPF_PROG_TYPE_SYSCALL, bpf_syscall, void *, void *) +#ifdef CONFIG_NETFILTER_BPF_LINK +BPF_PROG_TYPE(BPF_PROG_TYPE_NETFILTER, netfilter, + struct bpf_nf_ctx, struct bpf_nf_ctx) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index cf1bb1cf4a7b..3dd29a53b711 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -59,6 +59,14 @@ struct bpf_active_lock { u32 id; }; +#define ITER_PREFIX "bpf_iter_" + +enum bpf_iter_state { + BPF_ITER_STATE_INVALID, /* for non-first slot */ + BPF_ITER_STATE_ACTIVE, + BPF_ITER_STATE_DRAINED, +}; + struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; @@ -103,6 +111,18 @@ struct bpf_reg_state { bool first_slot; } dynptr; + /* For bpf_iter stack slots */ + struct { + /* BTF container and BTF type ID describing + * struct bpf_iter_<type> of an iterator state + */ + struct btf *btf; + u32 btf_id; + /* packing following two fields to fit iter state into 16 bytes */ + enum bpf_iter_state state:2; + int depth:30; + } iter; + /* Max size from any of the above. */ struct { unsigned long raw1; @@ -141,6 +161,8 @@ struct bpf_reg_state { * same reference to the socket, to determine proper reference freeing. * For stack slots that are dynptrs, this is used to track references to * the dynptr to determine proper reference freeing. + * Similarly to dynptrs, we use ID to track "belonging" of a reference + * to a specific instance of bpf_iter. */ u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned @@ -211,9 +233,11 @@ enum bpf_stack_slot_type { * is stored in bpf_stack_state->spilled_ptr.dynptr.type */ STACK_DYNPTR, + STACK_ITER, }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ + #define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern) #define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE) @@ -440,7 +464,12 @@ struct bpf_insn_aux_data { */ struct bpf_loop_inline_state loop_inline_state; }; - u64 obj_new_size; /* remember the size of type passed to bpf_obj_new to rewrite R1 */ + union { + /* remember the size of type passed to bpf_obj_new to rewrite R1 */ + u64 obj_new_size; + /* remember the offset of node field within type to rewrite */ + u64 insert_off; + }; struct btf_struct_meta *kptr_struct_meta; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ @@ -448,12 +477,17 @@ struct bpf_insn_aux_data { bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */ bool zext_dst; /* this insn zero extends dst reg */ bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */ + bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */ u8 alu_state; /* used in combination with alu_limit */ /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ - bool prune_point; bool jmp_point; + bool prune_point; + /* ensure we check state equivalence and save state checkpoint and + * this instruction, regardless of any heuristics + */ + bool force_checkpoint; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ @@ -462,39 +496,36 @@ struct bpf_insn_aux_data { #define BPF_VERIFIER_TMP_LOG_SIZE 1024 struct bpf_verifier_log { - u32 level; - char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; + /* Logical start and end positions of a "log window" of the verifier log. + * start_pos == 0 means we haven't truncated anything. + * Once truncation starts to happen, start_pos + len_total == end_pos, + * except during log reset situations, in which (end_pos - start_pos) + * might get smaller than len_total (see bpf_vlog_reset()). + * Generally, (end_pos - start_pos) gives number of useful data in + * user log buffer. + */ + u64 start_pos; + u64 end_pos; char __user *ubuf; - u32 len_used; + u32 level; u32 len_total; + u32 len_max; + char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; }; -static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) -{ - return log->len_used >= log->len_total - 1; -} - #define BPF_LOG_LEVEL1 1 #define BPF_LOG_LEVEL2 2 #define BPF_LOG_STATS 4 +#define BPF_LOG_FIXED 8 #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) -#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) +#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS | BPF_LOG_FIXED) #define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ #define BPF_LOG_MIN_ALIGNMENT 8U #define BPF_LOG_ALIGNMENT 40U static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { - return log && - ((log->level && log->ubuf && !bpf_verifier_log_full(log)) || - log->level == BPF_LOG_KERNEL); -} - -static inline bool -bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) -{ - return log->len_total >= 128 && log->len_total <= UINT_MAX >> 2 && - log->level && log->ubuf && !(log->level & ~BPF_LOG_MASK); + return log && log->level; } #define BPF_MAX_SUBPROGS 256 @@ -537,7 +568,6 @@ struct bpf_verifier_env { bool bypass_spec_v1; bool bypass_spec_v4; bool seen_direct_write; - bool rcu_tag_supported; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; @@ -575,7 +605,7 @@ struct bpf_verifier_env { u32 scratched_regs; /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; - u32 prev_log_len, prev_insn_print_len; + u64 prev_log_pos, prev_insn_print_pos; /* buffer used in reg_type_str() to generate reg_type string */ char type_str_buf[TYPE_STR_BUF_LEN]; }; @@ -586,6 +616,10 @@ __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...); +int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, + char __user *log_buf, u32 log_size); +void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos); +int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual); static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { @@ -616,9 +650,6 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, enum bpf_arg_type arg_type); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); -struct bpf_call_arg_meta; -int process_dynptr_func(struct bpf_verifier_env *env, int regno, - enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta); /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, diff --git a/include/linux/btf.h b/include/linux/btf.h index 49e0fe6d8274..508199e38415 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -18,7 +18,6 @@ #define KF_ACQUIRE (1 << 0) /* kfunc is an acquire function */ #define KF_RELEASE (1 << 1) /* kfunc is a release function */ #define KF_RET_NULL (1 << 2) /* kfunc returns a pointer that may be NULL */ -#define KF_KPTR_GET (1 << 3) /* kfunc returns reference to a kptr */ /* Trusted arguments are those which are guaranteed to be valid when passed to * the kfunc. It is used to enforce that pointers obtained from either acquire * kfuncs, or from the main kernel on a tracepoint or struct_ops callback @@ -70,7 +69,11 @@ #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */ #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ #define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */ -#define KF_RCU (1 << 7) /* kfunc only takes rcu pointer arguments */ +#define KF_RCU (1 << 7) /* kfunc takes either rcu or trusted pointer arguments */ +/* only one of KF_ITER_{NEW,NEXT,DESTROY} could be specified per kfunc */ +#define KF_ITER_NEW (1 << 8) /* kfunc implements BPF iter constructor */ +#define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ +#define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the @@ -109,7 +112,6 @@ struct btf_id_dtor_kfunc { struct btf_struct_meta { u32 btf_id; struct btf_record *record; - struct btf_field_offs *field_offs; }; struct btf_struct_metas { @@ -117,13 +119,11 @@ struct btf_struct_metas { struct btf_struct_meta types[]; }; -typedef void (*btf_dtor_kfunc_t)(void *); - extern const struct file_operations btf_fops; void btf_get(struct btf *btf); void btf_put(struct btf *btf); -int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr); +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, @@ -205,7 +205,6 @@ int btf_find_timer(const struct btf *btf, const struct btf_type *t); struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size); int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec); -struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 3a4f7cd882ca..00950cc03bff 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -204,7 +204,7 @@ extern struct btf_id_set8 name; #else -#define BTF_ID_LIST(name) static u32 __maybe_unused name[16]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[64]; #define BTF_ID(prefix, name) #define BTF_ID_FLAGS(prefix, name, ...) #define BTF_ID_UNUSED diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 8f14dca5fed7..1520793c72da 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -196,11 +196,17 @@ void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); +void folio_set_bh(struct buffer_head *bh, struct folio *folio, + unsigned long offset); bool try_to_free_buffers(struct folio *); +struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, + bool retry); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, unsigned long b_state); +void folio_create_empty_buffers(struct folio *folio, unsigned long blocksize, + unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); void end_buffer_write_sync(struct buffer_head *bh, int uptodate); void end_buffer_async_write(struct buffer_head *bh, int uptodate); diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 908e19d17f49..a5cfd44fab45 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -76,9 +76,11 @@ struct cpu_cacheinfo { unsigned int num_levels; unsigned int num_leaves; bool cpu_map_populated; + bool early_ci_levels; }; struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu); +int early_cache_level(unsigned int cpu); int init_cache_level(unsigned int cpu); int init_of_cache_level(unsigned int cpu); int populate_cache_leaves(unsigned int cpu); @@ -129,4 +131,10 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level) return -1; } +#ifdef CONFIG_ARM64 +#define use_arch_cache_info() (true) +#else +#define use_arch_cache_info() (false) +#endif + #endif /* _LINUX_CACHEINFO_H */ diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h new file mode 100644 index 000000000000..35ef41d8a61a --- /dev/null +++ b/include/linux/cdx/cdx_bus.h @@ -0,0 +1,174 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * CDX bus public interface + * + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + * + */ + +#ifndef _CDX_BUS_H_ +#define _CDX_BUS_H_ + +#include <linux/device.h> +#include <linux/list.h> +#include <linux/mod_devicetable.h> + +#define MAX_CDX_DEV_RESOURCES 4 +#define CDX_ANY_ID (0xFFFF) +#define CDX_CONTROLLER_ID_SHIFT 4 +#define CDX_BUS_NUM_MASK 0xF + +/* Forward declaration for CDX controller */ +struct cdx_controller; + +enum { + CDX_DEV_RESET_CONF, +}; + +struct cdx_device_config { + u8 type; +}; + +typedef int (*cdx_scan_cb)(struct cdx_controller *cdx); + +typedef int (*cdx_dev_configure_cb)(struct cdx_controller *cdx, + u8 bus_num, u8 dev_num, + struct cdx_device_config *dev_config); + +/** + * CDX_DEVICE_DRIVER_OVERRIDE - macro used to describe a CDX device with + * override_only flags. + * @vend: the 16 bit CDX Vendor ID + * @dev: the 16 bit CDX Device ID + * @driver_override: the 32 bit CDX Device override_only + * + * This macro is used to create a struct cdx_device_id that matches only a + * driver_override device. + */ +#define CDX_DEVICE_DRIVER_OVERRIDE(vend, dev, driver_override) \ + .vendor = (vend), .device = (dev), .override_only = (driver_override) + +/** + * struct cdx_ops - Callbacks supported by CDX controller. + * @scan: scan the devices on the controller + * @dev_configure: configuration like reset, master_enable, + * msi_config etc for a CDX device + */ +struct cdx_ops { + cdx_scan_cb scan; + cdx_dev_configure_cb dev_configure; +}; + +/** + * struct cdx_controller: CDX controller object + * @dev: Linux device associated with the CDX controller. + * @priv: private data + * @id: Controller ID + * @ops: CDX controller ops + */ +struct cdx_controller { + struct device *dev; + void *priv; + u32 id; + struct cdx_ops *ops; +}; + +/** + * struct cdx_device - CDX device object + * @dev: Linux driver model device object + * @cdx: CDX controller associated with the device + * @vendor: Vendor ID for CDX device + * @device: Device ID for CDX device + * @bus_num: Bus number for this CDX device + * @dev_num: Device number for this device + * @res: array of MMIO region entries + * @res_attr: resource binary attribute + * @res_count: number of valid MMIO regions + * @dma_mask: Default DMA mask + * @flags: CDX device flags + * @req_id: Requestor ID associated with CDX device + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. + */ +struct cdx_device { + struct device dev; + struct cdx_controller *cdx; + u16 vendor; + u16 device; + u8 bus_num; + u8 dev_num; + struct resource res[MAX_CDX_DEV_RESOURCES]; + u8 res_count; + u64 dma_mask; + u16 flags; + u32 req_id; + const char *driver_override; +}; + +#define to_cdx_device(_dev) \ + container_of(_dev, struct cdx_device, dev) + +/** + * struct cdx_driver - CDX device driver + * @driver: Generic device driver + * @match_id_table: table of supported device matching Ids + * @probe: Function called when a device is added + * @remove: Function called when a device is removed + * @shutdown: Function called at shutdown time to quiesce the device + * @reset_prepare: Function called before is reset to notify driver + * @reset_done: Function called after reset is complete to notify driver + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. + */ +struct cdx_driver { + struct device_driver driver; + const struct cdx_device_id *match_id_table; + int (*probe)(struct cdx_device *dev); + int (*remove)(struct cdx_device *dev); + void (*shutdown)(struct cdx_device *dev); + void (*reset_prepare)(struct cdx_device *dev); + void (*reset_done)(struct cdx_device *dev); + bool driver_managed_dma; +}; + +#define to_cdx_driver(_drv) \ + container_of(_drv, struct cdx_driver, driver) + +/* Macro to avoid include chaining to get THIS_MODULE */ +#define cdx_driver_register(drv) \ + __cdx_driver_register(drv, THIS_MODULE) + +/** + * __cdx_driver_register - registers a CDX device driver + * @cdx_driver: CDX driver to register + * @owner: module owner + * + * Return: -errno on failure, 0 on success. + */ +int __must_check __cdx_driver_register(struct cdx_driver *cdx_driver, + struct module *owner); + +/** + * cdx_driver_unregister - unregisters a device driver from the + * CDX bus. + * @cdx_driver: CDX driver to register + */ +void cdx_driver_unregister(struct cdx_driver *cdx_driver); + +extern struct bus_type cdx_bus_type; + +/** + * cdx_dev_reset - Reset CDX device + * @dev: device pointer + * + * Return: 0 for success, -errno on failure + */ +int cdx_dev_reset(struct device *dev); + +#endif /* _CDX_BUS_H_ */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3410aecffdb4..885f5395fcd0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -692,7 +692,7 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); -void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp); +void cgroup_rstat_flush_atomic(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(void); diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..28ff6f1a6ada 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -608,6 +608,25 @@ struct clk *clk_register_gate(struct device *dev, const char *name, __devm_clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ NULL, (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) +/** + * devm_clk_hw_register_gate_parent_data - register a gate clock with the + * clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_gate_parent_data(dev, name, parent_data, flags, \ + reg, bit_idx, clk_gate_flags, \ + lock) \ + __devm_clk_hw_register_gate((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) + void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); int clk_gate_is_enabled(struct clk_hw *hw); @@ -1135,10 +1154,8 @@ struct clk_fractional_divider { void __iomem *reg; u8 mshift; u8 mwidth; - u32 mmask; u8 nshift; u8 nwidth; - u32 nmask; u8 flags; void (*approximation)(struct clk_hw *hw, unsigned long rate, unsigned long *parent_rate, @@ -1363,7 +1380,13 @@ struct clk_hw_onecell_data { struct clk_hw *hws[]; }; -#define CLK_OF_DECLARE(name, compat, fn) OF_DECLARE_1(clk, name, compat, fn) +#define CLK_OF_DECLARE(name, compat, fn) \ + static void __init __##name##_of_clk_init_declare(struct device_node *np) \ + { \ + fn(np); \ + fwnode_dev_initialized(of_fwnode_handle(np), true); \ + } \ + OF_DECLARE_1(clk, name, compat, __##name##_of_clk_init_declare) /* * Use this macro when you have a driver that requires two initialization diff --git a/include/linux/cm4000_cs.h b/include/linux/cm4000_cs.h deleted file mode 100644 index ea4958e07a14..000000000000 --- a/include/linux/cm4000_cs.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CM4000_H_ -#define _CM4000_H_ - -#include <uapi/linux/cm4000_cs.h> - - -#define DEVICE_NAME "cmm" -#define MODULE_NAME "cm4000_cs" - -#endif /* _CM4000_H_ */ diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 52a9ff65faee..a6e512cfb670 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -81,13 +81,6 @@ static inline unsigned long compact_gap(unsigned int order) } #ifdef CONFIG_COMPACTION -extern unsigned int sysctl_compaction_proactiveness; -extern int sysctl_compaction_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, loff_t *ppos); -extern int compaction_proactiveness_sysctl_handler(struct ctl_table *table, - int write, void *buffer, size_t *length, loff_t *ppos); -extern int sysctl_extfrag_threshold; -extern int sysctl_compact_unevictable_allowed; extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); extern int fragmentation_index(struct zone *zone, unsigned int order); diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 947a60b801db..d7779a18b24f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -12,11 +12,10 @@ * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. */ -#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ - && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect, int is_constant); - +#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ + && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d4afa8508a80..d3cbb6c16bab 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -96,8 +96,9 @@ static inline void user_exit_irqoff(void) { } static inline int exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } +static inline int __ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } -static inline void context_tracking_guest_exit(void) { } +static __always_inline void context_tracking_guest_exit(void) { } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 4a4d56f77180..fdd537ea513f 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -46,7 +46,9 @@ struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); +#endif +#ifdef CONFIG_CONTEXT_TRACKING_USER static __always_inline int __ct_state(void) { return arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK; diff --git a/include/linux/cper.h b/include/linux/cper.h index eacb7dd7b3af..c1a7dc325121 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -572,4 +572,10 @@ void cper_print_proc_ia(const char *pfx, int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); +struct acpi_hest_generic_status; +void cper_estatus_print(const char *pfx, + const struct acpi_hest_generic_status *estatus); +int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus); +int cper_estatus_check(const struct acpi_hest_generic_status *estatus); + #endif diff --git a/include/linux/cpu.h b/include/linux/cpu.h index f83e4519c5f0..8582a7142623 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -182,7 +182,7 @@ void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); -void arch_cpu_idle_dead(void); +void __noreturn arch_cpu_idle_dead(void); int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h index be8aea04d023..cae324d10965 100644 --- a/include/linux/cpu_rmap.h +++ b/include/linux/cpu_rmap.h @@ -16,14 +16,13 @@ * struct cpu_rmap - CPU affinity reverse-map * @refcount: kref for object * @size: Number of objects to be reverse-mapped - * @used: Number of objects added * @obj: Pointer to array of object pointers * @near: For each CPU, the index and distance to the nearest object, * based on affinity masks */ struct cpu_rmap { struct kref refcount; - u16 size, used; + u16 size; void **obj; struct { u16 index; @@ -61,6 +60,7 @@ static inline struct cpu_rmap *alloc_irq_cpu_rmap(unsigned int size) } extern void free_irq_cpu_rmap(struct cpu_rmap *rmap); +int irq_cpu_rmap_remove(struct cpu_rmap *rmap, int irq); extern int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq); #endif /* __LINUX_CPU_RMAP_H */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 65623233ab2f..26e2eb399484 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -15,7 +15,6 @@ #include <linux/kobject.h> #include <linux/notifier.h> #include <linux/of.h> -#include <linux/of_device.h> #include <linux/pm_opp.h> #include <linux/pm_qos.h> #include <linux/spinlock.h> @@ -237,6 +236,7 @@ bool cpufreq_supports_freq_invariance(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); void cpufreq_disable_fast_switch(struct cpufreq_policy *policy); +bool has_target_index(void); #else static inline unsigned int cpufreq_get(unsigned int cpu) { diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c6fab004104a..3ceb9dfa0993 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -163,7 +163,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_MIPS_OP_LOONGSON3_STARTING, - CPUHP_AP_ARM_SDEI_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, @@ -201,6 +200,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_HYPERV_ONLINE, CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, @@ -218,7 +218,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_X86_IDXD_ONLINE, - CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index d4901ca8883c..ca736b05ec7b 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -351,6 +351,23 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** + * for_each_cpu_or - iterate over every cpu present in either mask + * @cpu: the (optionally unsigned) integer iterator + * @mask1: the first cpumask pointer + * @mask2: the second cpumask pointer + * + * This saves a temporary CPU mask in many places. It is equivalent to: + * struct cpumask tmp; + * cpumask_or(&tmp, &mask1, &mask2); + * for_each_cpu(cpu, &tmp) + * ... + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_or(cpu, mask1, mask2) \ + for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) + +/** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d58e0476ee8e..980b76a1237e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -80,18 +80,11 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p); void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); -extern bool __cpuset_node_allowed(int node, gfp_t gfp_mask); - -static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) -{ - if (cpusets_enabled()) - return __cpuset_node_allowed(node, gfp_mask); - return true; -} +extern bool cpuset_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { - return __cpuset_node_allowed(zone_to_nid(z), gfp_mask); + return cpuset_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) @@ -223,11 +216,6 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) return 1; } -static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) -{ - return true; -} - static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; diff --git a/include/linux/crc32c.h b/include/linux/crc32c.h index bd21af828ff6..357ae4611a45 100644 --- a/include/linux/crc32c.h +++ b/include/linux/crc32c.h @@ -5,7 +5,6 @@ #include <linux/types.h> extern u32 crc32c(u32 crc, const void *address, unsigned int length); -extern const char *crc32c_impl(void); /* This macro exists for backwards-compatibility. */ #define crc32c_le crc32c diff --git a/include/linux/crypto.h b/include/linux/crypto.h index bb1d9b0e1647..fa310ac1db59 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -12,26 +12,10 @@ #ifndef _LINUX_CRYPTO_H #define _LINUX_CRYPTO_H -#include <linux/atomic.h> -#include <linux/kernel.h> -#include <linux/list.h> -#include <linux/bug.h> +#include <linux/completion.h> #include <linux/refcount.h> #include <linux/slab.h> -#include <linux/completion.h> - -/* - * Autoloaded crypto modules should only use a prefixed name to avoid allowing - * arbitrary modules to be loaded. Loading from userspace may still need the - * unprefixed names, so retains those aliases as well. - * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3 - * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro - * expands twice on the same line. Instead, use a separate base name for the - * alias. - */ -#define MODULE_ALIAS_CRYPTO(name) \ - __MODULE_INFO(alias, alias_userspace, name); \ - __MODULE_INFO(alias, alias_crypto, "crypto-" name) +#include <linux/types.h> /* * Algorithm masks and types. @@ -171,10 +155,9 @@ #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN))) -struct scatterlist; -struct crypto_async_request; struct crypto_tfm; struct crypto_type; +struct module; typedef void (*crypto_completion_t)(void *req, int err); @@ -275,116 +258,6 @@ struct compress_alg { unsigned int slen, u8 *dst, unsigned int *dlen); }; -#ifdef CONFIG_CRYPTO_STATS -/* - * struct crypto_istat_aead - statistics for AEAD algorithm - * @encrypt_cnt: number of encrypt requests - * @encrypt_tlen: total data size handled by encrypt requests - * @decrypt_cnt: number of decrypt requests - * @decrypt_tlen: total data size handled by decrypt requests - * @err_cnt: number of error for AEAD requests - */ -struct crypto_istat_aead { - atomic64_t encrypt_cnt; - atomic64_t encrypt_tlen; - atomic64_t decrypt_cnt; - atomic64_t decrypt_tlen; - atomic64_t err_cnt; -}; - -/* - * struct crypto_istat_akcipher - statistics for akcipher algorithm - * @encrypt_cnt: number of encrypt requests - * @encrypt_tlen: total data size handled by encrypt requests - * @decrypt_cnt: number of decrypt requests - * @decrypt_tlen: total data size handled by decrypt requests - * @verify_cnt: number of verify operation - * @sign_cnt: number of sign requests - * @err_cnt: number of error for akcipher requests - */ -struct crypto_istat_akcipher { - atomic64_t encrypt_cnt; - atomic64_t encrypt_tlen; - atomic64_t decrypt_cnt; - atomic64_t decrypt_tlen; - atomic64_t verify_cnt; - atomic64_t sign_cnt; - atomic64_t err_cnt; -}; - -/* - * struct crypto_istat_cipher - statistics for cipher algorithm - * @encrypt_cnt: number of encrypt requests - * @encrypt_tlen: total data size handled by encrypt requests - * @decrypt_cnt: number of decrypt requests - * @decrypt_tlen: total data size handled by decrypt requests - * @err_cnt: number of error for cipher requests - */ -struct crypto_istat_cipher { - atomic64_t encrypt_cnt; - atomic64_t encrypt_tlen; - atomic64_t decrypt_cnt; - atomic64_t decrypt_tlen; - atomic64_t err_cnt; -}; - -/* - * struct crypto_istat_compress - statistics for compress algorithm - * @compress_cnt: number of compress requests - * @compress_tlen: total data size handled by compress requests - * @decompress_cnt: number of decompress requests - * @decompress_tlen: total data size handled by decompress requests - * @err_cnt: number of error for compress requests - */ -struct crypto_istat_compress { - atomic64_t compress_cnt; - atomic64_t compress_tlen; - atomic64_t decompress_cnt; - atomic64_t decompress_tlen; - atomic64_t err_cnt; -}; - -/* - * struct crypto_istat_hash - statistics for has algorithm - * @hash_cnt: number of hash requests - * @hash_tlen: total data size hashed - * @err_cnt: number of error for hash requests - */ -struct crypto_istat_hash { - atomic64_t hash_cnt; - atomic64_t hash_tlen; - atomic64_t err_cnt; -}; - -/* - * struct crypto_istat_kpp - statistics for KPP algorithm - * @setsecret_cnt: number of setsecrey operation - * @generate_public_key_cnt: number of generate_public_key operation - * @compute_shared_secret_cnt: number of compute_shared_secret operation - * @err_cnt: number of error for KPP requests - */ -struct crypto_istat_kpp { - atomic64_t setsecret_cnt; - atomic64_t generate_public_key_cnt; - atomic64_t compute_shared_secret_cnt; - atomic64_t err_cnt; -}; - -/* - * struct crypto_istat_rng: statistics for RNG algorithm - * @generate_cnt: number of RNG generate requests - * @generate_tlen: total data size of generated data by the RNG - * @seed_cnt: number of times the RNG was seeded - * @err_cnt: number of error for RNG requests - */ -struct crypto_istat_rng { - atomic64_t generate_cnt; - atomic64_t generate_tlen; - atomic64_t seed_cnt; - atomic64_t err_cnt; -}; -#endif /* CONFIG_CRYPTO_STATS */ - #define cra_cipher cra_u.cipher #define cra_compress cra_u.compress @@ -462,15 +335,6 @@ struct crypto_istat_rng { * @cra_refcnt: internally used * @cra_destroy: internally used * - * @stats: union of all possible crypto_istat_xxx structures - * @stats.aead: statistics for AEAD algorithm - * @stats.akcipher: statistics for akcipher algorithm - * @stats.cipher: statistics for cipher algorithm - * @stats.compress: statistics for compress algorithm - * @stats.hash: statistics for hash algorithm - * @stats.rng: statistics for rng algorithm - * @stats.kpp: statistics for KPP algorithm - * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not * be used by a cipher implementation as it is internal to the Crypto API. @@ -502,81 +366,8 @@ struct crypto_alg { void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; - -#ifdef CONFIG_CRYPTO_STATS - union { - struct crypto_istat_aead aead; - struct crypto_istat_akcipher akcipher; - struct crypto_istat_cipher cipher; - struct crypto_istat_compress compress; - struct crypto_istat_hash hash; - struct crypto_istat_rng rng; - struct crypto_istat_kpp kpp; - } stats; -#endif /* CONFIG_CRYPTO_STATS */ - } CRYPTO_MINALIGN_ATTR; -#ifdef CONFIG_CRYPTO_STATS -void crypto_stats_init(struct crypto_alg *alg); -void crypto_stats_get(struct crypto_alg *alg); -void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); -void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); -void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg); -void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg); -void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg); -void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret, struct crypto_alg *alg); -void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg); -void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg); -void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg); -void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg); -void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret); -void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret); -void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret); -void crypto_stats_rng_seed(struct crypto_alg *alg, int ret); -void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret); -void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); -void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); -#else -static inline void crypto_stats_init(struct crypto_alg *alg) -{} -static inline void crypto_stats_get(struct crypto_alg *alg) -{} -static inline void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) -{} -static inline void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) -{} -static inline void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret) -{} -static inline void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret) -{} -static inline void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret) -{} -static inline void crypto_stats_rng_seed(struct crypto_alg *alg, int ret) -{} -static inline void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret) -{} -static inline void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg) -{} -#endif /* * A helper struct for waiting for completion of async crypto ops */ @@ -617,14 +408,6 @@ static inline void crypto_init_wait(struct crypto_wait *wait) } /* - * Algorithm registration interface. - */ -int crypto_register_alg(struct crypto_alg *alg); -void crypto_unregister_alg(struct crypto_alg *alg); -int crypto_register_algs(struct crypto_alg *algs, int count); -void crypto_unregister_algs(struct crypto_alg *algs, int count); - -/* * Algorithm query interface. */ int crypto_has_alg(const char *name, u32 type, u32 mask); @@ -636,6 +419,7 @@ int crypto_has_alg(const char *name, u32 type, u32 mask); */ struct crypto_tfm { + refcount_t refcnt; u32 crt_flags; @@ -664,8 +448,6 @@ static inline void crypto_free_tfm(struct crypto_tfm *tfm) return crypto_destroy_tfm(tfm, tfm); } -int alg_test(const char *driver, const char *alg, u32 type, u32 mask); - /* * Transform helpers which query the underlying algorithm. */ @@ -679,16 +461,6 @@ static inline const char *crypto_tfm_alg_driver_name(struct crypto_tfm *tfm) return tfm->__crt_alg->cra_driver_name; } -static inline int crypto_tfm_alg_priority(struct crypto_tfm *tfm) -{ - return tfm->__crt_alg->cra_priority; -} - -static inline u32 crypto_tfm_alg_type(struct crypto_tfm *tfm) -{ - return tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK; -} - static inline unsigned int crypto_tfm_alg_blocksize(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_blocksize; diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 07e547c02fd8..325af611909f 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -305,10 +305,8 @@ struct dccp_sock { struct timer_list dccps_xmit_timer; }; -static inline struct dccp_sock *dccp_sk(const struct sock *sk) -{ - return (struct dccp_sock *)sk; -} +#define dccp_sk(ptr) container_of_const(ptr, struct dccp_sock, \ + dccps_inet_connection.icsk_inet.sk) static inline const char *dccp_role(const struct sock *sk) { diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 0da97dba9ef8..6639f48dac36 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -48,10 +48,13 @@ struct task_delay_info { u64 wpcopy_start; u64 wpcopy_delay; /* wait for write-protect copy */ + u64 irq_delay; /* wait for IRQ/SOFTIRQ */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ u32 compact_count; /* total count of memory compact */ u32 wpcopy_count; /* total count of write-protect copy */ + u32 irq_count; /* total count of IRQ/SOFTIRQ */ }; #endif @@ -81,6 +84,7 @@ extern void __delayacct_compact_start(void); extern void __delayacct_compact_end(void); extern void __delayacct_wpcopy_start(void); extern void __delayacct_wpcopy_end(void); +extern void __delayacct_irq(struct task_struct *task, u32 delta); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -215,6 +219,15 @@ static inline void delayacct_wpcopy_end(void) __delayacct_wpcopy_end(); } +static inline void delayacct_irq(struct task_struct *task, u32 delta) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (task->delays) + __delayacct_irq(task, delta); +} + #else static inline void delayacct_init(void) {} @@ -253,6 +266,8 @@ static inline void delayacct_wpcopy_start(void) {} static inline void delayacct_wpcopy_end(void) {} +static inline void delayacct_irq(struct task_struct *task, u32 delta) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 7975483816e4..a52d2b9a6846 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -359,6 +359,24 @@ struct dm_target { bool discards_supported:1; /* + * Set if this target requires that discards be split on + * 'max_discard_sectors' boundaries. + */ + bool max_discard_granularity:1; + + /* + * Set if this target requires that secure_erases be split on + * 'max_secure_erase_sectors' boundaries. + */ + bool max_secure_erase_granularity:1; + + /* + * Set if this target requires that write_zeroes be split on + * 'max_write_zeroes_sectors' boundaries. + */ + bool max_write_zeroes_granularity:1; + + /* * Set if we need to limit the number of in-flight bios when swapping. */ bool limit_swap_bios:1; @@ -512,8 +530,6 @@ int __init dm_early_create(struct dm_ioctl *dmi, struct dm_target_spec **spec_array, char **target_params_array); -struct queue_limits *dm_get_queue_limits(struct mapped_device *md); - /* * Geometry functions. */ @@ -625,6 +641,26 @@ void dm_destroy_crypto_profile(struct blk_crypto_profile *profile); DMEMIT("target_name=%s,target_version=%u.%u.%u", \ (y)->name, (y)->version[0], (y)->version[1], (y)->version[2]) +/** + * module_dm() - Helper macro for DM targets that don't do anything + * special in their module_init and module_exit. + * Each module may only use this macro once, and calling it replaces + * module_init() and module_exit(). + * + * @name: DM target's name + */ +#define module_dm(name) \ +static int __init dm_##name##_init(void) \ +{ \ + return dm_register_target(&(name##_target)); \ +} \ +module_init(dm_##name##_init) \ +static void __exit dm_##name##_exit(void) \ +{ \ + dm_unregister_target(&(name##_target)); \ +} \ +module_exit(dm_##name##_exit) + /* * Definitions of return values from target end_io function. */ diff --git a/include/linux/device.h b/include/linux/device.h index 1508e637bb26..472dd24d4823 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -243,21 +243,26 @@ void __iomem *devm_of_iomap(struct device *dev, resource_size_t *size); /* allows to add/remove a custom action to devres stack */ -int devm_add_action(struct device *dev, void (*action)(void *), void *data); void devm_remove_action(struct device *dev, void (*action)(void *), void *data); void devm_release_action(struct device *dev, void (*action)(void *), void *data); -static inline int devm_add_action_or_reset(struct device *dev, - void (*action)(void *), void *data) +int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); +#define devm_add_action(release, action, data) \ + __devm_add_action(release, action, data, #action) + +static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *), + void *data, const char *name) { int ret; - ret = devm_add_action(dev, action, data); + ret = __devm_add_action(dev, action, data, name); if (ret) action(data); return ret; } +#define devm_add_action_or_reset(release, action, data) \ + __devm_add_action_or_reset(release, action, data, #action) /** * devm_alloc_percpu - Resource-managed alloc_percpu @@ -561,7 +566,7 @@ struct device { const char *init_name; /* initial name of the device */ const struct device_type *type; - struct bus_type *bus; /* type of bus device is on */ + const struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device @@ -626,7 +631,7 @@ struct device { spinlock_t devres_lock; struct list_head devres_head; - struct class *class; + const struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); @@ -1010,13 +1015,13 @@ bool device_is_bound(struct device *dev); * Easy functions for dynamically creating devices on the fly */ __printf(5, 6) struct device * -device_create(struct class *cls, struct device *parent, dev_t devt, +device_create(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...); __printf(6, 7) struct device * -device_create_with_groups(struct class *cls, struct device *parent, dev_t devt, +device_create_with_groups(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); -void device_destroy(struct class *cls, dev_t devt); +void device_destroy(const struct class *cls, dev_t devt); int __must_check device_add_groups(struct device *dev, const struct attribute_group **groups); @@ -1083,8 +1088,7 @@ void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); -extern __printf(3, 4) -int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); +__printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ @@ -1092,10 +1096,4 @@ int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); #define MODULE_ALIAS_CHARDEV_MAJOR(major) \ MODULE_ALIAS("char-major-" __stringify(major) "-*") -#ifdef CONFIG_SYSFS_DEPRECATED -extern long sysfs_deprecated; -#else -#define sysfs_deprecated 0 -#endif - #endif /* _DEVICE_H_ */ diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 6ce32ef4b8fd..ae10c4322754 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -26,7 +26,6 @@ struct fwnode_handle; * * @name: The name of the bus. * @dev_name: Used for subsystems to enumerate devices like ("foo%u", dev->id). - * @dev_root: Default device to use as the parent. * @bus_groups: Default attributes of the bus. * @dev_groups: Default attributes of the devices on the bus. * @drv_groups: Default attributes of the device drivers on the bus. @@ -66,7 +65,6 @@ struct fwnode_handle; * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU * driver implementations to a bus and allow the driver to do * bus-specific setup - * @lock_key: Lock class key for use by the lock validator * @need_parent_lock: When probing or removing a device on this bus, the * device core should lock the device's parent. * @@ -82,7 +80,6 @@ struct fwnode_handle; struct bus_type { const char *name; const char *dev_name; - struct device *dev_root; const struct attribute_group **bus_groups; const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; @@ -112,16 +109,16 @@ struct bus_type { bool need_parent_lock; }; -extern int __must_check bus_register(struct bus_type *bus); +int __must_check bus_register(const struct bus_type *bus); -extern void bus_unregister(const struct bus_type *bus); +void bus_unregister(const struct bus_type *bus); -extern int __must_check bus_rescan_devices(struct bus_type *bus); +int __must_check bus_rescan_devices(const struct bus_type *bus); struct bus_attribute { struct attribute attr; - ssize_t (*show)(struct bus_type *bus, char *buf); - ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count); + ssize_t (*show)(const struct bus_type *bus, char *buf); + ssize_t (*store)(const struct bus_type *bus, const char *buf, size_t count); }; #define BUS_ATTR_RW(_name) \ @@ -246,10 +243,8 @@ void bus_sort_breadthfirst(struct bus_type *bus, */ struct notifier_block; -extern int bus_register_notifier(const struct bus_type *bus, - struct notifier_block *nb); -extern int bus_unregister_notifier(const struct bus_type *bus, - struct notifier_block *nb); +int bus_register_notifier(const struct bus_type *bus, struct notifier_block *nb); +int bus_unregister_notifier(const struct bus_type *bus, struct notifier_block *nb); /** * enum bus_notifier_event - Bus Notifier events that have happened @@ -281,7 +276,7 @@ enum bus_notifier_event { BUS_NOTIFY_DRIVER_NOT_BOUND, }; -extern struct kset *bus_get_kset(const struct bus_type *bus); +struct kset *bus_get_kset(const struct bus_type *bus); struct device *bus_get_dev_root(const struct bus_type *bus); #endif diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 42cc3fb44a84..abf3d3bfb6fe 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -25,10 +25,8 @@ struct fwnode_handle; /** * struct class - device classes * @name: Name of the class. - * @owner: The module owner. * @class_groups: Default attributes of this class. * @dev_groups: Default attributes of the devices that belong to the class. - * @dev_kobj: The kobject that represents this class and links it into the hierarchy. * @dev_uevent: Called when a device is added, removed from this class, or a * few other things that generate uevents to add the environment * variables. @@ -53,16 +51,14 @@ struct fwnode_handle; */ struct class { const char *name; - struct module *owner; const struct attribute_group **class_groups; const struct attribute_group **dev_groups; - struct kobject *dev_kobj; int (*dev_uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode); - void (*class_release)(struct class *class); + void (*class_release)(const struct class *class); void (*dev_release)(struct device *dev); int (*shutdown_pre)(struct device *dev); @@ -73,28 +69,17 @@ struct class { void (*get_ownership)(const struct device *dev, kuid_t *uid, kgid_t *gid); const struct dev_pm_ops *pm; - - struct subsys_private *p; }; struct class_dev_iter { struct klist_iter ki; const struct device_type *type; + struct subsys_private *sp; }; -extern struct kobject *sysfs_dev_block_kobj; -extern struct kobject *sysfs_dev_char_kobj; -extern int __must_check __class_register(struct class *class, - struct lock_class_key *key); -extern void class_unregister(struct class *class); - -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ -#define class_register(class) \ -({ \ - static struct lock_class_key __key; \ - __class_register(class, &__key); \ -}) +int __must_check class_register(const struct class *class); +void class_unregister(const struct class *class); +bool class_is_registered(const struct class *class); struct class_compat; struct class_compat *class_compat_register(const char *name); @@ -104,19 +89,15 @@ int class_compat_create_link(struct class_compat *cls, struct device *dev, void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); -extern void class_dev_iter_init(struct class_dev_iter *iter, - struct class *class, - struct device *start, - const struct device_type *type); -extern struct device *class_dev_iter_next(struct class_dev_iter *iter); -extern void class_dev_iter_exit(struct class_dev_iter *iter); +void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, + const struct device *start, const struct device_type *type); +struct device *class_dev_iter_next(struct class_dev_iter *iter); +void class_dev_iter_exit(struct class_dev_iter *iter); -extern int class_for_each_device(struct class *class, struct device *start, - void *data, - int (*fn)(struct device *dev, void *data)); -extern struct device *class_find_device(struct class *class, - struct device *start, const void *data, - int (*match)(struct device *, const void *)); +int class_for_each_device(const struct class *class, const struct device *start, void *data, + int (*fn)(struct device *dev, void *data)); +struct device *class_find_device(const struct class *class, const struct device *start, + const void *data, int (*match)(struct device *, const void *)); /** * class_find_device_by_name - device iterator for locating a particular device @@ -124,7 +105,7 @@ extern struct device *class_find_device(struct class *class, * @class: class type * @name: name of the device to match */ -static inline struct device *class_find_device_by_name(struct class *class, +static inline struct device *class_find_device_by_name(const struct class *class, const char *name) { return class_find_device(class, NULL, name, device_match_name); @@ -136,8 +117,8 @@ static inline struct device *class_find_device_by_name(struct class *class, * @class: class type * @np: of_node of the device to match. */ -static inline struct device * -class_find_device_by_of_node(struct class *class, const struct device_node *np) +static inline struct device *class_find_device_by_of_node(const struct class *class, + const struct device_node *np) { return class_find_device(class, NULL, np, device_match_of_node); } @@ -148,9 +129,8 @@ class_find_device_by_of_node(struct class *class, const struct device_node *np) * @class: class type * @fwnode: fwnode of the device to match. */ -static inline struct device * -class_find_device_by_fwnode(struct class *class, - const struct fwnode_handle *fwnode) +static inline struct device *class_find_device_by_fwnode(const struct class *class, + const struct fwnode_handle *fwnode) { return class_find_device(class, NULL, fwnode, device_match_fwnode); } @@ -161,7 +141,7 @@ class_find_device_by_fwnode(struct class *class, * @class: class type * @devt: device type of the device to match. */ -static inline struct device *class_find_device_by_devt(struct class *class, +static inline struct device *class_find_device_by_devt(const struct class *class, dev_t devt) { return class_find_device(class, NULL, &devt, device_match_devt); @@ -175,14 +155,14 @@ struct acpi_device; * @class: class type * @adev: ACPI_COMPANION device to match. */ -static inline struct device * -class_find_device_by_acpi_dev(struct class *class, const struct acpi_device *adev) +static inline struct device *class_find_device_by_acpi_dev(const struct class *class, + const struct acpi_device *adev) { return class_find_device(class, NULL, adev, device_match_acpi_dev); } #else -static inline struct device * -class_find_device_by_acpi_dev(struct class *class, const void *adev) +static inline struct device *class_find_device_by_acpi_dev(const struct class *class, + const void *adev) { return NULL; } @@ -190,10 +170,10 @@ class_find_device_by_acpi_dev(struct class *class, const void *adev) struct class_attribute { struct attribute attr; - ssize_t (*show)(struct class *class, struct class_attribute *attr, + ssize_t (*show)(const struct class *class, const struct class_attribute *attr, char *buf); - ssize_t (*store)(struct class *class, struct class_attribute *attr, - const char *buf, size_t count); + ssize_t (*store)(const struct class *class, const struct class_attribute *attr, + const char *buf, size_t count); }; #define CLASS_ATTR_RW(_name) \ @@ -203,20 +183,18 @@ struct class_attribute { #define CLASS_ATTR_WO(_name) \ struct class_attribute class_attr_##_name = __ATTR_WO(_name) -extern int __must_check class_create_file_ns(struct class *class, - const struct class_attribute *attr, - const void *ns); -extern void class_remove_file_ns(struct class *class, - const struct class_attribute *attr, - const void *ns); +int __must_check class_create_file_ns(const struct class *class, const struct class_attribute *attr, + const void *ns); +void class_remove_file_ns(const struct class *class, const struct class_attribute *attr, + const void *ns); -static inline int __must_check class_create_file(struct class *class, - const struct class_attribute *attr) +static inline int __must_check class_create_file(const struct class *class, + const struct class_attribute *attr) { return class_create_file_ns(class, attr, NULL); } -static inline void class_remove_file(struct class *class, +static inline void class_remove_file(const struct class *class, const struct class_attribute *attr) { return class_remove_file_ns(class, attr, NULL); @@ -235,46 +213,21 @@ struct class_attribute_string { struct class_attribute_string class_attr_##_name = \ _CLASS_ATTR_STRING(_name, _mode, _str) -extern ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, - char *buf); +ssize_t show_class_attr_string(const struct class *class, const struct class_attribute *attr, + char *buf); struct class_interface { struct list_head node; - struct class *class; + const struct class *class; - int (*add_dev) (struct device *, struct class_interface *); - void (*remove_dev) (struct device *, struct class_interface *); + int (*add_dev) (struct device *dev); + void (*remove_dev) (struct device *dev); }; -extern int __must_check class_interface_register(struct class_interface *); -extern void class_interface_unregister(struct class_interface *); - -extern struct class * __must_check __class_create(struct module *owner, - const char *name, - struct lock_class_key *key); -extern void class_destroy(struct class *cls); - -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ - -/** - * class_create - create a struct class structure - * @owner: pointer to the module that is to "own" this struct class - * @name: pointer to a string for the name of this class. - * - * This is used to create a struct class pointer that can then be used - * in calls to device_create(). - * - * Returns &struct class pointer on success, or ERR_PTR() on error. - * - * Note, the pointer created here is to be destroyed when finished by - * making a call to class_destroy(). - */ -#define class_create(owner, name) \ -({ \ - static struct lock_class_key __key; \ - __class_create(owner, name, &__key); \ -}) +int __must_check class_interface_register(struct class_interface *); +void class_interface_unregister(struct class_interface *); +struct class * __must_check class_create(const char *name); +void class_destroy(const struct class *cls); #endif /* _DEVICE_CLASS_H_ */ diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 50d0a416a5e7..c244267a6744 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -95,7 +95,7 @@ enum probe_type { */ struct device_driver { const char *name; - struct bus_type *bus; + const struct bus_type *bus; struct module *owner; const char *mod_name; /* used for built-in modules */ @@ -122,13 +122,12 @@ struct device_driver { }; -extern int __must_check driver_register(struct device_driver *drv); -extern void driver_unregister(struct device_driver *drv); +int __must_check driver_register(struct device_driver *drv); +void driver_unregister(struct device_driver *drv); -extern struct device_driver *driver_find(const char *name, - struct bus_type *bus); -extern int driver_probe_done(void); -extern void wait_for_device_probe(void); +struct device_driver *driver_find(const char *name, const struct bus_type *bus); +int driver_probe_done(void); +void wait_for_device_probe(void); void __init wait_for_init_devices_probe(void); /* sysfs interface for exporting driver attributes */ @@ -147,18 +146,15 @@ struct driver_attribute { #define DRIVER_ATTR_WO(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) -extern int __must_check driver_create_file(struct device_driver *driver, - const struct driver_attribute *attr); -extern void driver_remove_file(struct device_driver *driver, - const struct driver_attribute *attr); +int __must_check driver_create_file(struct device_driver *driver, + const struct driver_attribute *attr); +void driver_remove_file(struct device_driver *driver, + const struct driver_attribute *attr); int driver_set_override(struct device *dev, const char **override, const char *s, size_t len); -extern int __must_check driver_for_each_device(struct device_driver *drv, - struct device *start, - void *data, - int (*fn)(struct device *dev, - void *)); +int __must_check driver_for_each_device(struct device_driver *drv, struct device *start, + void *data, int (*fn)(struct device *dev, void *)); struct device *driver_find_device(struct device_driver *drv, struct device *start, const void *data, int (*match)(struct device *dev, const void *data)); diff --git a/include/linux/dim.h b/include/linux/dim.h index 6c5733981563..f343bc9aa2ec 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -236,8 +236,9 @@ void dim_park_tired(struct dim *dim); * * Calculate the delta between two samples (in data rates). * Takes into consideration counter wrap-around. + * Returned boolean indicates whether curr_stats are reliable. */ -void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, +bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, struct dim_stats *curr_stats); /** diff --git a/include/linux/dlm.h b/include/linux/dlm.h index c6bc2b5ee7e6..c58c4f790c04 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -53,9 +53,6 @@ struct dlm_lockspace_ops { * The dlm should not use a resource directory, but statically assign * resource mastery to nodes based on the name hash that is otherwise * used to select the directory node. Must be the same on all nodes. - * DLM_LSFL_TIMEWARN - * The dlm should emit netlink messages if locks have been waiting - * for a configurable amount of time. (Unused.) * DLM_LSFL_NEWEXCL * dlm_new_lockspace() should return -EEXIST if the lockspace exists. * diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 2056743aaaaa..681656a1c03d 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -131,12 +131,6 @@ int dm_bufio_issue_flush(struct dm_bufio_client *c); int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t count); /* - * Like dm_bufio_release but also move the buffer to the new - * block. dm_bufio_write_dirty_buffers is needed to commit the new block. - */ -void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block); - -/* * Free the given buffer. * This is just a hint, if the buffer is in use or dirty, this function * does nothing. diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 775cdc0b4f24..d54b595a0fe0 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -257,6 +257,26 @@ struct dma_fence_ops { */ void (*timeline_value_str)(struct dma_fence *fence, char *str, int size); + + /** + * @set_deadline: + * + * Callback to allow a fence waiter to inform the fence signaler of + * an upcoming deadline, such as vblank, by which point the waiter + * would prefer the fence to be signaled by. This is intended to + * give feedback to the fence signaler to aid in power management + * decisions, such as boosting GPU frequency. + * + * This is called without &dma_fence.lock held, it can be called + * multiple times and from any context. Locking is up to the callee + * if it has some state to manage. If multiple deadlines are set, + * the expectation is to track the soonest one. If the deadline is + * before the current time, it should be interpreted as an immediate + * deadline. + * + * This callback is optional. + */ + void (*set_deadline)(struct dma_fence *fence, ktime_t deadline); }; void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, @@ -583,6 +603,8 @@ static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr) return ret < 0 ? ret : 0; } +void dma_fence_set_deadline(struct dma_fence *fence, ktime_t deadline); + struct dma_fence *dma_fence_get_stub(void); struct dma_fence *dma_fence_allocate_private_stub(void); u64 dma_fence_context_alloc(unsigned num); diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 41bf4bdb117a..31f114f486c4 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -269,6 +269,8 @@ static inline bool dev_is_dma_coherent(struct device *dev) return dev->dma_coherent; } #else +#define dma_default_coherent true + static inline bool dev_is_dma_coherent(struct device *dev) { return true; diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 0637659a702c..8d0e34dad446 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -479,6 +479,8 @@ int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage, int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage, bool intr, unsigned long timeout); +void dma_resv_set_deadline(struct dma_resv *obj, enum dma_resv_usage usage, + ktime_t deadline); bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage); void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq); diff --git a/include/linux/dma/ti-cppi5.h b/include/linux/dma/ti-cppi5.h index efa2f0309f00..c53c0f6e3b1a 100644 --- a/include/linux/dma/ti-cppi5.h +++ b/include/linux/dma/ti-cppi5.h @@ -616,6 +616,7 @@ static inline void *cppi5_hdesc_get_swdata(struct cppi5_host_desc_t *desc) #define CPPI5_TR_CSF_SUPR_EVT BIT(2) #define CPPI5_TR_CSF_EOL_ADV_SHIFT (4U) #define CPPI5_TR_CSF_EOL_ADV_MASK GENMASK(6, 4) +#define CPPI5_TR_CSF_EOL_ICNT0 BIT(4) #define CPPI5_TR_CSF_EOP BIT(7) /** diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 41682278d2e8..061dd84d09f3 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -128,17 +128,16 @@ struct ddebug_class_param { const struct ddebug_class_map *map; }; -#if defined(CONFIG_DYNAMIC_DEBUG_CORE) - -int ddebug_add_module(struct _ddebug_info *dyndbg, const char *modname); +/* + * pr_debug() and friends are globally enabled or modules have selectively + * enabled them. + */ +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -extern int ddebug_remove_module(const char *mod_name); extern __printf(2, 3) void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...); -extern int ddebug_dyndbg_module_param_cb(char *param, char *val, - const char *modname); - struct device; extern __printf(3, 4) @@ -287,10 +286,6 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii) -struct kernel_param; -int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp); -int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); - /* for test only, generally expect drm.debug style macro wrappers */ #define __pr_debug_cls(cls, fmt, ...) do { \ BUILD_BUG_ON_MSG(!__builtin_constant_p(cls), \ @@ -298,21 +293,38 @@ int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); dynamic_pr_debug_cls(cls, fmt, ##__VA_ARGS__); \ } while (0) -#else /* !CONFIG_DYNAMIC_DEBUG_CORE */ +#else /* !(CONFIG_DYNAMIC_DEBUG || (CONFIG_DYNAMIC_DEBUG_CORE && DYNAMIC_DEBUG_MODULE)) */ #include <linux/string.h> #include <linux/errno.h> #include <linux/printk.h> -static inline int ddebug_add_module(struct _ddebug_info *dinfo, const char *modname) -{ - return 0; -} +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) +#define DYNAMIC_DEBUG_BRANCH(descriptor) false -static inline int ddebug_remove_module(const char *mod) -{ - return 0; -} +#define dynamic_pr_debug(fmt, ...) \ + do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) +#define dynamic_dev_dbg(dev, fmt, ...) \ + do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0) +#define dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ + groupsize, buf, len, ascii) \ + do { if (0) \ + print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii); \ + } while (0) + +#endif /* CONFIG_DYNAMIC_DEBUG || (CONFIG_DYNAMIC_DEBUG_CORE && DYNAMIC_DEBUG_MODULE) */ + + +#ifdef CONFIG_DYNAMIC_DEBUG_CORE + +extern int ddebug_dyndbg_module_param_cb(char *param, char *val, + const char *modname); +struct kernel_param; +int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp); +int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); + +#else static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, const char *modname) @@ -326,25 +338,15 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, return -EINVAL; } -#define dynamic_pr_debug(fmt, ...) \ - do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) -#define dynamic_dev_dbg(dev, fmt, ...) \ - do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0) -#define dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ - groupsize, buf, len, ascii) \ - do { if (0) \ - print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, \ - rowsize, groupsize, buf, len, ascii); \ - } while (0) - struct kernel_param; static inline int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp) { return 0; } static inline int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp) { return 0; } -#endif /* !CONFIG_DYNAMIC_DEBUG_CORE */ +#endif + extern const struct kernel_param_ops param_ops_dyndbg_classes; -#endif +#endif /* _DYNAMIC_DEBUG_H */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 04a733f0ba95..571d1a6e1b74 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -693,6 +693,7 @@ efi_guid_to_str(efi_guid_t *guid, char *out) } extern void efi_init (void); +extern void efi_earlycon_reprobe(void); #ifdef CONFIG_EFI extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ #else @@ -1337,4 +1338,6 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table) return xen_efi_config_table_is_usable(guid, table); } +umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n); + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 2792185dda22..62b61527bcc4 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -75,6 +75,8 @@ enum { * @tx_push: The flag of tx push mode * @rx_push: The flag of rx push mode * @cqe_size: Size of TX/RX completion queue event + * @tx_push_buf_len: Size of TX push buffer + * @tx_push_buf_max_len: Maximum allowed size of TX push buffer */ struct kernel_ethtool_ringparam { u32 rx_buf_len; @@ -82,6 +84,8 @@ struct kernel_ethtool_ringparam { u8 tx_push; u8 rx_push; u32 cqe_size; + u32 tx_push_buf_len; + u32 tx_push_buf_max_len; }; /** @@ -90,12 +94,14 @@ struct kernel_ethtool_ringparam { * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push + * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len */ enum ethtool_supported_ring_param { - ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), - ETHTOOL_RING_USE_CQE_SIZE = BIT(1), - ETHTOOL_RING_USE_TX_PUSH = BIT(2), - ETHTOOL_RING_USE_RX_PUSH = BIT(3), + ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), + ETHTOOL_RING_USE_CQE_SIZE = BIT(1), + ETHTOOL_RING_USE_TX_PUSH = BIT(2), + ETHTOOL_RING_USE_RX_PUSH = BIT(3), + ETHTOOL_RING_USE_TX_PUSH_BUF_LEN = BIT(4), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) @@ -705,6 +711,7 @@ struct ethtool_mm_stats { * @get_dump_data: Get dump data. * @set_dump: Set dump specific flags to the device. * @get_ts_info: Get the time stamping and PTP hardware clock capabilities. + * It may be called with RCU, or rtnl or reference on the device. * Drivers supporting transmit time stamps in software should set this to * ethtool_op_get_ts_info(). * @get_module_info: Get the size and type of the eeprom contained within diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 17003b385756..fae0dfb9a9c8 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -39,6 +39,7 @@ void ethtool_aggregate_pause_stats(struct net_device *dev, struct ethtool_pause_stats *pause_stats); void ethtool_aggregate_rmon_stats(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats); +bool ethtool_dev_mm_supported(struct net_device *dev); #else static inline int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd) @@ -112,5 +113,10 @@ ethtool_aggregate_rmon_stats(struct net_device *dev, { } +static inline bool ethtool_dev_mm_supported(struct net_device *dev) +{ + return false; +} + #endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */ #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 601700fedc91..9edb29101ec8 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -220,6 +220,7 @@ struct export_operations { #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ +#define EXPORT_OP_FLUSH_ON_CLOSE (0x20) /* fs flushes file data on close */ unsigned long flags; }; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 1701f25117ea..1d6402529d10 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -40,9 +40,8 @@ #define F2FS_ENC_UTF8_12_1 1 -#define F2FS_IO_SIZE(sbi) (1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ -#define F2FS_IO_SIZE_KB(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */ -#define F2FS_IO_SIZE_BYTES(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 12)) /* B */ +#define F2FS_IO_SIZE(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ +#define F2FS_IO_SIZE_KB(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits + 2) /* KB */ #define F2FS_IO_SIZE_BITS(sbi) (F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */ #define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1) #define F2FS_IO_ALIGNED(sbi) (F2FS_IO_SIZE(sbi) > 1) @@ -340,7 +339,7 @@ enum { OFFSET_BIT_SHIFT }; -#define OFFSET_BIT_MASK (0x07) /* (0x01 << OFFSET_BIT_SHIFT) - 1 */ +#define OFFSET_BIT_MASK GENMASK(OFFSET_BIT_SHIFT - 1, 0) struct node_footer { __le32 nid; /* node id */ @@ -545,7 +544,7 @@ typedef __le32 f2fs_hash_t; #define MAX_DIR_HASH_DEPTH 63 /* MAX buckets in one level of dir */ -#define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1)) +#define MAX_DIR_BUCKETS BIT((MAX_DIR_HASH_DEPTH / 2) - 1) /* * space utilization of regular dentry and inline dentry (w/o extra reservation) @@ -585,21 +584,6 @@ struct f2fs_dentry_block { __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN]; } __packed; -/* file types used in inode_info->flags */ -enum { - F2FS_FT_UNKNOWN, - F2FS_FT_REG_FILE, - F2FS_FT_DIR, - F2FS_FT_CHRDEV, - F2FS_FT_BLKDEV, - F2FS_FT_FIFO, - F2FS_FT_SOCK, - F2FS_FT_SYMLINK, - F2FS_FT_MAX -}; - -#define S_SHIFT 12 - #define F2FS_DEF_PROJID 0 /* default project ID */ #endif /* _LINUX_F2FS_FS_H */ diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 444236dadcf0..481abf530b3c 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/debugfs.h> +#include <linux/configfs.h> #include <linux/ratelimit.h> #include <linux/atomic.h> @@ -65,6 +66,27 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name, #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ +#ifdef CONFIG_FAULT_INJECTION_CONFIGFS + +struct fault_config { + struct fault_attr attr; + struct config_group group; +}; + +void fault_config_init(struct fault_config *config, const char *name); + +#else /* CONFIG_FAULT_INJECTION_CONFIGFS */ + +struct fault_config { +}; + +static inline void fault_config_init(struct fault_config *config, + const char *name) +{ +} + +#endif /* CONFIG_FAULT_INJECTION_CONFIGFS */ + #endif /* CONFIG_FAULT_INJECTION */ struct kmem_cache; diff --git a/include/linux/fb.h b/include/linux/fb.h index d8d20514ea05..08cb47da71f8 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -212,6 +212,7 @@ struct fb_deferred_io { /* delay between mkwrite and deferred handler */ unsigned long delay; bool sort_pagereflist; /* sort pagelist by offset */ + int open_count; /* number of opened files; protected by fb_info lock */ struct mutex lock; /* mutex that protects the pageref list */ struct list_head pagereflist; /* list of pagerefs for touched pages */ /* callback */ @@ -765,7 +766,6 @@ struct dmt_videomode { const struct fb_videomode *mode; }; -extern const char *fb_mode_option; extern const struct fb_videomode vesa_modes[]; extern const struct dmt_videomode dmt_modes[]; diff --git a/include/linux/filter.h b/include/linux/filter.h index 1727898f1641..bbce89937fde 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -571,8 +571,7 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); extern struct mutex nf_conn_btf_access_lock; extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag); + int off, int size); typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, @@ -921,6 +920,7 @@ void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_kfunc_call(void); +bool bpf_jit_supports_far_kfunc_call(void); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) @@ -1504,9 +1504,9 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, } #endif /* IS_ENABLED(CONFIG_IPV6) */ -static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, - u64 flags, const u64 flag_mask, - void *lookup_elem(struct bpf_map *map, u32 key)) +static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, + u64 flags, const u64 flag_mask, + void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; @@ -1542,4 +1542,50 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u64 index return XDP_REDIRECT; } +#ifdef CONFIG_NET +int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len); +int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, + u32 len, u64 flags); +int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); +int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); +void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len); +void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, + void *buf, unsigned long len, bool flush); +#else /* CONFIG_NET */ +static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, + void *to, u32 len) +{ + return -EOPNOTSUPP; +} + +static inline int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, + const void *from, u32 len, u64 flags) +{ + return -EOPNOTSUPP; +} + +static inline int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, + void *buf, u32 len) +{ + return -EOPNOTSUPP; +} + +static inline int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, + void *buf, u32 len) +{ + return -EOPNOTSUPP; +} + +static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) +{ + return NULL; +} + +static inline void *bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, + unsigned long len, bool flush) +{ + return NULL; +} +#endif /* CONFIG_NET */ + #endif /* __LINUX_FILTER_H__ */ diff --git a/include/linux/find.h b/include/linux/find.h index 4647864a5ffd..5e4f39ef2e72 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -14,6 +14,8 @@ unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long unsigned long nbits, unsigned long start); unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); +unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); @@ -127,6 +129,36 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1, } #endif +#ifndef find_next_or_bit +/** + * find_next_or_bit - find the next set bit in either memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_or_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = (*addr1 | *addr2) & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_or_bit(addr1, addr2, size, offset); +} +#endif + #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region @@ -536,6 +568,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) +#define for_each_or_bit(bit, addr1, addr2, size) \ + for ((bit) = 0; \ + (bit) = find_next_or_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) + /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 1716c01c4e54..efb6e2cf2034 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -391,7 +391,7 @@ struct fw_iso_packet { u32 tag:2; /* tx: Tag in packet header */ u32 sy:4; /* tx: Sy in packet header */ u32 header_length:8; /* Length of immediate header */ - u32 header[0]; /* tx: Top of 1394 isoch. data_block */ + u32 header[]; /* tx: Top of 1394 isoch. data_block */ }; #define FW_ISO_CONTEXT_TRANSMIT 0 diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index cad828e21c72..29cd11d5a3cf 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -156,6 +156,7 @@ struct cs_dsp { unsigned int sysclk_reg; unsigned int sysclk_mask; unsigned int sysclk_shift; + bool no_core_startstop; struct list_head alg_regions; diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index 1e449a5d7f5c..250ea4efb7cb 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -94,7 +94,7 @@ extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, u32 cp_nonpixel_start, u32 cp_nonpixel_size); extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, - unsigned int *src, + u64 *src, const struct qcom_scm_vmperm *newvm, unsigned int dest_cnt); diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 0e4c70987e6a..f5da51677069 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -71,6 +71,10 @@ #define XILINX_ZYNQMP_PM_FPGA_FULL 0x0U #define XILINX_ZYNQMP_PM_FPGA_PARTIAL BIT(0) +/* FPGA Status Reg */ +#define XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET 7U +#define XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG 0U + /* * Node IDs for the Error Events. */ @@ -124,6 +128,7 @@ enum pm_api_id { PM_CLOCK_GETRATE = 42, PM_CLOCK_SETPARENT = 43, PM_CLOCK_GETPARENT = 44, + PM_FPGA_READ = 46, PM_SECURE_AES = 47, PM_FEATURE_CHECK = 63, }; @@ -519,6 +524,7 @@ int zynqmp_pm_aes_engine(const u64 address, u32 *out); int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_get_status(u32 *value); +int zynqmp_pm_fpga_get_config_status(u32 *value); int zynqmp_pm_write_ggs(u32 index, u32 value); int zynqmp_pm_read_ggs(u32 index, u32 *value); int zynqmp_pm_write_pggs(u32 index, u32 value); @@ -725,6 +731,11 @@ static inline int zynqmp_pm_fpga_get_status(u32 *value) return -ENODEV; } +static inline int zynqmp_pm_fpga_get_config_status(u32 *value) +{ + return -ENODEV; +} + static inline int zynqmp_pm_write_ggs(u32 index, u32 value) { return -ENODEV; diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 1c2bde0ead73..47fefc7f363b 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -13,6 +13,8 @@ * @nmissed: The counter for missing events. * @flags: The status flag. * @rethook: The rethook data structure. (internal data) + * @entry_data_size: The private data storage size. + * @nr_maxactive: The max number of active functions. * @entry_handler: The callback function for function entry. * @exit_handler: The callback function for function exit. */ @@ -29,9 +31,13 @@ struct fprobe { unsigned long nmissed; unsigned int flags; struct rethook *rethook; + size_t entry_data_size; + int nr_maxactive; - void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); - void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); + int (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs, void *entry_data); + void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs, void *entry_data); }; /* This fprobe is soft-disabled. */ diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..133f0640fb24 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -168,6 +168,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_NOREUSE ((__force fmode_t)0x800000) +/* File supports non-exclusive O_DIRECT writes from multiple threads */ +#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -340,6 +343,20 @@ enum rw_hint { /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) +/* for use in trace events */ +#define TRACE_IOCB_STRINGS \ + { IOCB_HIPRI, "HIPRI" }, \ + { IOCB_DSYNC, "DSYNC" }, \ + { IOCB_SYNC, "SYNC" }, \ + { IOCB_NOWAIT, "NOWAIT" }, \ + { IOCB_APPEND, "APPEND" }, \ + { IOCB_EVENTFD, "EVENTFD"}, \ + { IOCB_DIRECT, "DIRECT" }, \ + { IOCB_WRITE, "WRITE" }, \ + { IOCB_WAITQ, "WAITQ" }, \ + { IOCB_NOIO, "NOIO" }, \ + { IOCB_ALLOC_CACHE, "ALLOC_CACHE" } + struct kiocb { struct file *ki_filp; loff_t ki_pos; @@ -1059,29 +1076,29 @@ extern int send_sigurg(struct fown_struct *fown); * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ -#define SB_RDONLY 1 /* Mount read-only */ -#define SB_NOSUID 2 /* Ignore suid and sgid bits */ -#define SB_NODEV 4 /* Disallow access to device special files */ -#define SB_NOEXEC 8 /* Disallow program execution */ -#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ -#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ -#define SB_NOATIME 1024 /* Do not update access times. */ -#define SB_NODIRATIME 2048 /* Do not update directory access times */ -#define SB_SILENT 32768 -#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define SB_I_VERSION (1<<23) /* Update inode I_version field */ -#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ +#define SB_RDONLY BIT(0) /* Mount read-only */ +#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ +#define SB_NODEV BIT(2) /* Disallow access to device special files */ +#define SB_NOEXEC BIT(3) /* Disallow program execution */ +#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ +#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ +#define SB_NOATIME BIT(10) /* Do not update access times. */ +#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ +#define SB_SILENT BIT(15) +#define SB_POSIXACL BIT(16) /* VFS does not apply the umask */ +#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ +#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ +#define SB_I_VERSION BIT(23) /* Update inode I_version field */ +#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ -#define SB_SUBMOUNT (1<<26) -#define SB_FORCE (1<<27) -#define SB_NOSEC (1<<28) -#define SB_BORN (1<<29) -#define SB_ACTIVE (1<<30) -#define SB_NOUSER (1<<31) +#define SB_SUBMOUNT BIT(26) +#define SB_FORCE BIT(27) +#define SB_NOSEC BIT(28) +#define SB_BORN BIT(29) +#define SB_ACTIVE BIT(30) +#define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) @@ -2675,6 +2692,8 @@ extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs(struct file *); +int setattr_should_drop_sgid(struct mnt_idmap *idmap, + const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set @@ -2778,7 +2797,7 @@ enum { ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, - dio_iodone_t end_io, dio_submit_t submit_io, + dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, @@ -2787,7 +2806,7 @@ static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); + get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 5469ffee21c7..ff6341e09925 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -104,7 +104,6 @@ struct fs_context { unsigned int sb_flags; /* Proposed superblock flags (SB_*) */ unsigned int sb_flags_mask; /* Superblock flags that were changed */ unsigned int s_iflags; /* OR'd with sb->s_iflags */ - unsigned int lsm_flags; /* Information flags from the fs to the LSM */ enum fs_context_purpose purpose:8; enum fs_context_phase phase:8; /* The phase the context is in */ bool need_free:1; /* Need to call ops->free() */ diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index e0a49c3125eb..c895b12737a1 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -273,6 +273,16 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return (struct page *)page_private(bounce_page); } +static inline bool fscrypt_is_bounce_folio(struct folio *folio) +{ + return folio->mapping == NULL; +} + +static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio) +{ + return bounce_folio->private; +} + void fscrypt_free_bounce_page(struct page *bounce_page); /* policy.c */ @@ -359,6 +369,7 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, unsigned int flags); int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, struct fscrypt_name *fname); +int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry); int __fscrypt_prepare_readdir(struct inode *dir); int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr); int fscrypt_prepare_setflags(struct inode *inode, @@ -445,6 +456,17 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return ERR_PTR(-EINVAL); } +static inline bool fscrypt_is_bounce_folio(struct folio *folio) +{ + return false; +} + +static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio) +{ + WARN_ON_ONCE(1); + return ERR_PTR(-EINVAL); +} + static inline void fscrypt_free_bounce_page(struct page *bounce_page) { } @@ -673,6 +695,12 @@ static inline int __fscrypt_prepare_lookup(struct inode *dir, return -EOPNOTSUPP; } +static inline int fscrypt_prepare_lookup_partial(struct inode *dir, + struct dentry *dentry) +{ + return -EOPNOTSUPP; +} + static inline int __fscrypt_prepare_readdir(struct inode *dir) { return -EOPNOTSUPP; diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 119a3266791f..e76605d5b36e 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -233,18 +233,18 @@ static inline int fsverity_ioctl_read_metadata(struct file *filp, static inline bool fsverity_verify_blocks(struct folio *folio, size_t len, size_t offset) { - WARN_ON(1); + WARN_ON_ONCE(1); return false; } static inline void fsverity_verify_bio(struct bio *bio) { - WARN_ON(1); + WARN_ON_ONCE(1); } static inline void fsverity_enqueue_verify_work(struct work_struct *work) { - WARN_ON(1); + WARN_ON_ONCE(1); } #endif /* !CONFIG_FS_VERITY */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 366c730beaa3..b23bdd414394 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -241,6 +241,12 @@ enum { FTRACE_OPS_FL_DIRECT = BIT(17), }; +#ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +#define FTRACE_OPS_FL_SAVE_ARGS FTRACE_OPS_FL_SAVE_REGS +#else +#define FTRACE_OPS_FL_SAVE_ARGS 0 +#endif + /* * FTRACE_OPS_CMD_* commands allow the ftrace core logic to request changes * to a ftrace_ops. Note, the requests may fail. @@ -321,6 +327,9 @@ struct ftrace_ops { unsigned long trampoline_size; struct list_head list; ftrace_ops_func_t ops_func; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + unsigned long direct_call; +#endif #endif }; @@ -397,64 +406,36 @@ struct ftrace_func_entry { #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS extern int ftrace_direct_func_count; -int register_ftrace_direct(unsigned long ip, unsigned long addr); -int unregister_ftrace_direct(unsigned long ip, unsigned long addr); -int modify_ftrace_direct(unsigned long ip, unsigned long old_addr, unsigned long new_addr); -struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr); -int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, - struct dyn_ftrace *rec, - unsigned long old_addr, - unsigned long new_addr); unsigned long ftrace_find_rec_direct(unsigned long ip); -int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); -int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); -int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); -int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr); +int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr); +int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, + bool free_filters); +int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr); +int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr); + +void ftrace_stub_direct_tramp(void); #else struct ftrace_ops; # define ftrace_direct_func_count 0 -static inline int register_ftrace_direct(unsigned long ip, unsigned long addr) -{ - return -ENOTSUPP; -} -static inline int unregister_ftrace_direct(unsigned long ip, unsigned long addr) -{ - return -ENOTSUPP; -} -static inline int modify_ftrace_direct(unsigned long ip, - unsigned long old_addr, unsigned long new_addr) -{ - return -ENOTSUPP; -} -static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr) -{ - return NULL; -} -static inline int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, - struct dyn_ftrace *rec, - unsigned long old_addr, - unsigned long new_addr) -{ - return -ENODEV; -} static inline unsigned long ftrace_find_rec_direct(unsigned long ip) { return 0; } -static inline int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +static inline int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) { return -ENODEV; } -static inline int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +static inline int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, + bool free_filters) { return -ENODEV; } -static inline int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +static inline int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) { return -ENODEV; } -static inline int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr) +static inline int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr) { return -ENODEV; } @@ -567,6 +548,8 @@ bool is_ftrace_trampoline(unsigned long addr); * DIRECT - there is a direct function to call * CALL_OPS - the record can use callsite-specific ops * CALL_OPS_EN - the function is set up to use callsite-specific ops + * TOUCHED - A callback was added since boot up + * MODIFIED - The function had IPMODIFY or DIRECT attached to it * * When a new ftrace_ops is registered and wants a function to save * pt_regs, the rec->flags REGS is set. When the function has been @@ -586,9 +569,11 @@ enum { FTRACE_FL_DIRECT_EN = (1UL << 23), FTRACE_FL_CALL_OPS = (1UL << 22), FTRACE_FL_CALL_OPS_EN = (1UL << 21), + FTRACE_FL_TOUCHED = (1UL << 20), + FTRACE_FL_MODIFIED = (1UL << 19), }; -#define FTRACE_REF_MAX_SHIFT 21 +#define FTRACE_REF_MAX_SHIFT 19 #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) #define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX) @@ -647,6 +632,7 @@ enum { FTRACE_ITER_PROBE = (1 << 4), FTRACE_ITER_MOD = (1 << 5), FTRACE_ITER_ENABLED = (1 << 6), + FTRACE_ITER_TOUCHED = (1 << 7), }; void arch_ftrace_update_code(int command); @@ -980,7 +966,7 @@ static inline void __ftrace_enabled_restore(int enabled) #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) -static inline unsigned long get_lock_parent_ip(void) +static __always_inline unsigned long get_lock_parent_ip(void) { unsigned long addr = CALLER_ADDR0; diff --git a/include/linux/gameport.h b/include/linux/gameport.h index 0a221e768ea4..07e370113b2b 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -63,7 +63,7 @@ struct gameport_driver { int gameport_open(struct gameport *gameport, struct gameport_driver *drv, int mode); void gameport_close(struct gameport *gameport); -#if defined(CONFIG_GAMEPORT) || (defined(MODULE) && defined(CONFIG_GAMEPORT_MODULE)) +#if IS_REACHABLE(CONFIG_GAMEPORT) void __gameport_register_port(struct gameport *gameport, struct module *owner); /* use a define to avoid include chaining to get THIS_MODULE */ diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 4a4b387181ad..2984b0cb24b1 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -209,7 +209,7 @@ static int s_name ## _from_attrs_for_change(struct s_name *s, \ * Magic: define op number to op name mapping {{{1 * {{{2 */ -const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd) +static const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd) { switch (cmd) { #undef GENL_op diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 65a78773dcca..ed8cb537c6a7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -319,7 +319,7 @@ extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) -void page_alloc_init(void); +void page_alloc_init_cpuhp(void); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); @@ -361,9 +361,4 @@ extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); -#ifdef CONFIG_CMA -/* CMA stuff */ -extern void init_cma_reserved_pageblock(struct page *page); -#endif - #endif /* __LINUX_GFP_H */ diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 5088637fe5c2..6583a58670c5 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -47,16 +47,14 @@ typedef unsigned int __bitwise gfp_t; #define ___GFP_ACCOUNT 0x400000u #define ___GFP_ZEROTAGS 0x800000u #ifdef CONFIG_KASAN_HW_TAGS -#define ___GFP_SKIP_ZERO 0x1000000u -#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u -#define ___GFP_SKIP_KASAN_POISON 0x4000000u +#define ___GFP_SKIP_ZERO 0x1000000u +#define ___GFP_SKIP_KASAN 0x2000000u #else -#define ___GFP_SKIP_ZERO 0 -#define ___GFP_SKIP_KASAN_UNPOISON 0 -#define ___GFP_SKIP_KASAN_POISON 0 +#define ___GFP_SKIP_ZERO 0 +#define ___GFP_SKIP_KASAN 0 #endif #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x8000000u +#define ___GFP_NOLOCKDEP 0x4000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -234,25 +232,24 @@ typedef unsigned int __bitwise gfp_t; * memory tags at the same time as zeroing memory has minimal additional * performace impact. * - * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation. - * Only effective in HW_TAGS mode. - * - * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation. - * Typically, used for userspace pages. Only effective in HW_TAGS mode. + * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation. + * Used for userspace and vmalloc pages; the latter are unpoisoned by + * kasan_unpoison_vmalloc instead. For userspace pages, results in + * poisoning being skipped as well, see should_skip_kasan_poison for + * details. Only effective in HW_TAGS mode. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) #define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO) -#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON) -#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) +#define __GFP_SKIP_KASAN ((__force gfp_t)___GFP_SKIP_KASAN) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (26 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** @@ -335,8 +332,7 @@ typedef unsigned int __bitwise gfp_t; #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) -#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \ - __GFP_SKIP_KASAN_POISON | __GFP_SKIP_KASAN_UNPOISON) +#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | __GFP_SKIP_KASAN) #define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) #define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 85beb236c925..8528353e073b 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -12,7 +12,9 @@ #ifndef __LINUX_GPIO_H #define __LINUX_GPIO_H -#include <linux/errno.h> +#include <linux/types.h> + +struct device; /* see Documentation/driver-api/gpio/legacy.rst */ @@ -55,50 +57,94 @@ struct gpio { #ifdef CONFIG_GPIOLIB -#ifdef CONFIG_ARCH_HAVE_CUSTOM_GPIO_H -#include <asm/gpio.h> -#else +#include <linux/gpio/consumer.h> + +/* + * "valid" GPIO numbers are nonnegative and may be passed to + * setup routines like gpio_request(). Only some valid numbers + * can successfully be requested and used. + * + * Invalid GPIO numbers are useful for indicating no-such-GPIO in + * platform data and other tables. + */ +static inline bool gpio_is_valid(int number) +{ + /* only non-negative numbers are valid */ + return number >= 0; +} + +/* + * Platforms may implement their GPIO interface with library code, + * at a small performance cost for non-inlined operations and some + * extra memory (for code and for per-GPIO table entries). + */ + +/* + * At the end we want all GPIOs to be dynamically allocated from 0. + * However, some legacy drivers still perform fixed allocation. + * Until they are all fixed, leave 0-512 space for them. + */ +#define GPIO_DYNAMIC_BASE 512 -#include <asm-generic/gpio.h> +/* Always use the library code for GPIO management calls, + * or when sleeping may be involved. + */ +int gpio_request(unsigned gpio, const char *label); +void gpio_free(unsigned gpio); -static inline int gpio_get_value(unsigned int gpio) +static inline int gpio_direction_input(unsigned gpio) +{ + return gpiod_direction_input(gpio_to_desc(gpio)); +} +static inline int gpio_direction_output(unsigned gpio, int value) +{ + return gpiod_direction_output_raw(gpio_to_desc(gpio), value); +} + +static inline int gpio_get_value_cansleep(unsigned gpio) +{ + return gpiod_get_raw_value_cansleep(gpio_to_desc(gpio)); +} +static inline void gpio_set_value_cansleep(unsigned gpio, int value) { - return __gpio_get_value(gpio); + return gpiod_set_raw_value_cansleep(gpio_to_desc(gpio), value); } -static inline void gpio_set_value(unsigned int gpio, int value) +static inline int gpio_get_value(unsigned gpio) { - __gpio_set_value(gpio, value); + return gpiod_get_raw_value(gpio_to_desc(gpio)); +} +static inline void gpio_set_value(unsigned gpio, int value) +{ + return gpiod_set_raw_value(gpio_to_desc(gpio), value); } -static inline int gpio_cansleep(unsigned int gpio) +static inline int gpio_cansleep(unsigned gpio) { - return __gpio_cansleep(gpio); + return gpiod_cansleep(gpio_to_desc(gpio)); } -static inline int gpio_to_irq(unsigned int gpio) +static inline int gpio_to_irq(unsigned gpio) { - return __gpio_to_irq(gpio); + return gpiod_to_irq(gpio_to_desc(gpio)); } -#endif /* ! CONFIG_ARCH_HAVE_CUSTOM_GPIO_H */ +int gpio_request_one(unsigned gpio, unsigned long flags, const char *label); +int gpio_request_array(const struct gpio *array, size_t num); +void gpio_free_array(const struct gpio *array, size_t num); /* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */ -struct device; - int devm_gpio_request(struct device *dev, unsigned gpio, const char *label); int devm_gpio_request_one(struct device *dev, unsigned gpio, unsigned long flags, const char *label); #else /* ! CONFIG_GPIOLIB */ -#include <linux/bug.h> #include <linux/kernel.h> -#include <linux/types.h> -struct device; -struct gpio_chip; +#include <asm/bug.h> +#include <asm/errno.h> static inline bool gpio_is_valid(int number) { @@ -147,11 +193,6 @@ static inline int gpio_direction_output(unsigned gpio, int value) return -ENOSYS; } -static inline int gpio_set_debounce(unsigned gpio, unsigned debounce) -{ - return -ENOSYS; -} - static inline int gpio_get_value(unsigned gpio) { /* GPIO can never have been requested or set as {in,out}put */ @@ -185,19 +226,6 @@ static inline void gpio_set_value_cansleep(unsigned gpio, int value) WARN_ON(1); } -static inline int gpio_export(unsigned gpio, bool direction_may_change) -{ - /* GPIO can never have been requested or set as {in,out}put */ - WARN_ON(1); - return -EINVAL; -} - -static inline void gpio_unexport(unsigned gpio) -{ - /* GPIO can never have been exported */ - WARN_ON(1); -} - static inline int gpio_to_irq(unsigned gpio) { /* GPIO can never have been requested or set as input */ diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 59cb20cfac3d..1c4385a00f88 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -3,13 +3,14 @@ #define __LINUX_GPIO_CONSUMER_H #include <linux/bits.h> -#include <linux/bug.h> -#include <linux/compiler_types.h> -#include <linux/err.h> +#include <linux/types.h> +struct acpi_device; struct device; -struct gpio_desc; +struct fwnode_handle; + struct gpio_array; +struct gpio_desc; /** * struct gpio_descs - Struct containing an array of descriptors that can be @@ -171,9 +172,6 @@ int gpiod_set_consumer_name(struct gpio_desc *desc, const char *name); struct gpio_desc *gpio_to_desc(unsigned gpio); int desc_to_gpio(const struct gpio_desc *desc); -/* Child properties interface */ -struct fwnode_handle; - struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, const char *con_id, int index, enum gpiod_flags flags, @@ -186,8 +184,11 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, #else /* CONFIG_GPIOLIB */ +#include <linux/err.h> #include <linux/kernel.h> +#include <asm/bug.h> + static inline int gpiod_count(struct device *dev, const char *con_id) { return 0; @@ -546,9 +547,6 @@ static inline int desc_to_gpio(const struct gpio_desc *desc) return -EINVAL; } -/* Child properties interface */ -struct fwnode_handle; - static inline struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, const char *con_id, int index, @@ -607,8 +605,6 @@ struct acpi_gpio_mapping { unsigned int quirks; }; -struct acpi_device; - #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_ACPI) int acpi_dev_add_driver_gpios(struct acpi_device *adev, @@ -622,6 +618,8 @@ struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ +#include <linux/err.h> + static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, const struct acpi_gpio_mapping *gpios) { @@ -653,6 +651,8 @@ void gpiod_unexport(struct gpio_desc *desc); #else /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */ +#include <asm/errno.h> + static inline int gpiod_export(struct gpio_desc *desc, bool direction_may_change) { diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index ccd8a512d854..67b8774eed8f 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -2,28 +2,35 @@ #ifndef __LINUX_GPIO_DRIVER_H #define __LINUX_GPIO_DRIVER_H -#include <linux/device.h> -#include <linux/irq.h> +#include <linux/bits.h> #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> +#include <linux/irqhandler.h> #include <linux/lockdep.h> #include <linux/pinctrl/pinconf-generic.h> #include <linux/pinctrl/pinctrl.h> #include <linux/property.h> +#include <linux/spinlock_types.h> #include <linux/types.h> +#ifdef CONFIG_GENERIC_MSI_IRQ #include <asm/msi.h> +#endif -struct gpio_desc; +struct device; +struct irq_chip; +struct irq_data; +struct module; struct of_phandle_args; -struct device_node; +struct pinctrl_dev; struct seq_file; -struct gpio_device; -struct module; -enum gpiod_flags; -enum gpio_lookup_flags; struct gpio_chip; +struct gpio_desc; +struct gpio_device; + +enum gpio_lookup_flags; +enum gpiod_flags; union gpio_irq_fwspec { struct irq_fwspec fwspec; @@ -245,6 +252,14 @@ struct gpio_irq_chip { bool initialized; /** + * @domain_is_allocated_externally: + * + * True it the irq_domain was allocated outside of gpiolib, in which + * case gpiolib won't free the irq_domain itself. + */ + bool domain_is_allocated_externally; + + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when * a particular driver wants to clear IRQ related registers @@ -680,6 +695,10 @@ bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gc, int gpiochip_irqchip_add_domain(struct gpio_chip *gc, struct irq_domain *domain); #else + +#include <asm/bug.h> +#include <asm/errno.h> + static inline int gpiochip_irqchip_add_domain(struct gpio_chip *gc, struct irq_domain *domain) { @@ -757,6 +776,10 @@ struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc); #else /* CONFIG_GPIOLIB */ +#include <linux/err.h> + +#include <asm/bug.h> + static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc) { /* GPIO can never have been requested */ diff --git a/include/linux/gpio/legacy-of-mm-gpiochip.h b/include/linux/gpio/legacy-of-mm-gpiochip.h new file mode 100644 index 000000000000..2e2bd3b19cc3 --- /dev/null +++ b/include/linux/gpio/legacy-of-mm-gpiochip.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * OF helpers for the old of_mm_gpio_chip, used on ppc32 and nios2, + * do not use in new code. + * + * Copyright (c) 2007-2008 MontaVista Software, Inc. + * + * Author: Anton Vorontsov <avorontsov@ru.mvista.com> + */ + +#ifndef __LINUX_GPIO_LEGACY_OF_MM_GPIO_CHIP_H +#define __LINUX_GPIO_LEGACY_OF_MM_GPIO_CHIP_H + +#include <linux/gpio/driver.h> +#include <linux/of.h> + +/* + * OF GPIO chip for memory mapped banks + */ +struct of_mm_gpio_chip { + struct gpio_chip gc; + void (*save_regs)(struct of_mm_gpio_chip *mm_gc); + void __iomem *regs; +}; + +static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc) +{ + return container_of(gc, struct of_mm_gpio_chip, gc); +} + +extern int of_mm_gpiochip_add_data(struct device_node *np, + struct of_mm_gpio_chip *mm_gc, + void *data); +extern void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc); + +#endif /* __LINUX_GPIO_LEGACY_OF_MM_GPIO_CHIP_H */ diff --git a/include/linux/hex.h b/include/linux/hex.h new file mode 100644 index 000000000000..2618382e5b0c --- /dev/null +++ b/include/linux/hex.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_HEX_H +#define _LINUX_HEX_H + +#include <linux/types.h> + +extern const char hex_asc[]; +#define hex_asc_lo(x) hex_asc[((x) & 0x0f)] +#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] + +static inline char *hex_byte_pack(char *buf, u8 byte) +{ + *buf++ = hex_asc_hi(byte); + *buf++ = hex_asc_lo(byte); + return buf; +} + +extern const char hex_asc_upper[]; +#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] +#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] + +static inline char *hex_byte_pack_upper(char *buf, u8 byte) +{ + *buf++ = hex_asc_upper_hi(byte); + *buf++ = hex_asc_upper_lo(byte); + return buf; +} + +extern int hex_to_bin(unsigned char ch); +extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); +extern char *bin2hex(char *dst, const void *src, size_t count); + +bool mac_pton(const char *s, u8 *mac); + +#endif diff --git a/include/linux/hid.h b/include/linux/hid.h index 1ea8c7a3570b..4e4c4fe36911 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -156,6 +156,7 @@ struct hid_item { #define HID_UP_DIGITIZER 0x000d0000 #define HID_UP_PID 0x000f0000 #define HID_UP_BATTERY 0x00850000 +#define HID_UP_CAMERA 0x00900000 #define HID_UP_HPVENDOR 0xff7f0000 #define HID_UP_HPVENDOR2 0xff010000 #define HID_UP_MSVENDOR 0xff000000 @@ -873,7 +874,7 @@ extern bool hid_is_usb(const struct hid_device *hdev); /* We ignore a few input applications that are not widely used */ #define IS_INPUT_APPLICATION(a) \ (((a >= HID_UP_GENDESK) && (a <= HID_GD_MULTIAXIS)) \ - || ((a >= HID_DG_PEN) && (a <= HID_DG_WHITEBOARD)) \ + || ((a >= HID_DG_DIGITIZER) && (a <= HID_DG_WHITEBOARD)) \ || (a == HID_GD_SYSTEM_CONTROL) || (a == HID_CP_CONSUMER_CONTROL) \ || (a == HID_GD_WIRELESS_RADIO_CTLS)) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 8fc10089e19e..4de1dbcd3ef6 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -243,12 +243,10 @@ static inline void clear_highpage(struct page *page) static inline void clear_highpage_kasan_tagged(struct page *page) { - u8 tag; + void *kaddr = kmap_local_page(page); - tag = page_kasan_tag(page); - page_kasan_tag_reset(page); - clear_highpage(page); - page_kasan_tag_set(page, tag); + clear_page(kasan_reset_tag(kaddr)); + kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE @@ -317,7 +315,29 @@ static inline void copy_user_highpage(struct page *to, struct page *from, #endif +#ifndef __HAVE_ARCH_COPY_HIGHPAGE + +static inline void copy_highpage(struct page *to, struct page *from) +{ + char *vfrom, *vto; + + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); + copy_page(vto, vfrom); + kmsan_copy_page_meta(to, from); + kunmap_local(vto); + kunmap_local(vfrom); +} + +#endif + #ifdef copy_mc_to_kernel +/* + * If architecture supports machine check exception handling, define the + * #MC versions of copy_user_highpage and copy_highpage. They copy a memory + * page with #MC in source page (@from) handled, and return the number + * of bytes not copied if there was a #MC, otherwise 0 for success. + */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { @@ -334,29 +354,35 @@ static inline int copy_mc_user_highpage(struct page *to, struct page *from, return ret; } -#else -static inline int copy_mc_user_highpage(struct page *to, struct page *from, - unsigned long vaddr, struct vm_area_struct *vma) -{ - copy_user_highpage(to, from, vaddr, vma); - return 0; -} -#endif - -#ifndef __HAVE_ARCH_COPY_HIGHPAGE -static inline void copy_highpage(struct page *to, struct page *from) +static inline int copy_mc_highpage(struct page *to, struct page *from) { + unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); - copy_page(vto, vfrom); - kmsan_copy_page_meta(to, from); + ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); + if (!ret) + kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); + + return ret; +} +#else +static inline int copy_mc_user_highpage(struct page *to, struct page *from, + unsigned long vaddr, struct vm_area_struct *vma) +{ + copy_user_highpage(to, from, vaddr, vma); + return 0; } +static inline int copy_mc_highpage(struct page *to, struct page *from) +{ + copy_highpage(to, from); + return 0; +} #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 9a9de4b97a25..9c8119ed13a4 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -443,7 +443,7 @@ int __host1x_client_register(struct host1x_client *client); __host1x_client_register(client); \ }) -int host1x_client_unregister(struct host1x_client *client); +void host1x_client_unregister(struct host1x_client *client); int host1x_client_suspend(struct host1x_client *client); int host1x_client_resume(struct host1x_client *client); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 70bd867eba94..20284387b841 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -39,47 +39,12 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); -vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write); -/** - * vmf_insert_pfn_pmd - insert a pmd size pfn - * @vmf: Structure describing the fault - * @pfn: pfn to insert - * @pgprot: page protection to use - * @write: whether it's a write fault - * - * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. - * - * Return: vm_fault_t value. - */ -static inline vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, - bool write) -{ - return vmf_insert_pfn_pmd_prot(vmf, pfn, vmf->vma->vm_page_prot, write); -} -vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write); - -/** - * vmf_insert_pfn_pud - insert a pud size pfn - * @vmf: Structure describing the fault - * @pfn: pfn to insert - * @pgprot: page protection to use - * @write: whether it's a write fault - * - * Insert a pud size pfn. See vmf_insert_pfn() for additional info. - * - * Return: vm_fault_t value. - */ -static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, - bool write) -{ - return vmf_insert_pfn_pud_prot(vmf, pfn, vmf->vma->vm_page_prot, write); -} +vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write); +vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write); enum transparent_hugepage_flag { - TRANSPARENT_HUGEPAGE_NEVER_DAX, + TRANSPARENT_HUGEPAGE_UNSUPPORTED, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7c977d234aba..6d041aa9f0fe 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -124,14 +124,6 @@ void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, - loff_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, @@ -158,13 +150,12 @@ unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD -int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy); +int hugetlb_mfill_atomic_pte(pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + uffd_flags_t flags, + struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -192,6 +183,23 @@ extern struct list_head huge_boot_pages; /* arch callbacks */ +#ifndef CONFIG_HIGHPTE +/* + * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures + * which may go down to the lowest PTE level in their huge_pte_offset() and + * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). + */ +static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) +{ + return pte_offset_kernel(pmd, address); +} +static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); +} +#endif + pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* @@ -393,14 +401,12 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, } #ifdef CONFIG_USERFAULTFD -static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, - pte_t *dst_pte, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy) +static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + uffd_flags_t flags, + struct folio **foliop) { BUG(); return 0; @@ -818,7 +824,7 @@ static inline unsigned huge_page_shift(struct hstate *h) static inline bool hstate_is_gigantic(struct hstate *h) { - return huge_page_order(h) >= MAX_ORDER; + return huge_page_order(h) > MAX_ORDER; } static inline unsigned int pages_per_huge_page(const struct hstate *h) diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index f319bd26b030..7fbb45911273 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -7,6 +7,16 @@ #ifdef CONFIG_HAVE_HW_BREAKPOINT +enum bp_type_idx { + TYPE_INST = 0, +#if defined(CONFIG_HAVE_MIXED_BREAKPOINTS_REGS) + TYPE_DATA = 0, +#else + TYPE_DATA = 1, +#endif + TYPE_MAX +}; + extern int __init init_hw_breakpoint(void); static inline void hw_breakpoint_init(struct perf_event_attr *attr) diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index c1b62384b6ee..492dd27a5dd8 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -430,7 +430,7 @@ struct hwmon_channel_info { */ struct hwmon_chip_info { const struct hwmon_ops *ops; - const struct hwmon_channel_info **info; + const struct hwmon_channel_info * const *info; }; /* hwmon_device_register() is deprecated */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 5ba89663ea86..13a1ce38cb0c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -385,7 +385,6 @@ static inline void i2c_set_clientdata(struct i2c_client *client, void *data) /* I2C slave support */ -#if IS_ENABLED(CONFIG_I2C_SLAVE) enum i2c_slave_event { I2C_SLAVE_READ_REQUESTED, I2C_SLAVE_WRITE_REQUESTED, @@ -396,9 +395,10 @@ enum i2c_slave_event { int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb); int i2c_slave_unregister(struct i2c_client *client); -bool i2c_detect_slave_mode(struct device *dev); int i2c_slave_event(struct i2c_client *client, enum i2c_slave_event event, u8 *val); +#if IS_ENABLED(CONFIG_I2C_SLAVE) +bool i2c_detect_slave_mode(struct device *dev); #else static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } #endif diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 604a126b78c8..0b52da4f2346 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -22,9 +22,10 @@ #define I3C_BROADCAST_ADDR 0x7e #define I3C_MAX_ADDR GENMASK(6, 0) +struct i2c_client; + struct i3c_master_controller; struct i3c_bus; -struct i2c_device; struct i3c_device; /** @@ -541,7 +542,7 @@ int i3c_master_register(struct i3c_master_controller *master, struct device *parent, const struct i3c_master_controller_ops *ops, bool secondary); -int i3c_master_unregister(struct i3c_master_controller *master); +void i3c_master_unregister(struct i3c_master_controller *master); /** * i3c_dev_get_master_data() - get master private data attached to an I3C diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2463bdd2a382..c4cf296e7eaf 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net> * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2022 Intel Corporation + * Copyright (c) 2018 - 2023 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -783,20 +783,6 @@ static inline bool ieee80211_is_any_nullfunc(__le16 fc) } /** - * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU - * @fc: frame control field in little-endian byteorder - */ -static inline bool ieee80211_is_bufferable_mmpdu(__le16 fc) -{ - /* IEEE 802.11-2012, definition of "bufferable management frame"; - * note that this ignores the IBSS special case. */ - return ieee80211_is_mgmt(fc) && - (ieee80211_is_action(fc) || - ieee80211_is_disassoc(fc) || - ieee80211_is_deauth(fc)); -} - -/** * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set * @seq_ctrl: frame sequence control bytes in little-endian byteorder */ @@ -3557,11 +3543,6 @@ enum ieee80211_unprotected_wnm_actioncode { WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE = 1, }; -/* Public action codes */ -enum ieee80211_public_actioncode { - WLAN_PUBLIC_ACTION_FTM_RESPONSE = 33, -}; - /* Security key length */ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, @@ -3653,7 +3634,7 @@ enum ieee80211_pub_actioncode { WLAN_PUB_ACTION_NETWORK_CHANNEL_CONTROL = 30, WLAN_PUB_ACTION_WHITE_SPACE_MAP_ANN = 31, WLAN_PUB_ACTION_FTM_REQUEST = 32, - WLAN_PUB_ACTION_FTM = 33, + WLAN_PUB_ACTION_FTM_RESPONSE = 33, WLAN_PUB_ACTION_FILS_DISCOVERY = 34, }; @@ -4138,6 +4119,44 @@ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr) } /** + * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU + * @skb: the skb to check, starting with the 802.11 header + */ +static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (void *)skb->data; + __le16 fc = mgmt->frame_control; + + /* + * IEEE 802.11 REVme D2.0 definition of bufferable MMPDU; + * note that this ignores the IBSS special case. + */ + if (!ieee80211_is_mgmt(fc)) + return false; + + if (ieee80211_is_disassoc(fc) || ieee80211_is_deauth(fc)) + return true; + + if (!ieee80211_is_action(fc)) + return false; + + if (skb->len < offsetofend(typeof(*mgmt), u.action.u.ftm.action_code)) + return true; + + /* action frame - additionally check for non-bufferable FTM */ + + if (mgmt->u.action.category != WLAN_CATEGORY_PUBLIC && + mgmt->u.action.category != WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION) + return true; + + if (mgmt->u.action.u.ftm.action_code == WLAN_PUB_ACTION_FTM_REQUEST || + mgmt->u.action.u.ftm.action_code == WLAN_PUB_ACTION_FTM_RESPONSE) + return false; + + return true; +} + +/** * _ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame * @hdr: the frame (buffer must include at least the first octet of payload) */ @@ -4383,7 +4402,7 @@ static inline bool ieee80211_is_ftm(struct sk_buff *skb) return false; if (mgmt->u.action.u.ftm.action_code == - WLAN_PUBLIC_ACTION_FTM_RESPONSE && + WLAN_PUB_ACTION_FTM_RESPONSE && skb->len >= offsetofend(typeof(*mgmt), u.action.u.ftm)) return true; diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 1668ac4d7adc..3ff96ae31bf6 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -60,6 +60,7 @@ struct br_ip_list { #define BR_TX_FWD_OFFLOAD BIT(20) #define BR_PORT_LOCKED BIT(21) #define BR_PORT_MAB BIT(22) +#define BR_NEIGH_VLAN_SUPPRESS BIT(23) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/linux/if_team.h b/include/linux/if_team.h index fc985e5c739d..8de6b6e67829 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -208,6 +208,7 @@ struct team { bool queue_override_enabled; struct list_head *qom_lists; /* array of queue override mapping lists */ bool port_mtu_change_allowed; + bool notifier_ctx; struct { unsigned int count; unsigned int interval; /* in ms */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 6864b89ef868..6ba71957851e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -62,6 +62,14 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) return (struct vlan_ethhdr *)skb_mac_header(skb); } +/* Prefer this version in TX path, instead of + * skb_reset_mac_header() + vlan_eth_hdr() + */ +static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb) +{ + return (struct vlan_ethhdr *)skb->data; +} + #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 #define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */ @@ -351,7 +359,8 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, /* Move the mac header sans proto to the beginning of the new header. */ if (likely(mac_len > ETH_TLEN)) memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); - skb->mac_header -= VLAN_HLEN; + if (skb_mac_header_was_set(skb)) + skb->mac_header -= VLAN_HLEN; veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN); @@ -528,7 +537,7 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, */ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { - struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb->data; + struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) return -EINVAL; @@ -628,6 +637,23 @@ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) return __vlan_get_protocol(skb, skb->protocol, NULL); } +/* This version of __vlan_get_protocol() also pulls mac header in skb->head */ +static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb, + __be16 type, int *depth) +{ + int maclen; + + type = __vlan_get_protocol(skb, type, &maclen); + + if (type) { + if (!pskb_may_pull(skb, maclen)) + type = 0; + else if (depth) + *depth = maclen; + } + return type; +} + /* A getter for the SKB protocol field which will handle VLAN tags consistently * whether VLAN acceleration is enabled or not. */ @@ -677,6 +703,27 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, } /** + * vlan_remove_tag - remove outer VLAN tag from payload + * @skb: skbuff to remove tag from + * @vlan_tci: buffer to store value + * + * Expects the skb to contain a VLAN tag in the payload, and to have skb->data + * pointing at the MAC header. + * + * Returns a new pointer to skb->data, or NULL on failure to pull. + */ +static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) +{ + struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); + + *vlan_tci = ntohs(vhdr->h_vlan_TCI); + + memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); + vlan_set_encap_proto(skb, vhdr); + return __skb_pull(skb, VLAN_HLEN); +} + +/** * skb_vlan_tagged - check if skb is vlan tagged. * @skb: skbuff to query * @@ -712,7 +759,7 @@ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) return false; - veh = (struct vlan_ethhdr *)skb->data; + veh = skb_vlan_eth_hdr(skb); protocol = veh->h_vlan_encapsulated_proto; } diff --git a/include/linux/igmp.h b/include/linux/igmp.h index b19d3284551f..ebf4349a53af 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -122,7 +122,7 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t offset); -extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, +extern int ip_mc_sf_allow(const struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h new file mode 100644 index 000000000000..9cb6c80dea71 --- /dev/null +++ b/include/linux/iio/iio-gts-helper.h @@ -0,0 +1,206 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* gain-time-scale conversion helpers for IIO light sensors + * + * Copyright (c) 2023 Matti Vaittinen <mazziesaccount@gmail.com> + */ + +#ifndef __IIO_GTS_HELPER__ +#define __IIO_GTS_HELPER__ + +#include <linux/types.h> + +struct device; + +/** + * struct iio_gain_sel_pair - gain - selector values + * + * In many cases devices like light sensors allow setting signal amplification + * (gain) using a register interface. This structure describes amplification + * and corresponding selector (register value) + * + * @gain: Gain (multiplication) value. Gain must be positive, negative + * values are reserved for error handling. + * @sel: Selector (usually register value) used to indicate this gain. + * NOTE: Only selectors >= 0 supported. + */ +struct iio_gain_sel_pair { + int gain; + int sel; +}; + +/** + * struct iio_itime_sel_mul - integration time description + * + * In many cases devices like light sensors allow setting the duration of + * collecting data. Typically this duration has also an impact to the magnitude + * of measured values (gain). This structure describes the relation of + * integration time and amplification as well as corresponding selector + * (register value). + * + * An example could be a sensor allowing 50, 100, 200 and 400 mS times. The + * respective multiplication values could be 50 mS => 1, 100 mS => 2, + * 200 mS => 4 and 400 mS => 8 assuming the impact of integration time would be + * linear in a way that when collecting data for 50 mS caused value X, doubling + * the data collection time caused value 2X etc. + * + * @time_us: Integration time in microseconds. Time values must be positive, + * negative values are reserved for error handling. + * @sel: Selector (usually register value) used to indicate this time + * NOTE: Only selectors >= 0 supported. + * @mul: Multiplication to the values caused by this time. + * NOTE: Only multipliers > 0 supported. + */ +struct iio_itime_sel_mul { + int time_us; + int sel; + int mul; +}; + +struct iio_gts { + u64 max_scale; + const struct iio_gain_sel_pair *hwgain_table; + int num_hwgain; + const struct iio_itime_sel_mul *itime_table; + int num_itime; + int **per_time_avail_scale_tables; + int *avail_all_scales_table; + int num_avail_all_scales; + int *avail_time_tables; + int num_avail_time_tables; +}; + +#define GAIN_SCALE_GAIN(_gain, _sel) \ +{ \ + .gain = (_gain), \ + .sel = (_sel), \ +} + +#define GAIN_SCALE_ITIME_US(_itime, _sel, _mul) \ +{ \ + .time_us = (_itime), \ + .sel = (_sel), \ + .mul = (_mul), \ +} + +static inline const struct iio_itime_sel_mul * +iio_gts_find_itime_by_time(struct iio_gts *gts, int time) +{ + int i; + + if (!gts->num_itime) + return NULL; + + for (i = 0; i < gts->num_itime; i++) + if (gts->itime_table[i].time_us == time) + return >s->itime_table[i]; + + return NULL; +} + +static inline const struct iio_itime_sel_mul * +iio_gts_find_itime_by_sel(struct iio_gts *gts, int sel) +{ + int i; + + for (i = 0; i < gts->num_itime; i++) + if (gts->itime_table[i].sel == sel) + return >s->itime_table[i]; + + return NULL; +} + +int devm_iio_init_iio_gts(struct device *dev, int max_scale_int, int max_scale_nano, + const struct iio_gain_sel_pair *gain_tbl, int num_gain, + const struct iio_itime_sel_mul *tim_tbl, int num_times, + struct iio_gts *gts); +/** + * iio_gts_find_int_time_by_sel - find integration time matching a selector + * @gts: Gain time scale descriptor + * @sel: selector for which matching integration time is searched for + * + * Return: integration time matching given selector or -EINVAL if + * integration time was not found. + */ +static inline int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel) +{ + const struct iio_itime_sel_mul *itime; + + itime = iio_gts_find_itime_by_sel(gts, sel); + if (!itime) + return -EINVAL; + + return itime->time_us; +} + +/** + * iio_gts_find_sel_by_int_time - find selector matching integration time + * @gts: Gain time scale descriptor + * @time: Integration time for which matching selector is searched for + * + * Return: a selector matching given integration time or -EINVAL if + * selector was not found. + */ +static inline int iio_gts_find_sel_by_int_time(struct iio_gts *gts, int time) +{ + const struct iio_itime_sel_mul *itime; + + itime = iio_gts_find_itime_by_time(gts, time); + if (!itime) + return -EINVAL; + + return itime->sel; +} + +/** + * iio_gts_valid_time - check if given integration time is valid + * @gts: Gain time scale descriptor + * @time_us: Integration time to check + * + * Return: True if given time is supported by device. False if not. + */ +static inline bool iio_gts_valid_time(struct iio_gts *gts, int time_us) +{ + return iio_gts_find_itime_by_time(gts, time_us) != NULL; +} + +int iio_gts_find_sel_by_gain(struct iio_gts *gts, int gain); + +/** + * iio_gts_valid_gain - check if given HW-gain is valid + * @gts: Gain time scale descriptor + * @gain: HW-gain to check + * + * Return: True if given time is supported by device. False if not. + */ +static inline bool iio_gts_valid_gain(struct iio_gts *gts, int gain) +{ + return iio_gts_find_sel_by_gain(gts, gain) >= 0; +} + +int iio_find_closest_gain_low(struct iio_gts *gts, int gain, bool *in_range); +int iio_gts_find_gain_by_sel(struct iio_gts *gts, int sel); +int iio_gts_get_min_gain(struct iio_gts *gts); +int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel); +int iio_gts_find_sel_by_int_time(struct iio_gts *gts, int time); + +int iio_gts_total_gain_to_scale(struct iio_gts *gts, int total_gain, + int *scale_int, int *scale_nano); +int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel, + int scale_int, int scale_nano, + int *gain_sel); +int iio_gts_get_scale(struct iio_gts *gts, int gain, int time, int *scale_int, + int *scale_nano); +int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts, + int old_gain, int old_time_sel, + int new_time_sel, int *new_gain); +int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain, + int old_time, int new_time, + int *new_gain); +int iio_gts_avail_times(struct iio_gts *gts, const int **vals, int *type, + int *length); +int iio_gts_all_avail_scales(struct iio_gts *gts, const int **vals, int *type, + int *length); +int iio_gts_avail_scales_for_time(struct iio_gts *gts, int time, + const int **vals, int *type, int *length); + +#endif diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index f6360d9a492d..51f52c5c6092 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -151,14 +151,8 @@ void iio_trigger_unregister(struct iio_trigger *trig_info); **/ int iio_trigger_set_immutable(struct iio_dev *indio_dev, struct iio_trigger *trig); -/** - * iio_trigger_poll() - called on a trigger occurring - * @trig: trigger which occurred - * - * Typically called in relevant hardware interrupt handler. - **/ void iio_trigger_poll(struct iio_trigger *trig); -void iio_trigger_poll_chained(struct iio_trigger *trig); +void iio_trigger_poll_nested(struct iio_trigger *trig); irqreturn_t iio_trigger_generic_data_rdy_poll(int irq, void *private); diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 501fa8486749..1b608e00290a 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -15,12 +15,11 @@ /** * instrument_read - instrument regular read access + * @v: address of access + * @size: size of access * * Instrument a regular read access. The instrumentation should be inserted * before the actual read happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_read(const volatile void *v, size_t size) { @@ -30,12 +29,11 @@ static __always_inline void instrument_read(const volatile void *v, size_t size) /** * instrument_write - instrument regular write access + * @v: address of access + * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_write(const volatile void *v, size_t size) { @@ -45,12 +43,11 @@ static __always_inline void instrument_write(const volatile void *v, size_t size /** * instrument_read_write - instrument regular read-write access + * @v: address of access + * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_read_write(const volatile void *v, size_t size) { @@ -60,12 +57,11 @@ static __always_inline void instrument_read_write(const volatile void *v, size_t /** * instrument_atomic_read - instrument atomic read access + * @v: address of access + * @size: size of access * * Instrument an atomic read access. The instrumentation should be inserted * before the actual read happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) { @@ -75,12 +71,11 @@ static __always_inline void instrument_atomic_read(const volatile void *v, size_ /** * instrument_atomic_write - instrument atomic write access + * @v: address of access + * @size: size of access * * Instrument an atomic write access. The instrumentation should be inserted * before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) { @@ -90,12 +85,11 @@ static __always_inline void instrument_atomic_write(const volatile void *v, size /** * instrument_atomic_read_write - instrument atomic read-write access + * @v: address of access + * @size: size of access * * Instrument an atomic read-write access. The instrumentation should be * inserted before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) { @@ -105,13 +99,12 @@ static __always_inline void instrument_atomic_read_write(const volatile void *v, /** * instrument_copy_to_user - instrument reads of copy_to_user + * @to: destination address + * @from: source address + * @n: number of bytes to copy * * Instrument reads from kernel memory, that are due to copy_to_user (and * variants). The instrumentation must be inserted before the accesses. - * - * @to destination address - * @from source address - * @n number of bytes to copy */ static __always_inline void instrument_copy_to_user(void __user *to, const void *from, unsigned long n) @@ -123,13 +116,12 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n) /** * instrument_copy_from_user_before - add instrumentation before copy_from_user + * @to: destination address + * @from: source address + * @n: number of bytes to copy * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. - * - * @to destination address - * @from source address - * @n number of bytes to copy */ static __always_inline void instrument_copy_from_user_before(const void *to, const void __user *from, unsigned long n) @@ -140,14 +132,13 @@ instrument_copy_from_user_before(const void *to, const void __user *from, unsign /** * instrument_copy_from_user_after - add instrumentation after copy_from_user + * @to: destination address + * @from: source address + * @n: number of bytes to copy + * @left: number of bytes not copied (as returned by copy_from_user) * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted after the accesses. - * - * @to destination address - * @from source address - * @n number of bytes to copy - * @left number of bytes not copied (as returned by copy_from_user) */ static __always_inline void instrument_copy_from_user_after(const void *to, const void __user *from, @@ -158,12 +149,11 @@ instrument_copy_from_user_after(const void *to, const void __user *from, /** * instrument_get_user() - add instrumentation to get_user()-like macros + * @to: destination variable, may not be address-taken * * get_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. - * - * @to destination variable, may not be address-taken */ #define instrument_get_user(to) \ ({ \ @@ -175,14 +165,13 @@ instrument_copy_from_user_after(const void *to, const void __user *from, /** * instrument_put_user() - add instrumentation to put_user()-like macros + * @from: source address + * @ptr: userspace pointer to copy to + * @size: number of bytes to copy * * put_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. - * - * @from source address - * @ptr userspace pointer to copy to - * @size number of bytes to copy */ #define instrument_put_user(from, ptr, size) \ ({ \ diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index cd5c5a27557f..e6d8aca6886d 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -118,12 +118,12 @@ int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, struct icc_node *icc_node_create(int id); void icc_node_destroy(int id); int icc_link_create(struct icc_node *node, const int dst_id); -int icc_link_destroy(struct icc_node *src, struct icc_node *dst); void icc_node_add(struct icc_node *node, struct icc_provider *provider); void icc_node_del(struct icc_node *node); int icc_nodes_remove(struct icc_provider *provider); -int icc_provider_add(struct icc_provider *provider); -void icc_provider_del(struct icc_provider *provider); +void icc_provider_init(struct icc_provider *provider); +int icc_provider_register(struct icc_provider *provider); +void icc_provider_deregister(struct icc_provider *provider); struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec); void icc_sync_state(struct device *dev); @@ -149,11 +149,6 @@ static inline int icc_link_create(struct icc_node *node, const int dst_id) return -ENOTSUPP; } -static inline int icc_link_destroy(struct icc_node *src, struct icc_node *dst) -{ - return -ENOTSUPP; -} - static inline void icc_node_add(struct icc_node *node, struct icc_provider *provider) { } @@ -167,14 +162,14 @@ static inline int icc_nodes_remove(struct icc_provider *provider) return -ENOTSUPP; } -static inline int icc_provider_add(struct icc_provider *provider) +static inline void icc_provider_init(struct icc_provider *provider) { } + +static inline int icc_provider_register(struct icc_provider *provider) { return -ENOTSUPP; } -static inline void icc_provider_del(struct icc_provider *provider) -{ -} +static inline void icc_provider_deregister(struct icc_provider *provider) { } static inline struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec) { diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 09d4f17c8d3b..7376c1df9c90 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -69,7 +69,10 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, BUG_ON(offset >= mapping->size); phys_addr = mapping->base + offset; - preempt_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + migrate_disable(); pagefault_disable(); return __iomap_local_pfn_prot(PHYS_PFN(phys_addr), mapping->prot); } @@ -79,7 +82,10 @@ io_mapping_unmap_atomic(void __iomem *vaddr) { kunmap_local_indexed((void __force *)vaddr); pagefault_enable(); - preempt_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + migrate_enable(); } static inline void __iomem * @@ -162,7 +168,10 @@ static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) { - preempt_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + migrate_disable(); pagefault_disable(); return io_mapping_map_wc(mapping, offset, PAGE_SIZE); } @@ -172,7 +181,10 @@ io_mapping_unmap_atomic(void __iomem *vaddr) { io_mapping_unmap(vaddr); pagefault_enable(); - preempt_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + migrate_enable(); } static inline void __iomem * diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 934e5dd4ccc0..7fe31b2cd02f 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -24,10 +24,10 @@ enum io_uring_cmd_flags { struct io_uring_cmd { struct file *file; - const void *cmd; + const struct io_uring_sqe *sqe; union { /* callback to defer completions to task context */ - void (*task_work_cb)(struct io_uring_cmd *cmd); + void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned); /* used for polled completion */ void *cookie; }; @@ -36,12 +36,18 @@ struct io_uring_cmd { u8 pdu[32]; /* available inline for free use */ }; +static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) +{ + return sqe->cmd; +} + #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); -void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, + unsigned issue_flags); void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *)); + void (*task_work_cb)(struct io_uring_cmd *, unsigned)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); @@ -72,11 +78,11 @@ static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, return -EOPNOTSUPP; } static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, - ssize_t ret2) + ssize_t ret2, unsigned issue_flags) { } static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *)) + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) { } static inline struct sock *io_uring_get_socket(struct file *file) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 00689c12f6ab..1b2a20a42413 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -188,8 +188,10 @@ struct io_ev_fd { }; struct io_alloc_cache { - struct hlist_head list; + struct io_wq_work_node list; unsigned int nr_cached; + unsigned int max_cached; + size_t elem_size; }; struct io_ring_ctx { @@ -239,7 +241,6 @@ struct io_ring_ctx { * uring_lock, and updated through io_uring_register(2) */ struct io_rsrc_node *rsrc_node; - int rsrc_cached_refs; atomic_t cancel_seq; struct io_file_table file_table; unsigned nr_user_files; @@ -295,7 +296,7 @@ struct io_ring_ctx { spinlock_t completion_lock; bool poll_multi_queue; - bool cq_waiting; + atomic_t cq_wait_nr; /* * ->iopoll_list is protected by the ctx->uring_lock for @@ -325,16 +326,15 @@ struct io_ring_ctx { struct io_restriction restrictions; /* slow path rsrc auxilary data, used by update/register */ - struct io_rsrc_node *rsrc_backup_node; struct io_mapped_ubuf *dummy_ubuf; struct io_rsrc_data *file_data; struct io_rsrc_data *buf_data; - struct delayed_work rsrc_put_work; - struct callback_head rsrc_put_tw; - struct llist_head rsrc_put_llist; + /* protected by ->uring_lock */ struct list_head rsrc_ref_list; - spinlock_t rsrc_ref_lock; + struct io_alloc_cache rsrc_node_cache; + struct wait_queue_head rsrc_quiesce_wq; + unsigned rsrc_quiesce; struct list_head io_buffers_pages; @@ -366,6 +366,11 @@ struct io_ring_ctx { unsigned evfd_last_cq_tail; }; +struct io_tw_state { + /* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */ + bool locked; +}; + enum { REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, @@ -472,7 +477,7 @@ enum { REQ_F_HASH_LOCKED = BIT(REQ_F_HASH_LOCKED_BIT), }; -typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked); +typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); struct io_task_work { struct llist_node node; @@ -562,6 +567,7 @@ struct io_kiocb { atomic_t refs; atomic_t poll_refs; struct io_task_work io_task_work; + unsigned nr_tw; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ union { struct hlist_node hash_node; diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h deleted file mode 100644 index af1c9d62e642..000000000000 --- a/include/linux/ioasid.h +++ /dev/null @@ -1,83 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_IOASID_H -#define __LINUX_IOASID_H - -#include <linux/types.h> -#include <linux/errno.h> - -#define INVALID_IOASID ((ioasid_t)-1) -typedef unsigned int ioasid_t; -typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); -typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); - -struct ioasid_set { - int dummy; -}; - -/** - * struct ioasid_allocator_ops - IOASID allocator helper functions and data - * - * @alloc: helper function to allocate IOASID - * @free: helper function to free IOASID - * @list: for tracking ops that share helper functions but not data - * @pdata: data belong to the allocator, provided when calling alloc() - */ -struct ioasid_allocator_ops { - ioasid_alloc_fn_t alloc; - ioasid_free_fn_t free; - struct list_head list; - void *pdata; -}; - -#define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 } - -#if IS_ENABLED(CONFIG_IOASID) -ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, - void *private); -void ioasid_free(ioasid_t ioasid); -void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)); -int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); -void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); -int ioasid_set_data(ioasid_t ioasid, void *data); -static inline bool pasid_valid(ioasid_t ioasid) -{ - return ioasid != INVALID_IOASID; -} - -#else /* !CONFIG_IOASID */ -static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, - ioasid_t max, void *private) -{ - return INVALID_IOASID; -} - -static inline void ioasid_free(ioasid_t ioasid) { } - -static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)) -{ - return NULL; -} - -static inline int ioasid_register_allocator(struct ioasid_allocator_ops *allocator) -{ - return -ENOTSUPP; -} - -static inline void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator) -{ -} - -static inline int ioasid_set_data(ioasid_t ioasid, void *data) -{ - return -ENOTSUPP; -} - -static inline bool pasid_valid(ioasid_t ioasid) -{ - return false; -} - -#endif /* CONFIG_IOASID */ -#endif /* __LINUX_IOASID_H */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0f8123504e5e..e2b836c2e119 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -377,12 +377,6 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_PARTIAL (1 << 2) -/* - * The caller will sync the write if needed; do not sync it within - * iomap_dio_rw. Overrides IOMAP_DIO_FORCE_WAIT. - */ -#define IOMAP_DIO_NOSYNC (1 << 3) - ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 6595454d4f48..e8c9a7da1060 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -13,7 +13,6 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/of.h> -#include <linux/ioasid.h> #include <uapi/linux/iommu.h> #define IOMMU_READ (1 << 0) @@ -192,6 +191,7 @@ enum iommu_dev_features { }; #define IOMMU_PASID_INVALID (-1U) +typedef unsigned int ioasid_t; #ifdef CONFIG_IOMMU_API @@ -455,12 +455,11 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) return dev->iommu->iommu_dev->ops; } -extern int bus_iommu_probe(struct bus_type *bus); -extern bool iommu_present(struct bus_type *bus); +extern int bus_iommu_probe(const struct bus_type *bus); +extern bool iommu_present(const struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern bool iommu_group_has_isolated_msi(struct iommu_group *group); -extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); -extern struct iommu_group *iommu_group_get_by_id(int id); +extern struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus); extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); @@ -699,7 +698,6 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv) } int iommu_probe_device(struct device *dev); -void iommu_release_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); @@ -732,7 +730,7 @@ struct iommu_device {}; struct iommu_fault_param {}; struct iommu_iotlb_gather {}; -static inline bool iommu_present(struct bus_type *bus) +static inline bool iommu_present(const struct bus_type *bus) { return false; } @@ -742,12 +740,7 @@ static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) return false; } -static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) -{ - return NULL; -} - -static inline struct iommu_group *iommu_group_get_by_id(int id) +static inline struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus) { return NULL; } @@ -1173,6 +1166,15 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream } #ifdef CONFIG_IOMMU_SVA +static inline void mm_pasid_init(struct mm_struct *mm) +{ + mm->pasid = IOMMU_PASID_INVALID; +} +static inline bool mm_valid_pasid(struct mm_struct *mm) +{ + return mm->pasid != IOMMU_PASID_INVALID; +} +void mm_pasid_drop(struct mm_struct *mm); struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); void iommu_sva_unbind_device(struct iommu_sva *handle); @@ -1192,6 +1194,9 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) { return IOMMU_PASID_INVALID; } +static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; } +static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif /* CONFIG_IOMMU_SVA */ #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index c0b5b3ac34f1..1129a36a74c4 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -40,9 +40,10 @@ enum { }; struct iommufd_access * -iommufd_access_create(struct iommufd_ctx *ictx, u32 ioas_id, - const struct iommufd_access_ops *ops, void *data); +iommufd_access_create(struct iommufd_ctx *ictx, + const struct iommufd_access_ops *ops, void *data, u32 *id); void iommufd_access_destroy(struct iommufd_access *access); +int iommufd_access_attach(struct iommufd_access *access, u32 ioas_id); void iommufd_ctx_get(struct iommufd_ctx *ictx); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 37dfdcfcdd54..839247a4f48e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -336,10 +336,7 @@ static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; } -static inline struct raw6_sock *raw6_sk(const struct sock *sk) -{ - return (struct raw6_sock *)sk; -} +#define raw6_sk(ptr) container_of_const(ptr, struct raw6_sock, inet.sk) #define ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 5686711b0f40..2223f95079ce 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -151,12 +151,6 @@ int gic_of_init(struct device_node *node, struct device_node *parent); */ int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq); -/* - * Legacy platforms not converted to DT yet must use this to init - * their GIC - */ -void gic_init(void __iomem *dist , void __iomem *cpu); - void gic_send_sgi(unsigned int cpu_id, unsigned int irq); int gic_get_cpu_id(unsigned int cpu); void gic_migrate_target(unsigned int new_cpu_id); diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 0065209cc004..fe3c9993b5bf 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -67,8 +67,7 @@ static inline void *dereference_symbol_descriptor(void *ptr) #ifdef CONFIG_KALLSYMS unsigned long kallsyms_sym_address(int idx); -int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, - unsigned long), +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), void *data); int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), const char *name, void *data); @@ -166,8 +165,8 @@ static inline bool kallsyms_show_value(const struct cred *cred) return false; } -static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, - unsigned long), void *data) +static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), + void *data) { return -EOPNOTSUPP; } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 40bce7495af8..0d91e0af0125 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -20,6 +20,7 @@ #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/bitops.h> +#include <linux/hex.h> #include <linux/kstrtox.h> #include <linux/log2.h> #include <linux/math.h> @@ -263,34 +264,6 @@ extern enum system_states { SYSTEM_SUSPEND, } system_state; -extern const char hex_asc[]; -#define hex_asc_lo(x) hex_asc[((x) & 0x0f)] -#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] - -static inline char *hex_byte_pack(char *buf, u8 byte) -{ - *buf++ = hex_asc_hi(byte); - *buf++ = hex_asc_lo(byte); - return buf; -} - -extern const char hex_asc_upper[]; -#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] -#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] - -static inline char *hex_byte_pack_upper(char *buf, u8 byte) -{ - *buf++ = hex_asc_upper_hi(byte); - *buf++ = hex_asc_upper_lo(byte); - return buf; -} - -extern int hex_to_bin(unsigned char ch); -extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); -extern char *bin2hex(char *dst, const void *src, size_t count); - -bool mac_pton(const char *s, u8 *mac); - /* * General tracing related utility functions - trace_printk(), * tracing_on/tracing_off and tracing_start()/tracing_stop diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 6883c5922701..22b5cd24f581 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -190,7 +190,6 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, void *buf, unsigned int size, bool get_value); void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); -void *kexec_image_load_default(struct kimage *image); #ifndef arch_kexec_kernel_image_probe static inline int @@ -207,13 +206,6 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image) } #endif -#ifndef arch_kexec_kernel_image_load -static inline void *arch_kexec_kernel_image_load(struct kimage *image) -{ - return kexec_image_load_default(image); -} -#endif - #ifdef CONFIG_KEXEC_SIG #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len); diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index e38ae3c34618..e0c23a32cdf0 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -54,7 +54,8 @@ void __init kmsan_init_runtime(void); * Freed pages are either returned to buddy allocator or held back to be used * as metadata pages. */ -bool __init kmsan_memblock_free_pages(struct page *page, unsigned int order); +bool __init __must_check kmsan_memblock_free_pages(struct page *page, + unsigned int order); /** * kmsan_alloc_page() - Notify KMSAN about an alloc_pages() call. @@ -134,11 +135,14 @@ void kmsan_kfree_large(const void *ptr); * @page_shift: page_shift passed to vmap_range_noflush(). * * KMSAN maps shadow and origin pages of @pages into contiguous ranges in - * vmalloc metadata address range. + * vmalloc metadata address range. Returns 0 on success, callers must check + * for non-zero return value. */ -void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift); +int __must_check kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift); /** * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. @@ -159,11 +163,12 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); * @page_shift: page_shift argument passed to vmap_range_noflush(). * * KMSAN creates new metadata pages for the physical pages mapped into the - * virtual memory. + * virtual memory. Returns 0 on success, callers must check for non-zero return + * value. */ -void kmsan_ioremap_page_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift); +int __must_check kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); /** * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. @@ -235,8 +240,8 @@ static inline void kmsan_init_runtime(void) { } -static inline bool kmsan_memblock_free_pages(struct page *page, - unsigned int order) +static inline bool __must_check kmsan_memblock_free_pages(struct page *page, + unsigned int order) { return true; } @@ -249,10 +254,9 @@ static inline void kmsan_task_exit(struct task_struct *task) { } -static inline int kmsan_alloc_page(struct page *page, unsigned int order, - gfp_t flags) +static inline void kmsan_alloc_page(struct page *page, unsigned int order, + gfp_t flags) { - return 0; } static inline void kmsan_free_page(struct page *page, unsigned int order) @@ -281,12 +285,11 @@ static inline void kmsan_kfree_large(const void *ptr) { } -static inline void kmsan_vmap_pages_range_noflush(unsigned long start, - unsigned long end, - pgprot_t prot, - struct page **pages, - unsigned int page_shift) +static inline int __must_check kmsan_vmap_pages_range_noflush( + unsigned long start, unsigned long end, pgprot_t prot, + struct page **pages, unsigned int page_shift) { + return 0; } static inline void kmsan_vunmap_range_noflush(unsigned long start, @@ -294,12 +297,13 @@ static inline void kmsan_vunmap_range_noflush(unsigned long start, { } -static inline void kmsan_ioremap_page_range(unsigned long start, - unsigned long end, - phys_addr_t phys_addr, - pgprot_t prot, - unsigned int page_shift) +static inline int __must_check kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, + pgprot_t prot, + unsigned int page_shift) { + return 0; } static inline void kmsan_iounmap_page_range(unsigned long start, diff --git a/include/linux/kobject.h b/include/linux/kobject.h index bdab370a24f4..c392c811d9ad 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -79,43 +79,37 @@ struct kobject { unsigned int uevent_suppress:1; }; -extern __printf(2, 3) -int kobject_set_name(struct kobject *kobj, const char *name, ...); -extern __printf(2, 0) -int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, - va_list vargs); +__printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); +__printf(2, 0) int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { return kobj->name; } -extern void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); -extern __printf(3, 4) __must_check -int kobject_add(struct kobject *kobj, struct kobject *parent, - const char *fmt, ...); -extern __printf(4, 5) __must_check -int kobject_init_and_add(struct kobject *kobj, - const struct kobj_type *ktype, struct kobject *parent, - const char *fmt, ...); +void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); +__printf(3, 4) __must_check int kobject_add(struct kobject *kobj, + struct kobject *parent, + const char *fmt, ...); +__printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, + const struct kobj_type *ktype, + struct kobject *parent, + const char *fmt, ...); -extern void kobject_del(struct kobject *kobj); +void kobject_del(struct kobject *kobj); -extern struct kobject * __must_check kobject_create_and_add(const char *name, - struct kobject *parent); +struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); -extern int __must_check kobject_rename(struct kobject *, const char *new_name); -extern int __must_check kobject_move(struct kobject *, struct kobject *); +int __must_check kobject_rename(struct kobject *, const char *new_name); +int __must_check kobject_move(struct kobject *, struct kobject *); -extern struct kobject *kobject_get(struct kobject *kobj); -extern struct kobject * __must_check kobject_get_unless_zero( - struct kobject *kobj); -extern void kobject_put(struct kobject *kobj); +struct kobject *kobject_get(struct kobject *kobj); +struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj); +void kobject_put(struct kobject *kobj); -extern const void *kobject_namespace(const struct kobject *kobj); -extern void kobject_get_ownership(const struct kobject *kobj, - kuid_t *uid, kgid_t *gid); -extern char *kobject_get_path(const struct kobject *kobj, gfp_t flag); +const void *kobject_namespace(const struct kobject *kobj); +void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid); +char *kobject_get_path(const struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); @@ -176,12 +170,11 @@ struct kset { const struct kset_uevent_ops *uevent_ops; } __randomize_layout; -extern void kset_init(struct kset *kset); -extern int __must_check kset_register(struct kset *kset); -extern void kset_unregister(struct kset *kset); -extern struct kset * __must_check kset_create_and_add(const char *name, - const struct kset_uevent_ops *u, - struct kobject *parent_kobj); +void kset_init(struct kset *kset); +int __must_check kset_register(struct kset *kset); +void kset_unregister(struct kset *kset); +struct kset * __must_check kset_create_and_add(const char *name, const struct kset_uevent_ops *u, + struct kobject *parent_kobj); static inline struct kset *to_kset(struct kobject *kobj) { @@ -203,7 +196,7 @@ static inline const struct kobj_type *get_ktype(const struct kobject *kobj) return kobj->ktype; } -extern struct kobject *kset_find_obj(struct kset *, const char *); +struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 7e232ba59b86..899a314bc487 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -18,13 +18,28 @@ #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); + +void ksm_add_vma(struct vm_area_struct *vma); +int ksm_enable_merge_any(struct mm_struct *mm); +int ksm_disable_merge_any(struct mm_struct *mm); +int ksm_disable(struct mm_struct *mm); + int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) - return __ksm_enter(mm); + int ret; + + if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) { + ret = __ksm_enter(mm); + if (ret) + return ret; + } + + if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags)) + set_bit(MMF_VM_MERGE_ANY, &mm->flags); + return 0; } @@ -51,8 +66,26 @@ struct page *ksm_might_need_to_copy(struct page *page, void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); +#ifdef CONFIG_MEMORY_FAILURE +void collect_procs_ksm(struct page *page, struct list_head *to_kill, + int force_early); +#endif + +#ifdef CONFIG_PROC_FS +long ksm_process_profit(struct mm_struct *); +#endif /* CONFIG_PROC_FS */ + #else /* !CONFIG_KSM */ +static inline void ksm_add_vma(struct vm_area_struct *vma) +{ +} + +static inline int ksm_disable(struct mm_struct *mm) +{ + return 0; +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { return 0; @@ -62,6 +95,13 @@ static inline void ksm_exit(struct mm_struct *mm) { } +#ifdef CONFIG_MEMORY_FAILURE +static inline void collect_procs_ksm(struct page *page, + struct list_head *to_kill, int force_early) +{ +} +#endif + #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8ada23756b0e..0e571e973bc2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -58,7 +58,7 @@ /* * Bit 63 of the memslot generation number is an "update in-progress flag", - * e.g. is temporarily set for the duration of install_new_memslots(). + * e.g. is temporarily set for the duration of kvm_swap_active_memslots(). * This flag effectively creates a unique generation number that is used to * mark cached memslot data, e.g. MMIO accesses, as potentially being stale, * i.e. may (or may not) have come from the previous memslots generation. @@ -713,7 +713,7 @@ struct kvm { * use by the VM. To be used under the slots_lock (above) or in a * kvm->srcu critical section where acquiring the slots_lock would * lead to deadlock with the synchronize_srcu in - * install_new_memslots. + * kvm_swap_active_memslots(). */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ @@ -755,6 +755,7 @@ struct kvm { struct { spinlock_t lock; struct list_head items; + /* resampler_list update side is protected by resampler_lock. */ struct list_head resampler_list; struct mutex resampler_lock; } irqfds; @@ -1397,8 +1398,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status); int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg); +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -1986,6 +1986,9 @@ int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #ifdef CONFIG_HAVE_KVM_IRQFD int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); +bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin); void kvm_irq_routing_update(struct kvm *); #else static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) @@ -1994,6 +1997,13 @@ static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) } static inline void kvm_irqfd_release(struct kvm *kvm) {} + +static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin) +{ + return false; +} #endif #else diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h index dac047abdba7..8ad43692e3bb 100644 --- a/include/linux/kvm_irqfd.h +++ b/include/linux/kvm_irqfd.h @@ -31,7 +31,7 @@ struct kvm_kernel_irqfd_resampler { /* * Entry in list of kvm->irqfd.resampler_list. Use for sharing * resamplers among irqfds on the same gsi. - * Accessed and modified under kvm->irqfds.resampler_lock + * RCU list modified under kvm->irqfds.resampler_lock */ struct list_head link; }; diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 2728d49bbdf6..6f4737d5046a 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -91,11 +91,11 @@ struct gfn_to_pfn_cache { * is topped up (__kvm_mmu_topup_memory_cache()). */ struct kvm_mmu_memory_cache { - int nobjs; gfp_t gfp_zero; gfp_t gfp_custom; struct kmem_cache *kmem_cache; int capacity; + int nobjs; void **objects; }; #endif diff --git a/include/linux/leds.h b/include/linux/leds.h index d71201a968b6..c39bbf17a25b 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -82,7 +82,15 @@ struct led_init_data { bool devname_mandatory; }; +#if IS_ENABLED(CONFIG_NEW_LEDS) enum led_default_state led_init_default_state_get(struct fwnode_handle *fwnode); +#else +static inline enum led_default_state +led_init_default_state_get(struct fwnode_handle *fwnode) +{ + return LEDS_DEFSTATE_OFF; +} +#endif struct led_hw_trigger_type { int dummy; @@ -217,9 +225,19 @@ static inline int led_classdev_register(struct device *parent, return led_classdev_register_ext(parent, led_cdev, NULL); } +#if IS_ENABLED(CONFIG_LEDS_CLASS) int devm_led_classdev_register_ext(struct device *parent, struct led_classdev *led_cdev, struct led_init_data *init_data); +#else +static inline int +devm_led_classdev_register_ext(struct device *parent, + struct led_classdev *led_cdev, + struct led_init_data *init_data) +{ + return 0; +} +#endif static inline int devm_led_classdev_register(struct device *parent, struct led_classdev *led_cdev) @@ -256,7 +274,7 @@ struct led_classdev *__must_check devm_of_led_get(struct device *dev, * * Note that if software blinking is active, simply calling * led_cdev->brightness_set() will not stop the blinking, - * use led_classdev_brightness_set() instead. + * use led_set_brightness() instead. */ void led_blink_set(struct led_classdev *led_cdev, unsigned long *delay_on, unsigned long *delay_off); diff --git a/include/linux/libata.h b/include/linux/libata.h index a759dfbdcc91..dd5797fb6305 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -836,7 +836,7 @@ struct ata_port { struct mutex scsi_scan_mutex; struct delayed_work hotplug_task; - struct work_struct scsi_rescan_task; + struct delayed_work scsi_rescan_task; unsigned int hsm_task_state; @@ -1065,10 +1065,10 @@ extern void ata_host_get(struct ata_host *host); extern void ata_host_put(struct ata_host *host); extern int ata_host_start(struct ata_host *host); extern int ata_host_register(struct ata_host *host, - struct scsi_host_template *sht); + const struct scsi_host_template *sht); extern int ata_host_activate(struct ata_host *host, int irq, irq_handler_t irq_handler, unsigned long irq_flags, - struct scsi_host_template *sht); + const struct scsi_host_template *sht); extern void ata_host_detach(struct ata_host *host); extern void ata_host_init(struct ata_host *, struct device *, struct ata_port_operations *); extern int ata_scsi_detect(struct scsi_host_template *sht); @@ -1980,10 +1980,10 @@ extern int ata_pci_sff_prepare_host(struct pci_dev *pdev, struct ata_host **r_host); extern int ata_pci_sff_activate_host(struct ata_host *host, irq_handler_t irq_handler, - struct scsi_host_template *sht); + const struct scsi_host_template *sht); extern int ata_pci_sff_init_one(struct pci_dev *pdev, const struct ata_port_info * const * ppi, - struct scsi_host_template *sht, void *host_priv, int hflags); + const struct scsi_host_template *sht, void *host_priv, int hflags); #endif /* CONFIG_PCI */ #ifdef CONFIG_ATA_BMDMA @@ -2019,7 +2019,7 @@ extern int ata_pci_bmdma_prepare_host(struct pci_dev *pdev, struct ata_host **r_host); extern int ata_pci_bmdma_init_one(struct pci_dev *pdev, const struct ata_port_info * const * ppi, - struct scsi_host_template *sht, + const struct scsi_host_template *sht, void *host_priv, int hflags); #endif /* CONFIG_PCI */ #endif /* CONFIG_ATA_BMDMA */ diff --git a/include/linux/libgcc.h b/include/linux/libgcc.h index b8dc75f0c830..fc388da6a027 100644 --- a/include/linux/libgcc.h +++ b/include/linux/libgcc.h @@ -27,4 +27,11 @@ typedef union { long long ll; } DWunion; +long long notrace __ashldi3(long long u, word_type b); +long long notrace __ashrdi3(long long u, word_type b); +word_type notrace __cmpdi2(long long a, long long b); +long long notrace __lshrdi3(long long u, word_type b); +long long notrace __muldi3(long long u, long long v); +word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b); + #endif /* __ASM_LIBGCC_H */ diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 293e29960c6e..9b9b38e89563 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -13,6 +13,7 @@ #include <linux/ftrace.h> #include <linux/completion.h> #include <linux/list.h> +#include <linux/livepatch_sched.h> #if IS_ENABLED(CONFIG_LIVEPATCH) diff --git a/include/linux/livepatch_sched.h b/include/linux/livepatch_sched.h new file mode 100644 index 000000000000..013794fb5da0 --- /dev/null +++ b/include/linux/livepatch_sched.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_LIVEPATCH_SCHED_H_ +#define _LINUX_LIVEPATCH_SCHED_H_ + +#include <linux/jump_label.h> +#include <linux/static_call_types.h> + +#ifdef CONFIG_LIVEPATCH + +void __klp_sched_try_switch(void); + +#if !defined(CONFIG_PREEMPT_DYNAMIC) || !defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) + +DECLARE_STATIC_KEY_FALSE(klp_sched_try_switch_key); + +static __always_inline void klp_sched_try_switch(void) +{ + if (static_branch_unlikely(&klp_sched_try_switch_key)) + __klp_sched_try_switch(); +} + +#endif /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ + +#else /* !CONFIG_LIVEPATCH */ +static inline void klp_sched_try_switch(void) {} +static inline void __klp_sched_try_switch(void) {} +#endif /* CONFIG_LIVEPATCH */ + +#endif /* _LINUX_LIVEPATCH_SCHED_H_ */ diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 0168ac9fdda8..f42594a9efe0 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -99,21 +99,11 @@ struct nsm_handle { /* * Rigorous type checking on sockaddr type conversions */ -static inline struct sockaddr_in *nlm_addr_in(const struct nlm_host *host) -{ - return (struct sockaddr_in *)&host->h_addr; -} - static inline struct sockaddr *nlm_addr(const struct nlm_host *host) { return (struct sockaddr *)&host->h_addr; } -static inline struct sockaddr_in *nlm_srcaddr_in(const struct nlm_host *host) -{ - return (struct sockaddr_in *)&host->h_srcaddr; -} - static inline struct sockaddr *nlm_srcaddr(const struct nlm_host *host) { return (struct sockaddr *)&host->h_srcaddr; @@ -131,7 +121,16 @@ struct nlm_lockowner { uint32_t pid; }; -struct nlm_wait; +/* + * This is the representation of a blocked client lock. + */ +struct nlm_wait { + struct list_head b_list; /* linked list */ + wait_queue_head_t b_wait; /* where to wait on */ + struct nlm_host *b_host; + struct file_lock *b_lock; /* local file lock */ + __be32 b_status; /* grant callback status */ +}; /* * Memory chunk for NLM client RPC request. @@ -212,9 +211,11 @@ struct nlm_rqst * nlm_alloc_call(struct nlm_host *host); int nlm_async_call(struct nlm_rqst *, u32, const struct rpc_call_ops *); int nlm_async_reply(struct nlm_rqst *, u32, const struct rpc_call_ops *); void nlmclnt_release_call(struct nlm_rqst *); -struct nlm_wait * nlmclnt_prepare_block(struct nlm_host *host, struct file_lock *fl); -void nlmclnt_finish_block(struct nlm_wait *block); -int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout); +void nlmclnt_prepare_block(struct nlm_wait *block, struct nlm_host *host, + struct file_lock *fl); +void nlmclnt_queue_block(struct nlm_wait *block); +__be32 nlmclnt_dequeue_block(struct nlm_wait *block); +int nlmclnt_wait(struct nlm_wait *block, struct nlm_rqst *req, long timeout); __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock); void nlmclnt_recovery(struct nlm_host *); diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 9a6b55da8fd6..72831e35dca3 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -22,6 +22,7 @@ #define nlm4_fbig cpu_to_be32(NLM_FBIG) #define nlm4_failed cpu_to_be32(NLM_FAILED) +void nlm4svc_set_file_lock_range(struct file_lock *fl, u64 off, u64 len); 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); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1023f349af71..74bd269a80a2 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -134,7 +134,8 @@ struct held_lock { unsigned int read:2; /* see lock_acquire() comment */ unsigned int check:1; /* see lock_acquire() comment */ unsigned int hardirqs_off:1; - unsigned int references:12; /* 32 bits */ + unsigned int sync:1; + unsigned int references:11; /* 32 bits */ unsigned int pin_count; }; @@ -268,6 +269,10 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, extern void lock_release(struct lockdep_map *lock, unsigned long ip); +extern void lock_sync(struct lockdep_map *lock, unsigned int subclass, + int read, int check, struct lockdep_map *nest_lock, + unsigned long ip); + /* lock_is_held_type() returns */ #define LOCK_STATE_UNKNOWN -1 #define LOCK_STATE_NOT_HELD 0 @@ -339,6 +344,16 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) #define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) +/* + * Must use lock_map_aquire_try() with override maps to avoid + * lockdep thinking they participate in the block chain. + */ +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map _name = { \ + .name = #_name "-wait-type-override", \ + .wait_type_inner = _wait_type, \ + .lock_type = LD_LOCK_WAIT_OVERRIDE, } + #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) @@ -427,6 +442,9 @@ extern int lockdep_is_held(const void *); #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map __maybe_unused _name = {} + #endif /* !LOCKDEP */ enum xhlock_context_t { @@ -551,9 +569,11 @@ do { \ #define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) +#define lock_map_acquire_try(l) lock_acquire_exclusive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) +#define lock_map_sync(l) lock_sync(l, 0, 0, 1, NULL, _THIS_IP_) #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index d22430840b53..59f4fb1626ea 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -33,6 +33,7 @@ enum lockdep_wait_type { enum lockdep_lock_type { LD_LOCK_NORMAL = 0, /* normal, catch all */ LD_LOCK_PERCPU, /* percpu */ + LD_LOCK_WAIT_OVERRIDE, /* annotation */ LD_LOCK_MAX, }; diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 094b76dc7164..6bb55e61e8e8 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -381,7 +381,7 @@ LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key) LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) -LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **_buffer) +LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **buffer) #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 6e156d2acffc..ab2b2fafa4a4 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -29,1630 +29,6 @@ #include <linux/init.h> #include <linux/rculist.h> -/** - * union security_list_options - Linux Security Module hook function list - * - * Security hooks for program execution operations. - * - * @bprm_creds_for_exec: - * If the setup in prepare_exec_creds did not setup @bprm->cred->security - * properly for executing @bprm->file, update the LSM's portion of - * @bprm->cred->security to be what commit_creds needs to install for the - * new program. This hook may also optionally check permissions - * (e.g. for transitions between security domains). - * The hook must set @bprm->secureexec to 1 if AT_SECURE should be set to - * request libc enable secure mode. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_creds_from_file: - * If @file is setpcap, suid, sgid or otherwise marked to change - * privilege upon exec, update @bprm->cred to reflect that change. - * This is called after finding the binary that will be executed. - * without an interpreter. This ensures that the credentials will not - * be derived from a script that the binary will need to reopen, which - * when reopend may end up being a completely different file. This - * hook may also optionally check permissions (e.g. for transitions - * between security domains). - * The hook must set @bprm->secureexec to 1 if AT_SECURE should be set to - * request libc enable secure mode. - * The hook must add to @bprm->per_clear any personality flags that - * should be cleared from current->personality. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_check_security: - * This hook mediates the point when a search for a binary handler will - * begin. It allows a check against the @bprm->cred->security value - * which was set in the preceding creds_for_exec call. The argv list and - * envp list are reliably available in @bprm. This hook may be called - * multiple times during a single execve. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_committing_creds: - * Prepare to install the new security attributes of a process being - * transformed by an execve operation, based on the old credentials - * pointed to by @current->cred and the information set in @bprm->cred by - * the bprm_creds_for_exec hook. @bprm points to the linux_binprm - * structure. This hook is a good place to perform state changes on the - * process such as closing open file descriptors to which access will no - * longer be granted when the attributes are changed. This is called - * immediately before commit_creds(). - * @bprm_committed_creds: - * Tidy up after the installation of the new security attributes of a - * process being transformed by an execve operation. The new credentials - * have, by this point, been set to @current->cred. @bprm points to the - * linux_binprm structure. This hook is a good place to perform state - * changes on the process such as clearing out non-inheritable signal - * state. This is called immediately after commit_creds(). - * - * Security hooks for mount using fs_context. - * [See also Documentation/filesystems/mount_api.rst] - * - * @fs_context_dup: - * Allocate and attach a security structure to sc->security. This pointer - * is initialised to NULL by the caller. - * @fc indicates the new filesystem context. - * @src_fc indicates the original filesystem context. - * Return 0 on success or a negative error code on failure. - * @fs_context_parse_param: - * Userspace provided a parameter to configure a superblock. The LSM may - * reject it with an error and may use it for itself, in which case it - * should return 0; otherwise it should return -ENOPARAM to pass it on to - * the filesystem. - * @fc indicates the filesystem context. - * @param The parameter. - * - * Security hooks for filesystem operations. - * - * @sb_alloc_security: - * Allocate and attach a security structure to the sb->s_security field. - * The s_security field is initialized to NULL when the structure is - * allocated. - * @sb contains the super_block structure to be modified. - * Return 0 if operation was successful. - * @sb_delete: - * Release objects tied to a superblock (e.g. inodes). - * @sb contains the super_block structure being released. - * @sb_free_security: - * Deallocate and clear the sb->s_security field. - * @sb contains the super_block structure to be modified. - * @sb_free_mnt_opts: - * Free memory associated with @mnt_ops. - * @sb_eat_lsm_opts: - * Eat (scan @orig options) and save them in @mnt_opts. - * Return 0 on success, negative values on failure. - * @sb_statfs: - * Check permission before obtaining filesystem statistics for the @mnt - * mountpoint. - * @dentry is a handle on the superblock for the filesystem. - * Return 0 if permission is granted. - * @sb_mount: - * Check permission before an object specified by @dev_name is mounted on - * the mount point named by @nd. For an ordinary mount, @dev_name - * identifies a device if the file system type requires a device. For a - * remount (@flags & MS_REMOUNT), @dev_name is irrelevant. For a - * loopback/bind mount (@flags & MS_BIND), @dev_name identifies the - * pathname of the object being mounted. - * @dev_name contains the name for object being mounted. - * @path contains the path for mount point object. - * @type contains the filesystem type. - * @flags contains the mount flags. - * @data contains the filesystem-specific data. - * Return 0 if permission is granted. - * @sb_mnt_opts_compat: - * Determine if the new mount options in @mnt_opts are allowed given - * the existing mounted filesystem at @sb. - * @sb superblock being compared. - * @mnt_opts new mount options. - * Return 0 if options are compatible. - * @sb_remount: - * Extracts security system specific mount options and verifies no changes - * are being made to those options. - * @sb superblock being remounted. - * @data contains the filesystem-specific data. - * Return 0 if permission is granted. - * @sb_kern_mount: - * Mount this @sb if allowed by permissions. - * Return 0 if permission is granted. - * @sb_show_options: - * Show (print on @m) mount options for this @sb. - * Return 0 on success, negative values on failure. - * @sb_umount: - * Check permission before the @mnt file system is unmounted. - * @mnt contains the mounted file system. - * @flags contains the unmount flags, e.g. MNT_FORCE. - * Return 0 if permission is granted. - * @sb_pivotroot: - * Check permission before pivoting the root filesystem. - * @old_path contains the path for the new location of the - * current root (put_old). - * @new_path contains the path for the new root (new_root). - * Return 0 if permission is granted. - * @sb_set_mnt_opts: - * Set the security relevant mount options used for a superblock - * @sb the superblock to set security mount options for. - * @opts binary data structure containing all lsm mount data. - * Return 0 on success, error on failure. - * @sb_clone_mnt_opts: - * Copy all security options from a given superblock to another - * @oldsb old superblock which contain information to clone. - * @newsb new superblock which needs filled in. - * Return 0 on success, error on failure. - * @move_mount: - * Check permission before a mount is moved. - * @from_path indicates the mount that is going to be moved. - * @to_path indicates the mountpoint that will be mounted upon. - * Return 0 if permission is granted. - * @dentry_init_security: - * Compute a context for a dentry as the inode is not yet available - * since NFSv4 has no label backed by an EA anyway. - * @dentry dentry to use in calculating the context. - * @mode mode used to determine resource type. - * @name name of the last path component used to create file. - * @xattr_name pointer to place the pointer to security xattr name. - * Caller does not have to free the resulting pointer. Its - * a pointer to static string. - * @ctx pointer to place the pointer to the resulting context in. - * @ctxlen point to place the length of the resulting context. - * Return 0 on success, negative values on failure. - * @dentry_create_files_as: - * Compute a context for a dentry as the inode is not yet available - * and set that context in passed in creds so that new files are - * created using that context. Context is calculated using the - * passed in creds and not the creds of the caller. - * @dentry dentry to use in calculating the context. - * @mode mode used to determine resource type. - * @name name of the last path component used to create file. - * @old creds which should be used for context calculation. - * @new creds to modify. - * Return 0 on success, error on failure. - * - * - * Security hooks for inode operations. - * - * @inode_alloc_security: - * Allocate and attach a security structure to @inode->i_security. The - * i_security field is initialized to NULL when the inode structure is - * allocated. - * @inode contains the inode structure. - * Return 0 if operation was successful. - * @inode_free_security: - * @inode contains the inode structure. - * Deallocate the inode security structure and set @inode->i_security to - * NULL. - * @inode_init_security: - * Obtain the security attribute name suffix and value to set on a newly - * created inode and set up the incore security field for the new inode. - * This hook is called by the fs code as part of the inode creation - * transaction and provides for atomic labeling of the inode, unlike - * the post_create/mkdir/... hooks called by the VFS. The hook function - * is expected to allocate the name and value via kmalloc, with the caller - * being responsible for calling kfree after using them. - * If the security module does not use security attributes or does - * not wish to put a security attribute on this particular inode, - * then it should return -EOPNOTSUPP to skip this processing. - * @inode contains the inode structure of the newly created inode. - * @dir contains the inode structure of the parent directory. - * @qstr contains the last path component of the new object. - * @name will be set to the allocated name suffix (e.g. selinux). - * @value will be set to the allocated attribute value. - * @len will be set to the length of the value. - * Returns 0 if @name and @value have been successfully set, - * -EOPNOTSUPP if no security attribute is needed, or - * -ENOMEM on memory allocation failure. - * @inode_init_security_anon: - * Set up the incore security field for the new anonymous inode - * and return whether the inode creation is permitted by the security - * module or not. - * @inode contains the inode structure. - * @name name of the anonymous inode class. - * @context_inode optional related inode. - * Returns 0 on success, -EACCES if the security module denies the - * creation of this inode, or another -errno upon other errors. - * @inode_create: - * Check permission to create a regular file. - * @dir contains inode structure of the parent of the new file. - * @dentry contains the dentry structure for the file to be created. - * @mode contains the file mode of the file to be created. - * Return 0 if permission is granted. - * @inode_link: - * Check permission before creating a new hard link to a file. - * @old_dentry contains the dentry structure for an existing - * link to the file. - * @dir contains the inode structure of the parent directory - * of the new link. - * @new_dentry contains the dentry structure for the new link. - * Return 0 if permission is granted. - * @path_link: - * Check permission before creating a new hard link to a file. - * @old_dentry contains the dentry structure for an existing link - * to the file. - * @new_dir contains the path structure of the parent directory of - * the new link. - * @new_dentry contains the dentry structure for the new link. - * Return 0 if permission is granted. - * @inode_unlink: - * Check the permission to remove a hard link to a file. - * @dir contains the inode structure of parent directory of the file. - * @dentry contains the dentry structure for file to be unlinked. - * Return 0 if permission is granted. - * @path_unlink: - * Check the permission to remove a hard link to a file. - * @dir contains the path structure of parent directory of the file. - * @dentry contains the dentry structure for file to be unlinked. - * Return 0 if permission is granted. - * @inode_symlink: - * Check the permission to create a symbolic link to a file. - * @dir contains the inode structure of parent directory of - * the symbolic link. - * @dentry contains the dentry structure of the symbolic link. - * @old_name contains the pathname of file. - * Return 0 if permission is granted. - * @path_symlink: - * Check the permission to create a symbolic link to a file. - * @dir contains the path structure of parent directory of - * the symbolic link. - * @dentry contains the dentry structure of the symbolic link. - * @old_name contains the pathname of file. - * Return 0 if permission is granted. - * @inode_mkdir: - * Check permissions to create a new directory in the existing directory - * associated with inode structure @dir. - * @dir contains the inode structure of parent of the directory - * to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. - * Return 0 if permission is granted. - * @path_mkdir: - * Check permissions to create a new directory in the existing directory - * associated with path structure @path. - * @dir contains the path structure of parent of the directory - * to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. - * Return 0 if permission is granted. - * @inode_rmdir: - * Check the permission to remove a directory. - * @dir contains the inode structure of parent of the directory - * to be removed. - * @dentry contains the dentry structure of directory to be removed. - * Return 0 if permission is granted. - * @path_rmdir: - * Check the permission to remove a directory. - * @dir contains the path structure of parent of the directory to be - * removed. - * @dentry contains the dentry structure of directory to be removed. - * Return 0 if permission is granted. - * @inode_mknod: - * Check permissions when creating a special file (or a socket or a fifo - * file created via the mknod system call). Note that if mknod operation - * is being done for a regular file, then the create hook will be called - * and not this hook. - * @dir contains the inode structure of parent of the new file. - * @dentry contains the dentry structure of the new file. - * @mode contains the mode of the new file. - * @dev contains the device number. - * Return 0 if permission is granted. - * @path_mknod: - * Check permissions when creating a file. Note that this hook is called - * even if mknod operation is being done for a regular file. - * @dir contains the path structure of parent of the new file. - * @dentry contains the dentry structure of the new file. - * @mode contains the mode of the new file. - * @dev contains the undecoded device number. Use new_decode_dev() to get - * the decoded device number. - * Return 0 if permission is granted. - * @inode_rename: - * Check for permission to rename a file or directory. - * @old_dir contains the inode structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the inode structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. - * Return 0 if permission is granted. - * @path_rename: - * Check for permission to rename a file or directory. - * @old_dir contains the path structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the path structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. - * @flags may contain rename options such as RENAME_EXCHANGE. - * Return 0 if permission is granted. - * @path_chmod: - * Check for permission to change a mode of the file @path. The new - * mode is specified in @mode. - * @path contains the path structure of the file to change the mode. - * @mode contains the new DAC's permission, which is a bitmask of - * constants from <include/uapi/linux/stat.h>. - * Return 0 if permission is granted. - * @path_chown: - * Check for permission to change owner/group of a file or directory. - * @path contains the path structure. - * @uid contains new owner's ID. - * @gid contains new group's ID. - * Return 0 if permission is granted. - * @path_chroot: - * Check for permission to change root directory. - * @path contains the path structure. - * Return 0 if permission is granted. - * @path_notify: - * Check permissions before setting a watch on events as defined by @mask, - * on an object at @path, whose type is defined by @obj_type. - * Return 0 if permission is granted. - * @inode_readlink: - * Check the permission to read the symbolic link. - * @dentry contains the dentry structure for the file link. - * Return 0 if permission is granted. - * @inode_follow_link: - * Check permission to follow a symbolic link when looking up a pathname. - * @dentry contains the dentry structure for the link. - * @inode contains the inode, which itself is not stable in RCU-walk. - * @rcu indicates whether we are in RCU-walk mode. - * Return 0 if permission is granted. - * @inode_permission: - * Check permission before accessing an inode. This hook is called by the - * existing Linux permission function, so a security module can use it to - * provide additional checking for existing Linux permission checks. - * Notice that this hook is called when a file is opened (as well as many - * other operations), whereas the file_security_ops permission hook is - * called when the actual read/write operations are performed. - * @inode contains the inode structure to check. - * @mask contains the permission mask. - * Return 0 if permission is granted. - * @inode_setattr: - * Check permission before setting file attributes. Note that the kernel - * call to notify_change is performed from several locations, whenever - * file attributes change (such as when a file is truncated, chown/chmod - * operations, transferring disk quotas, etc). - * @dentry contains the dentry structure for the file. - * @attr is the iattr structure containing the new file attributes. - * Return 0 if permission is granted. - * @path_truncate: - * Check permission before truncating the file indicated by path. - * Note that truncation permissions may also be checked based on - * already opened files, using the @file_truncate hook. - * @path contains the path structure for the file. - * Return 0 if permission is granted. - * @inode_getattr: - * Check permission before obtaining file attributes. - * @path contains the path structure for the file. - * Return 0 if permission is granted. - * @inode_setxattr: - * Check permission before setting the extended attributes - * @value identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_post_setxattr: - * Update inode security field after successful setxattr operation. - * @value identified by @name for @dentry. - * @inode_getxattr: - * Check permission before obtaining the extended attributes - * identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_listxattr: - * Check permission before obtaining the list of extended attribute - * names for @dentry. - * Return 0 if permission is granted. - * @inode_removexattr: - * Check permission before removing the extended attribute - * identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_set_acl: - * Check permission before setting posix acls - * The posix acls in @kacl are identified by @acl_name. - * Return 0 if permission is granted. - * @inode_get_acl: - * Check permission before getting osix acls - * The posix acls are identified by @acl_name. - * Return 0 if permission is granted. - * @inode_remove_acl: - * Check permission before removing posix acls - * The posix acls are identified by @acl_name. - * Return 0 if permission is granted. - * @inode_getsecurity: - * Retrieve a copy of the extended attribute representation of the - * security label associated with @name for @inode via @buffer. Note that - * @name is the remainder of the attribute name after the security prefix - * has been removed. @alloc is used to specify if the call should return a - * value via the buffer or just the value length. - * Return size of buffer on success. - * @inode_setsecurity: - * Set the security label associated with @name for @inode from the - * extended attribute value @value. @size indicates the size of the - * @value in bytes. @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. - * Note that @name is the remainder of the attribute name after the - * security. prefix has been removed. - * Return 0 on success. - * @inode_listsecurity: - * Copy the extended attribute names for the security labels - * associated with @inode into @buffer. The maximum size of @buffer - * is specified by @buffer_size. @buffer may be NULL to request - * the size of the buffer required. - * Returns number of bytes used/required on success. - * @inode_need_killpriv: - * Called when an inode has been changed. - * @dentry is the dentry being changed. - * Return <0 on error to abort the inode change operation. - * Return 0 if inode_killpriv does not need to be called. - * Return >0 if inode_killpriv does need to be called. - * @inode_killpriv: - * The setuid bit is being removed. Remove similar security labels. - * Called with the dentry->d_inode->i_mutex held. - * @idmap: idmap of the mount. - * @dentry is the dentry being changed. - * Return 0 on success. If error is returned, then the operation - * causing setuid bit removal is failed. - * @inode_getsecid: - * Get the secid associated with the node. - * @inode contains a pointer to the inode. - * @secid contains a pointer to the location where result will be saved. - * In case of failure, @secid will be set to zero. - * @inode_copy_up: - * A file is about to be copied up from lower layer to upper layer of - * overlay filesystem. Security module can prepare a set of new creds - * and modify as need be and return new creds. Caller will switch to - * new creds temporarily to create new file and release newly allocated - * creds. - * @src indicates the union dentry of file that is being copied up. - * @new pointer to pointer to return newly allocated creds. - * Returns 0 on success or a negative error code on error. - * @inode_copy_up_xattr: - * Filter the xattrs being copied up when a unioned file is copied - * up from a lower layer to the union/overlay layer. - * @name indicates the name of the xattr. - * Returns 0 to accept the xattr, 1 to discard the xattr, -EOPNOTSUPP if - * security module does not know about attribute or a negative error code - * to abort the copy up. Note that the caller is responsible for reading - * and writing the xattrs as this hook is merely a filter. - * @d_instantiate: - * Fill in @inode security information for a @dentry if allowed. - * @getprocattr: - * Read attribute @name for process @p and store it into @value if allowed. - * Return the length of @value on success, a negative value otherwise. - * @setprocattr: - * Write (set) attribute @name to @value, size @size if allowed. - * Return written bytes on success, a negative value otherwise. - * - * Security hooks for kernfs node operations - * - * @kernfs_init_security: - * Initialize the security context of a newly created kernfs node based - * on its own and its parent's attributes. - * @kn_dir the parent kernfs node. - * @kn the new child kernfs node. - * Return 0 if permission is granted. - * - * Security hooks for file operations - * - * @file_permission: - * Check file permissions before accessing an open file. This hook is - * called by various operations that read or write files. A security - * module can use this hook to perform additional checking on these - * operations, e.g. to revalidate permissions on use to support privilege - * bracketing or policy changes. Notice that this hook is used when the - * actual read/write operations are performed, whereas the - * inode_security_ops hook is called when a file is opened (as well as - * many other operations). - * Caveat: Although this hook can be used to revalidate permissions for - * various system call operations that read or write files, it does not - * address the revalidation of permissions for memory-mapped files. - * Security modules must handle this separately if they need such - * revalidation. - * @file contains the file structure being accessed. - * @mask contains the requested permissions. - * Return 0 if permission is granted. - * @file_alloc_security: - * Allocate and attach a security structure to the file->f_security field. - * The security field is initialized to NULL when the structure is first - * created. - * @file contains the file structure to secure. - * Return 0 if the hook is successful and permission is granted. - * @file_free_security: - * Deallocate and free any security structures stored in file->f_security. - * @file contains the file structure being modified. - * @file_ioctl: - * @file contains the file structure. - * @cmd contains the operation to perform. - * @arg contains the operational arguments. - * Check permission for an ioctl operation on @file. Note that @arg - * sometimes represents a user space pointer; in other cases, it may be a - * simple integer value. When @arg represents a user space pointer, it - * should never be used by the security module. - * Return 0 if permission is granted. - * @mmap_addr: - * Check permissions for a mmap operation at @addr. - * @addr contains virtual address that will be used for the operation. - * Return 0 if permission is granted. - * @mmap_file: - * Check permissions for a mmap operation. The @file may be NULL, e.g. - * if mapping anonymous memory. - * @file contains the file structure for file to map (may be NULL). - * @reqprot contains the protection requested by the application. - * @prot contains the protection that will be applied by the kernel. - * @flags contains the operational flags. - * Return 0 if permission is granted. - * @file_mprotect: - * Check permissions before changing memory access permissions. - * @vma contains the memory region to modify. - * @reqprot contains the protection requested by the application. - * @prot contains the protection that will be applied by the kernel. - * Return 0 if permission is granted. - * @file_lock: - * Check permission before performing file locking operations. - * Note the hook mediates both flock and fcntl style locks. - * @file contains the file structure. - * @cmd contains the posix-translated lock operation to perform - * (e.g. F_RDLCK, F_WRLCK). - * Return 0 if permission is granted. - * @file_fcntl: - * Check permission before allowing the file operation specified by @cmd - * from being performed on the file @file. Note that @arg sometimes - * represents a user space pointer; in other cases, it may be a simple - * integer value. When @arg represents a user space pointer, it should - * never be used by the security module. - * @file contains the file structure. - * @cmd contains the operation to be performed. - * @arg contains the operational arguments. - * Return 0 if permission is granted. - * @file_set_fowner: - * Save owner security information (typically from current->security) in - * file->f_security for later use by the send_sigiotask hook. - * @file contains the file structure to update. - * Return 0 on success. - * @file_send_sigiotask: - * Check permission for the file owner @fown to send SIGIO or SIGURG to the - * process @tsk. Note that this hook is sometimes called from interrupt. - * Note that the fown_struct, @fown, is never outside the context of a - * struct file, so the file structure (and associated security information) - * can always be obtained: container_of(fown, struct file, f_owner) - * @tsk contains the structure of task receiving signal. - * @fown contains the file owner information. - * @sig is the signal that will be sent. When 0, kernel sends SIGIO. - * Return 0 if permission is granted. - * @file_receive: - * This hook allows security modules to control the ability of a process - * to receive an open file descriptor via socket IPC. - * @file contains the file structure being received. - * Return 0 if permission is granted. - * @file_truncate: - * Check permission before truncating a file, i.e. using ftruncate. - * Note that truncation permission may also be checked based on the path, - * using the @path_truncate hook. - * @file contains the file structure for the file. - * Return 0 if permission is granted. - * @file_open: - * Save open-time permission checking state for later use upon - * file_permission, and recheck access if anything has changed - * since inode_permission. - * Return 0 if permission is granted. - * - * Security hooks for task operations. - * - * @task_alloc: - * @task task being allocated. - * @clone_flags contains the flags indicating what should be shared. - * Handle allocation of task-related resources. - * Returns a zero on success, negative values on failure. - * @task_free: - * @task task about to be freed. - * Handle release of task-related resources. (Note that this can be called - * from interrupt context.) - * @cred_alloc_blank: - * @cred points to the credentials. - * @gfp indicates the atomicity of any memory allocations. - * Only allocate sufficient memory and attach to @cred such that - * cred_transfer() will not get ENOMEM. - * Return 0 on success, negative values on failure. - * @cred_free: - * @cred points to the credentials. - * Deallocate and clear the cred->security field in a set of credentials. - * @cred_prepare: - * @new points to the new credentials. - * @old points to the original credentials. - * @gfp indicates the atomicity of any memory allocations. - * Prepare a new set of credentials by copying the data from the old set. - * Return 0 on success, negative values on failure. - * @cred_transfer: - * @new points to the new credentials. - * @old points to the original credentials. - * Transfer data from original creds to new creds - * @cred_getsecid: - * Retrieve the security identifier of the cred structure @c - * @c contains the credentials, secid will be placed into @secid. - * In case of failure, @secid will be set to zero. - * @kernel_act_as: - * Set the credentials for a kernel service to act as (subjective context). - * @new points to the credentials to be modified. - * @secid specifies the security ID to be set. - * The current task must be the one that nominated @secid. - * Return 0 if successful. - * @kernel_create_files_as: - * Set the file creation context in a set of credentials to be the same as - * the objective context of the specified inode. - * @new points to the credentials to be modified. - * @inode points to the inode to use as a reference. - * The current task must be the one that nominated @inode. - * Return 0 if successful. - * @kernel_module_request: - * Ability to trigger the kernel to automatically upcall to userspace for - * userspace to load a kernel module with the given name. - * @kmod_name name of the module requested by the kernel. - * Return 0 if successful. - * @kernel_load_data: - * Load data provided by userspace. - * @id kernel load data identifier. - * @contents if a subsequent @kernel_post_load_data will be called. - * Return 0 if permission is granted. - * @kernel_post_load_data: - * Load data provided by a non-file source (usually userspace buffer). - * @buf pointer to buffer containing the data contents. - * @size length of the data contents. - * @id kernel load data identifier. - * @description a text description of what was loaded, @id-specific. - * Return 0 if permission is granted. - * This must be paired with a prior @kernel_load_data call that had - * @contents set to true. - * @kernel_read_file: - * Read a file specified by userspace. - * @file contains the file structure pointing to the file being read - * by the kernel. - * @id kernel read file identifier. - * @contents if a subsequent @kernel_post_read_file will be called. - * Return 0 if permission is granted. - * @kernel_post_read_file: - * Read a file specified by userspace. - * @file contains the file structure pointing to the file being read - * by the kernel. - * @buf pointer to buffer containing the file contents. - * @size length of the file contents. - * @id kernel read file identifier. - * This must be paired with a prior @kernel_read_file call that had - * @contents set to true. - * Return 0 if permission is granted. - * @task_fix_setuid: - * Update the module's state after setting one or more of the user - * identity attributes of the current process. The @flags parameter - * indicates which of the set*uid system calls invoked this hook. If - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaced. - * @flags contains one of the LSM_SETID_* values. - * Return 0 on success. - * @task_fix_setgid: - * Update the module's state after setting one or more of the group - * identity attributes of the current process. The @flags parameter - * indicates which of the set*gid system calls invoked this hook. - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaced. - * @flags contains one of the LSM_SETID_* values. - * Return 0 on success. - * @task_fix_setgroups: - * Update the module's state after setting the supplementary group - * identity attributes of the current process. - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaced. - * Return 0 on success. - * @task_setpgid: - * Check permission before setting the process group identifier of the - * process @p to @pgid. - * @p contains the task_struct for process being modified. - * @pgid contains the new pgid. - * Return 0 if permission is granted. - * @task_getpgid: - * Check permission before getting the process group identifier of the - * process @p. - * @p contains the task_struct for the process. - * Return 0 if permission is granted. - * @task_getsid: - * Check permission before getting the session identifier of the process - * @p. - * @p contains the task_struct for the process. - * Return 0 if permission is granted. - * @current_getsecid_subj: - * Retrieve the subjective security identifier of the current task and - * return it in @secid. - * In case of failure, @secid will be set to zero. - * @task_getsecid_obj: - * Retrieve the objective security identifier of the task_struct in @p - * and return it in @secid. - * In case of failure, @secid will be set to zero. - * - * @task_setnice: - * Check permission before setting the nice value of @p to @nice. - * @p contains the task_struct of process. - * @nice contains the new nice value. - * Return 0 if permission is granted. - * @task_setioprio: - * Check permission before setting the ioprio value of @p to @ioprio. - * @p contains the task_struct of process. - * @ioprio contains the new ioprio value. - * Return 0 if permission is granted. - * @task_getioprio: - * Check permission before getting the ioprio value of @p. - * @p contains the task_struct of process. - * Return 0 if permission is granted. - * @task_prlimit: - * Check permission before getting and/or setting the resource limits of - * another task. - * @cred points to the cred structure for the current task. - * @tcred points to the cred structure for the target task. - * @flags contains the LSM_PRLIMIT_* flag bits indicating whether the - * resource limits are being read, modified, or both. - * Return 0 if permission is granted. - * @task_setrlimit: - * Check permission before setting the resource limits of process @p - * for @resource to @new_rlim. The old resource limit values can - * be examined by dereferencing (p->signal->rlim + resource). - * @p points to the task_struct for the target task's group leader. - * @resource contains the resource whose limit is being set. - * @new_rlim contains the new limits for @resource. - * Return 0 if permission is granted. - * @task_setscheduler: - * Check permission before setting scheduling policy and/or parameters of - * process @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_getscheduler: - * Check permission before obtaining scheduling information for process - * @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_movememory: - * Check permission before moving memory owned by process @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_kill: - * Check permission before sending signal @sig to @p. @info can be NULL, - * the constant 1, or a pointer to a kernel_siginfo structure. If @info is 1 or - * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming - * from the kernel and should typically be permitted. - * SIGIO signals are handled separately by the send_sigiotask hook in - * file_security_ops. - * @p contains the task_struct for process. - * @info contains the signal information. - * @sig contains the signal value. - * @cred contains the cred of the process where the signal originated, or - * NULL if the current task is the originator. - * Return 0 if permission is granted. - * @task_prctl: - * Check permission before performing a process control operation on the - * current process. - * @option contains the operation. - * @arg2 contains a argument. - * @arg3 contains a argument. - * @arg4 contains a argument. - * @arg5 contains a argument. - * Return -ENOSYS if no-one wanted to handle this op, any other value to - * cause prctl() to return immediately with that value. - * @task_to_inode: - * Set the security attributes for an inode based on an associated task's - * security attributes, e.g. for /proc/pid inodes. - * @p contains the task_struct for the task. - * @inode contains the inode structure for the inode. - * @userns_create: - * Check permission prior to creating a new user namespace. - * @cred points to prepared creds. - * Return 0 if successful, otherwise < 0 error code. - * - * Security hooks for Netlink messaging. - * - * @netlink_send: - * Save security information for a netlink message so that permission - * checking can be performed when the message is processed. The security - * information can be saved using the eff_cap field of the - * netlink_skb_parms structure. Also may be used to provide fine - * grained control over message transmission. - * @sk associated sock of task sending the message. - * @skb contains the sk_buff structure for the netlink message. - * Return 0 if the information was successfully saved and message - * is allowed to be transmitted. - * - * Security hooks for Unix domain networking. - * - * @unix_stream_connect: - * Check permissions before establishing a Unix domain stream connection - * between @sock and @other. - * @sock contains the sock structure. - * @other contains the peer sock structure. - * @newsk contains the new sock structure. - * Return 0 if permission is granted. - * @unix_may_send: - * Check permissions before connecting or sending datagrams from @sock to - * @other. - * @sock contains the socket structure. - * @other contains the peer socket structure. - * Return 0 if permission is granted. - * - * The @unix_stream_connect and @unix_may_send hooks were necessary because - * Linux provides an alternative to the conventional file name space for Unix - * domain sockets. Whereas binding and connecting to sockets in the file name - * space is mediated by the typical file permissions (and caught by the mknod - * and permission hooks in inode_security_ops), binding and connecting to - * sockets in the abstract name space is completely unmediated. Sufficient - * control of Unix domain sockets in the abstract name space isn't possible - * using only the socket layer hooks, since we need to know the actual target - * socket, which is not looked up until we are inside the af_unix code. - * - * Security hooks for socket operations. - * - * @socket_create: - * Check permissions prior to creating a new socket. - * @family contains the requested protocol family. - * @type contains the requested communications type. - * @protocol contains the requested protocol. - * @kern set to 1 if a kernel socket. - * Return 0 if permission is granted. - * @socket_post_create: - * This hook allows a module to update or allocate a per-socket security - * structure. Note that the security field was not added directly to the - * socket structure, but rather, the socket security information is stored - * in the associated inode. Typically, the inode alloc_security hook will - * allocate and attach security information to - * SOCK_INODE(sock)->i_security. This hook may be used to update the - * SOCK_INODE(sock)->i_security field with additional information that - * wasn't available when the inode was allocated. - * @sock contains the newly created socket structure. - * @family contains the requested protocol family. - * @type contains the requested communications type. - * @protocol contains the requested protocol. - * @kern set to 1 if a kernel socket. - * Return 0 if permission is granted. - * @socket_socketpair: - * Check permissions before creating a fresh pair of sockets. - * @socka contains the first socket structure. - * @sockb contains the second socket structure. - * Return 0 if permission is granted and the connection was established. - * @socket_bind: - * Check permission before socket protocol layer bind operation is - * performed and the socket @sock is bound to the address specified in the - * @address parameter. - * @sock contains the socket structure. - * @address contains the address to bind to. - * @addrlen contains the length of address. - * Return 0 if permission is granted. - * @socket_connect: - * Check permission before socket protocol layer connect operation - * attempts to connect socket @sock to a remote address, @address. - * @sock contains the socket structure. - * @address contains the address of remote endpoint. - * @addrlen contains the length of address. - * Return 0 if permission is granted. - * @socket_listen: - * Check permission before socket protocol layer listen operation. - * @sock contains the socket structure. - * @backlog contains the maximum length for the pending connection queue. - * Return 0 if permission is granted. - * @socket_accept: - * Check permission before accepting a new connection. Note that the new - * socket, @newsock, has been created and some information copied to it, - * but the accept operation has not actually been performed. - * @sock contains the listening socket structure. - * @newsock contains the newly created server socket for connection. - * Return 0 if permission is granted. - * @socket_sendmsg: - * Check permission before transmitting a message to another socket. - * @sock contains the socket structure. - * @msg contains the message to be transmitted. - * @size contains the size of message. - * Return 0 if permission is granted. - * @socket_recvmsg: - * Check permission before receiving a message from a socket. - * @sock contains the socket structure. - * @msg contains the message structure. - * @size contains the size of message structure. - * @flags contains the operational flags. - * Return 0 if permission is granted. - * @socket_getsockname: - * Check permission before the local address (name) of the socket object - * @sock is retrieved. - * @sock contains the socket structure. - * Return 0 if permission is granted. - * @socket_getpeername: - * Check permission before the remote address (name) of a socket object - * @sock is retrieved. - * @sock contains the socket structure. - * Return 0 if permission is granted. - * @socket_getsockopt: - * Check permissions before retrieving the options associated with socket - * @sock. - * @sock contains the socket structure. - * @level contains the protocol level to retrieve option from. - * @optname contains the name of option to retrieve. - * Return 0 if permission is granted. - * @socket_setsockopt: - * Check permissions before setting the options associated with socket - * @sock. - * @sock contains the socket structure. - * @level contains the protocol level to set options for. - * @optname contains the name of the option to set. - * Return 0 if permission is granted. - * @socket_shutdown: - * Checks permission before all or part of a connection on the socket - * @sock is shut down. - * @sock contains the socket structure. - * @how contains the flag indicating how future sends and receives - * are handled. - * Return 0 if permission is granted. - * @socket_sock_rcv_skb: - * Check permissions on incoming network packets. This hook is distinct - * from Netfilter's IP input hooks since it is the first time that the - * incoming sk_buff @skb has been associated with a particular socket, @sk. - * Must not sleep inside this hook because some callers hold spinlocks. - * @sk contains the sock (not socket) associated with the incoming sk_buff. - * @skb contains the incoming network data. - * Return 0 if permission is granted. - * @socket_getpeersec_stream: - * This hook allows the security module to provide peer socket security - * state for unix or connected tcp sockets to userspace via getsockopt - * SO_GETPEERSEC. For tcp sockets this can be meaningful if the - * socket is associated with an ipsec SA. - * @sock is the local socket. - * @optval memory where the security state is to be copied. - * @optlen memory where the module should copy the actual length - * of the security state. - * @len as input is the maximum length to copy to userspace provided - * by the caller. - * Return 0 if all is well, otherwise, typical getsockopt return - * values. - * @socket_getpeersec_dgram: - * This hook allows the security module to provide peer socket security - * state for udp sockets on a per-packet basis to userspace via - * getsockopt SO_GETPEERSEC. The application must first have indicated - * the IP_PASSSEC option via getsockopt. It can then retrieve the - * security state returned by this hook for a packet via the SCM_SECURITY - * ancillary message type. - * @sock contains the peer socket. May be NULL. - * @skb is the sk_buff for the packet being queried. May be NULL. - * @secid pointer to store the secid of the packet. - * Return 0 on success, error on failure. - * @sk_alloc_security: - * Allocate and attach a security structure to the sk->sk_security field, - * which is used to copy security attributes between local stream sockets. - * Return 0 on success, error on failure. - * @sk_free_security: - * Deallocate security structure. - * @sk_clone_security: - * Clone/copy security structure. - * @sk_getsecid: - * Retrieve the LSM-specific secid for the sock to enable caching - * of network authorizations. - * @sock_graft: - * Sets the socket's isec sid to the sock's sid. - * @inet_conn_request: - * Sets the openreq's sid to socket's sid with MLS portion taken - * from peer sid. - * Return 0 if permission is granted. - * @inet_csk_clone: - * Sets the new child socket's sid to the openreq sid. - * @inet_conn_established: - * Sets the connection's peersid to the secmark on skb. - * @secmark_relabel_packet: - * Check if the process should be allowed to relabel packets to - * the given secid. - * Return 0 if permission is granted. - * @secmark_refcount_inc: - * Tells the LSM to increment the number of secmark labeling rules loaded. - * @secmark_refcount_dec: - * Tells the LSM to decrement the number of secmark labeling rules loaded. - * @req_classify_flow: - * Sets the flow's sid to the openreq sid. - * @tun_dev_alloc_security: - * This hook allows a module to allocate a security structure for a TUN - * device. - * @security pointer to a security structure pointer. - * Returns a zero on success, negative values on failure. - * @tun_dev_free_security: - * This hook allows a module to free the security structure for a TUN - * device. - * @security pointer to the TUN device's security structure. - * @tun_dev_create: - * Check permissions prior to creating a new TUN device. - * Return 0 if permission is granted. - * @tun_dev_attach_queue: - * Check permissions prior to attaching to a TUN device queue. - * @security pointer to the TUN device's security structure. - * Return 0 if permission is granted. - * @tun_dev_attach: - * This hook can be used by the module to update any security state - * associated with the TUN device's sock structure. - * @sk contains the existing sock structure. - * @security pointer to the TUN device's security structure. - * Return 0 if permission is granted. - * @tun_dev_open: - * This hook can be used by the module to update any security state - * associated with the TUN device's security structure. - * @security pointer to the TUN devices's security structure. - * Return 0 if permission is granted. - * - * Security hooks for SCTP - * - * @sctp_assoc_request: - * Passes the @asoc and @chunk->skb of the association INIT packet to - * the security module. - * @asoc pointer to sctp association structure. - * @skb pointer to skbuff of association packet. - * Return 0 on success, error on failure. - * @sctp_bind_connect: - * Validiate permissions required for each address associated with sock - * @sk. Depending on @optname, the addresses will be treated as either - * for a connect or bind service. The @addrlen is calculated on each - * ipv4 and ipv6 address using sizeof(struct sockaddr_in) or - * sizeof(struct sockaddr_in6). - * @sk pointer to sock structure. - * @optname name of the option to validate. - * @address list containing one or more ipv4/ipv6 addresses. - * @addrlen total length of address(s). - * Return 0 on success, error on failure. - * @sctp_sk_clone: - * 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). - * @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. - * Return 0 if permission is granted. - * - * Security hooks for Infiniband - * - * @ib_pkey_access: - * Check permission to access a pkey when modifing a QP. - * @subnet_prefix the subnet prefix of the port being used. - * @pkey the pkey to be accessed. - * @sec pointer to a security structure. - * Return 0 if permission is granted. - * @ib_endport_manage_subnet: - * Check permissions to send and receive SMPs on a end port. - * @dev_name the IB device name (i.e. mlx4_0). - * @port_num the port number. - * @sec pointer to a security structure. - * Return 0 if permission is granted. - * @ib_alloc_security: - * Allocate a security structure for Infiniband objects. - * @sec pointer to a security structure pointer. - * Returns 0 on success, non-zero on failure. - * @ib_free_security: - * Deallocate an Infiniband security structure. - * @sec contains the security structure to be freed. - * - * Security hooks for XFRM operations. - * - * @xfrm_policy_alloc_security: - * @ctxp is a pointer to the xfrm_sec_ctx being added to Security Policy - * Database used by the XFRM system. - * @sec_ctx contains the security context information being provided by - * the user-level policy update program (e.g., setkey). - * @gfp is to specify the context for the allocation. - * Allocate a security structure to the xp->security field; the security - * field is initialized to NULL when the xfrm_policy is allocated. - * Return 0 if operation was successful (memory to allocate, legal - * context). - * @xfrm_policy_clone_security: - * @old_ctx contains an existing xfrm_sec_ctx. - * @new_ctxp contains a new xfrm_sec_ctx being cloned from old. - * Allocate a security structure in new_ctxp that contains the - * information from the old_ctx structure. - * Return 0 if operation was successful (memory to allocate). - * @xfrm_policy_free_security: - * @ctx contains the xfrm_sec_ctx. - * Deallocate xp->security. - * @xfrm_policy_delete_security: - * @ctx contains the xfrm_sec_ctx. - * Authorize deletion of xp->security. - * Return 0 if permission is granted. - * @xfrm_state_alloc: - * @x contains the xfrm_state being added to the Security Association - * Database by the XFRM system. - * @sec_ctx contains the security context information being provided by - * the user-level SA generation program (e.g., setkey or racoon). - * Allocate a security structure to the x->security field; the security - * field is initialized to NULL when the xfrm_state is allocated. Set the - * context to correspond to sec_ctx. Return 0 if operation was successful - * (memory to allocate, legal context). - * @xfrm_state_alloc_acquire: - * @x contains the xfrm_state being added to the Security Association - * Database by the XFRM system. - * @polsec contains the policy's security context. - * @secid contains the secid from which to take the mls portion of the - * context. - * Allocate a security structure to the x->security field; the security - * field is initialized to NULL when the xfrm_state is allocated. Set the - * context to correspond to secid. Return 0 if operation was successful - * (memory to allocate, legal context). - * @xfrm_state_free_security: - * @x contains the xfrm_state. - * Deallocate x->security. - * @xfrm_state_delete_security: - * @x contains the xfrm_state. - * Authorize deletion of x->security. - * Return 0 if permission is granted. - * @xfrm_policy_lookup: - * @ctx contains the xfrm_sec_ctx for which the access control is being - * checked. - * @fl_secid contains the flow security label that is used to authorize - * access to the policy xp. - * @dir contains the direction of the flow (input or output). - * Check permission when a flow selects a xfrm_policy for processing - * XFRMs on a packet. The hook is called when selecting either a - * per-socket policy or a generic xfrm policy. - * Return 0 if permission is granted, -ESRCH otherwise, or -errno - * on other errors. - * @xfrm_state_pol_flow_match: - * @x contains the state to match. - * @xp contains the policy to check for a match. - * @flic contains the flowi_common struct to check for a match. - * Return 1 if there is a match. - * @xfrm_decode_session: - * @skb points to skb to decode. - * @secid points to the flow key secid to set. - * @ckall says if all xfrms used should be checked for same secid. - * Return 0 if ckall is zero or all xfrms used have the same secid. - * - * Security hooks affecting all Key Management operations - * - * @key_alloc: - * Permit allocation of a key and assign security data. Note that key does - * not have a serial number assigned at this point. - * @key points to the key. - * @flags is the allocation flags. - * Return 0 if permission is granted, -ve error otherwise. - * @key_free: - * Notification of destruction; free security data. - * @key points to the key. - * No return value. - * @key_permission: - * See whether a specific operational right is granted to a process on a - * key. - * @key_ref refers to the key (key pointer + possession attribute bit). - * @cred points to the credentials to provide the context against which to - * evaluate the security data on the key. - * @perm describes the combination of permissions required of this key. - * Return 0 if permission is granted, -ve error otherwise. - * @key_getsecurity: - * Get a textual representation of the security context attached to a key - * for the purposes of honouring KEYCTL_GETSECURITY. This function - * allocates the storage for the NUL-terminated string and the caller - * should free it. - * @key points to the key to be queried. - * @_buffer points to a pointer that should be set to point to the - * resulting string (if no label or an error occurs). - * Return the length of the string (including terminating NUL) or -ve if - * an error. - * May also return 0 (and a NULL buffer pointer) if there is no label. - * - * Security hooks affecting all System V IPC operations. - * - * @ipc_permission: - * Check permissions for access to IPC - * @ipcp contains the kernel IPC permission structure. - * @flag contains the desired (requested) permission set. - * Return 0 if permission is granted. - * @ipc_getsecid: - * Get the secid associated with the ipc object. - * @ipcp contains the kernel IPC permission structure. - * @secid contains a pointer to the location where result will be saved. - * In case of failure, @secid will be set to zero. - * - * Security hooks for individual messages held in System V IPC message queues - * - * @msg_msg_alloc_security: - * Allocate and attach a security structure to the msg->security field. - * The security field is initialized to NULL when the structure is first - * created. - * @msg contains the message structure to be modified. - * Return 0 if operation was successful and permission is granted. - * @msg_msg_free_security: - * Deallocate the security structure for this message. - * @msg contains the message structure to be modified. - * - * Security hooks for System V IPC Message Queues - * - * @msg_queue_alloc_security: - * Allocate and attach a security structure to the - * @perm->security field. The security field is initialized to - * NULL when the structure is first created. - * @perm contains the IPC permissions of the message queue. - * Return 0 if operation was successful and permission is granted. - * @msg_queue_free_security: - * Deallocate security field @perm->security for the message queue. - * @perm contains the IPC permissions of the message queue. - * @msg_queue_associate: - * Check permission when a message queue is requested through the - * msgget system call. This hook is only called when returning the - * message queue identifier for an existing message queue, not when a - * new message queue is created. - * @perm contains the IPC permissions of the message queue. - * @msqflg contains the operation control flags. - * Return 0 if permission is granted. - * @msg_queue_msgctl: - * Check permission when a message control operation specified by @cmd - * is to be performed on the message queue with permissions @perm. - * The @perm may be NULL, e.g. for IPC_INFO or MSG_INFO. - * @perm contains the IPC permissions of the msg queue. May be NULL. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @msg_queue_msgsnd: - * Check permission before a message, @msg, is enqueued on the message - * queue with permissions @perm. - * @perm contains the IPC permissions of the message queue. - * @msg contains the message to be enqueued. - * @msqflg contains operational flags. - * Return 0 if permission is granted. - * @msg_queue_msgrcv: - * Check permission before a message, @msg, is removed from the message - * queue. The @target task structure contains a pointer to the - * process that will be receiving the message (not equal to the current - * process when inline receives are being performed). - * @perm contains the IPC permissions of the message queue. - * @msg contains the message destination. - * @target contains the task structure for recipient process. - * @type contains the type of message requested. - * @mode contains the operational flags. - * Return 0 if permission is granted. - * - * Security hooks for System V Shared Memory Segments - * - * @shm_alloc_security: - * Allocate and attach a security structure to the @perm->security - * field. The security field is initialized to NULL when the structure is - * first created. - * @perm contains the IPC permissions of the shared memory structure. - * Return 0 if operation was successful and permission is granted. - * @shm_free_security: - * Deallocate the security structure @perm->security for the memory segment. - * @perm contains the IPC permissions of the shared memory structure. - * @shm_associate: - * Check permission when a shared memory region is requested through the - * shmget system call. This hook is only called when returning the shared - * memory region identifier for an existing region, not when a new shared - * memory region is created. - * @perm contains the IPC permissions of the shared memory structure. - * @shmflg contains the operation control flags. - * Return 0 if permission is granted. - * @shm_shmctl: - * Check permission when a shared memory control operation specified by - * @cmd is to be performed on the shared memory region with permissions @perm. - * The @perm may be NULL, e.g. for IPC_INFO or SHM_INFO. - * @perm contains the IPC permissions of the shared memory structure. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @shm_shmat: - * Check permissions prior to allowing the shmat system call to attach the - * shared memory segment with permissions @perm to the data segment of the - * calling process. The attaching address is specified by @shmaddr. - * @perm contains the IPC permissions of the shared memory structure. - * @shmaddr contains the address to attach memory region to. - * @shmflg contains the operational flags. - * Return 0 if permission is granted. - * - * Security hooks for System V Semaphores - * - * @sem_alloc_security: - * Allocate and attach a security structure to the @perm->security - * field. The security field is initialized to NULL when the structure is - * first created. - * @perm contains the IPC permissions of the semaphore. - * Return 0 if operation was successful and permission is granted. - * @sem_free_security: - * Deallocate security structure @perm->security for the semaphore. - * @perm contains the IPC permissions of the semaphore. - * @sem_associate: - * Check permission when a semaphore is requested through the semget - * system call. This hook is only called when returning the semaphore - * identifier for an existing semaphore, not when a new one must be - * created. - * @perm contains the IPC permissions of the semaphore. - * @semflg contains the operation control flags. - * Return 0 if permission is granted. - * @sem_semctl: - * Check permission when a semaphore operation specified by @cmd is to be - * performed on the semaphore. The @perm may be NULL, e.g. for - * IPC_INFO or SEM_INFO. - * @perm contains the IPC permissions of the semaphore. May be NULL. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @sem_semop: - * Check permissions before performing operations on members of the - * semaphore set. If the @alter flag is nonzero, the semaphore set - * may be modified. - * @perm contains the IPC permissions of the semaphore. - * @sops contains the operations to perform. - * @nsops contains the number of operations to perform. - * @alter contains the flag indicating whether changes are to be made. - * Return 0 if permission is granted. - * - * @binder_set_context_mgr: - * Check whether @mgr is allowed to be the binder context manager. - * @mgr contains the struct cred for the current binder process. - * Return 0 if permission is granted. - * @binder_transaction: - * Check whether @from is allowed to invoke a binder transaction call - * to @to. - * @from contains the struct cred for the sending process. - * @to contains the struct cred for the receiving process. - * Return 0 if permission is granted. - * @binder_transfer_binder: - * Check whether @from is allowed to transfer a binder reference to @to. - * @from contains the struct cred for the sending process. - * @to contains the struct cred for the receiving process. - * Return 0 if permission is granted. - * @binder_transfer_file: - * Check whether @from is allowed to transfer @file to @to. - * @from contains the struct cred for the sending process. - * @file contains the struct file being transferred. - * @to contains the struct cred for the receiving process. - * Return 0 if permission is granted. - * - * @ptrace_access_check: - * Check permission before allowing the current process to trace the - * @child process. - * Security modules may also want to perform a process tracing check - * during an execve in the set_security or apply_creds hooks of - * tracing check during an execve in the bprm_set_creds hook of - * binprm_security_ops if the process is being traced and its security - * attributes would be changed by the execve. - * @child contains the task_struct structure for the target process. - * @mode contains the PTRACE_MODE flags indicating the form of access. - * Return 0 if permission is granted. - * @ptrace_traceme: - * Check that the @parent process has sufficient permission to trace the - * current process before allowing the current process to present itself - * to the @parent process for tracing. - * @parent contains the task_struct structure for debugger process. - * Return 0 if permission is granted. - * @capget: - * Get the @effective, @inheritable, and @permitted capability sets for - * the @target process. The hook may also perform permission checking to - * determine if the current process is allowed to see the capability sets - * of the @target process. - * @target contains the task_struct structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 if the capability sets were successfully obtained. - * @capset: - * Set the @effective, @inheritable, and @permitted capability sets for - * the current process. - * @new contains the new credentials structure for target process. - * @old contains the current credentials structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 and update @new if permission is granted. - * @capable: - * Check whether the @tsk process has the @cap capability in the indicated - * credentials. - * @cred contains the credentials to use. - * @ns contains the user namespace we want the capability in. - * @cap contains the capability <include/linux/capability.h>. - * @opts contains options for the capable check <include/linux/security.h>. - * Return 0 if the capability is granted for @tsk. - * @quotactl: - * Check whether the quotactl syscall is allowed for this @sb. - * Return 0 if permission is granted. - * @quota_on: - * Check whether QUOTAON is allowed for this @dentry. - * Return 0 if permission is granted. - * @syslog: - * Check permission before accessing the kernel message ring or changing - * logging to the console. - * See the syslog(2) manual page for an explanation of the @type values. - * @type contains the SYSLOG_ACTION_* constant from - * <include/linux/syslog.h>. - * Return 0 if permission is granted. - * @settime: - * Check permission to change the system time. - * struct timespec64 is defined in <include/linux/time64.h> and timezone - * is defined in <include/linux/time.h> - * @ts contains new time. - * @tz contains new timezone. - * Return 0 if permission is granted. - * @vm_enough_memory: - * Check permissions for allocating a new virtual mapping. - * @mm contains the mm struct it is being added to. - * @pages contains the number of pages. - * Return 0 if permission is granted by the LSM infrastructure to the - * caller. If all LSMs return a positive value, __vm_enough_memory() will - * be called with cap_sys_admin set. If at least one LSM returns 0 or - * negative, __vm_enough_memory() will be called with cap_sys_admin - * cleared. - * - * @ismaclabel: - * Check if the extended attribute specified by @name - * represents a MAC label. Returns 1 if name is a MAC - * attribute otherwise returns 0. - * @name full extended attribute name to check against - * LSM as a MAC label. - * - * @secid_to_secctx: - * Convert secid to security context. If secdata is NULL the length of - * the result will be returned in seclen, but no secdata will be returned. - * This does mean that the length could change between calls to check the - * length and the next call which actually allocates and returns the - * secdata. - * @secid contains the security ID. - * @secdata contains the pointer that stores the converted security - * context. - * @seclen pointer which contains the length of the data. - * Return 0 on success, error on failure. - * @secctx_to_secid: - * Convert security context to secid. - * @secid contains the pointer to the generated security ID. - * @secdata contains the security context. - * Return 0 on success, error on failure. - * - * @release_secctx: - * Release the security context. - * @secdata contains the security context. - * @seclen contains the length of the security context. - * - * Security hooks for Audit - * - * @audit_rule_init: - * Allocate and initialize an LSM audit rule structure. - * @field contains the required Audit action. - * Fields flags are defined in <include/linux/audit.h> - * @op contains the operator the rule uses. - * @rulestr contains the context where the rule will be applied to. - * @lsmrule contains a pointer to receive the result. - * Return 0 if @lsmrule has been successfully set, - * -EINVAL in case of an invalid rule. - * - * @audit_rule_known: - * Specifies whether given @krule contains any fields related to - * current LSM. - * @krule contains the audit rule of interest. - * Return 1 in case of relation found, 0 otherwise. - * - * @audit_rule_match: - * Determine if given @secid matches a rule previously approved - * by @audit_rule_known. - * @secid contains the security id in question. - * @field contains the field which relates to current LSM. - * @op contains the operator that will be used for matching. - * @lrule points to the audit rule that will be checked against. - * Return 1 if secid matches the rule, 0 if it does not, -ERRNO on failure. - * - * @audit_rule_free: - * Deallocate the LSM audit rule structure previously allocated by - * audit_rule_init. - * @lsmrule contains the allocated rule. - * - * @inode_invalidate_secctx: - * Notify the security module that it must revalidate the security context - * of an inode. - * - * @inode_notifysecctx: - * Notify the security module of what the security context of an inode - * should be. Initializes the incore security context managed by the - * security module for this inode. Example usage: NFS client invokes - * this hook to initialize the security context in its incore inode to the - * value provided by the server for the file when the server returned the - * file's attributes to the client. - * Must be called with inode->i_mutex locked. - * @inode we wish to set the security context of. - * @ctx contains the string which we wish to set in the inode. - * @ctxlen contains the length of @ctx. - * Return 0 on success, error on failure. - * - * @inode_setsecctx: - * Change the security context of an inode. Updates the - * incore security context managed by the security module and invokes the - * fs code as needed (via __vfs_setxattr_noperm) to update any backing - * xattrs that represent the context. Example usage: NFS server invokes - * this hook to change the security context in its incore inode and on the - * backing filesystem to a value provided by the client on a SETATTR - * operation. - * Must be called with inode->i_mutex locked. - * @dentry contains the inode we wish to set the security context of. - * @ctx contains the string which we wish to set in the inode. - * @ctxlen contains the length of @ctx. - * Return 0 on success, error on failure. - * - * @inode_getsecctx: - * On success, returns 0 and fills out @ctx and @ctxlen with the security - * context for the given @inode. - * @inode we wish to get the security context of. - * @ctx is a pointer in which to place the allocated security context. - * @ctxlen points to the place to put the length of @ctx. - * Return 0 on success, error on failure. - * - * Security hooks for the general notification queue: - * - * @post_notification: - * Check to see if a watch notification can be posted to a particular - * queue. - * @w_cred: The credentials of the whoever set the watch. - * @cred: The event-triggerer's credentials. - * @n: The notification being posted. - * Return 0 if permission is granted. - * - * @watch_key: - * Check to see if a process is allowed to watch for event notifications - * from a key or keyring. - * @key: The key to watch. - * Return 0 if permission is granted. - * - * Security hooks for using the eBPF maps and programs functionalities through - * eBPF syscalls. - * - * @bpf: - * Do a initial check for all bpf syscalls after the attribute is copied - * into the kernel. The actual security module can implement their own - * rules to check the specific cmd they need. - * Return 0 if permission is granted. - * - * @bpf_map: - * Do a check when the kernel generate and return a file descriptor for - * eBPF maps. - * @map: bpf map that we want to access. - * @mask: the access flags. - * Return 0 if permission is granted. - * - * @bpf_prog: - * Do a check when the kernel generate and return a file descriptor for - * eBPF programs. - * @prog: bpf prog that userspace want to use. - * Return 0 if permission is granted. - * - * @bpf_map_alloc_security: - * Initialize the security field inside bpf map. - * Return 0 on success, error on failure. - * - * @bpf_map_free_security: - * Clean up the security information stored inside bpf map. - * - * @bpf_prog_alloc_security: - * Initialize the security field inside bpf program. - * Return 0 on success, error on failure. - * - * @bpf_prog_free_security: - * Clean up the security information stored inside bpf prog. - * - * @locked_down: - * Determine whether a kernel feature that potentially enables arbitrary - * code execution in kernel space should be permitted. - * @what: kernel feature being accessed. - * Return 0 if permission is granted. - * - * Security hooks for perf events - * - * @perf_event_open: - * Check whether the @type of perf_event_open syscall is allowed. - * Return 0 if permission is granted. - * @perf_event_alloc: - * Allocate and save perf_event security info. - * Return 0 on success, error on failure. - * @perf_event_free: - * Release (free) perf_event security info. - * @perf_event_read: - * Read perf_event security info if allowed. - * Return 0 if permission is granted. - * @perf_event_write: - * Write perf_event security info if allowed. - * Return 0 if permission is granted. - * - * Security hooks for io_uring - * - * @uring_override_creds: - * Check if the current task, executing an io_uring operation, is allowed - * to override it's credentials with @new. - * @new: the new creds to use. - * Return 0 if permission is granted. - * - * @uring_sqpoll: - * Check whether the current task is allowed to spawn a io_uring polling - * thread (IORING_SETUP_SQPOLL). - * Return 0 if permission is granted. - * - * @uring_cmd: - * Check whether the file_operations uring_cmd is allowed to run. - * Return 0 if permission is granted. - * - */ union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); #include "lsm_hook_defs.h" @@ -1716,6 +92,7 @@ extern void security_add_hooks(struct security_hook_list *hooks, int count, enum lsm_order { LSM_ORDER_FIRST = -1, /* This is only for capabilities. */ LSM_ORDER_MUTABLE = 0, + LSM_ORDER_LAST = 1, /* This is only for integrity. */ }; struct lsm_info { @@ -1740,36 +117,6 @@ extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; __used __section(".early_lsm_info.init") \ __aligned(sizeof(unsigned long)) -#ifdef CONFIG_SECURITY_SELINUX_DISABLE -/* - * Assuring the safety of deleting a security module is up to - * the security module involved. This may entail ordering the - * module's hook list in a particular way, refusing to disable - * the module once a policy is loaded or any number of other - * actions better imagined than described. - * - * The name of the configuration option reflects the only module - * that currently uses the mechanism. Any developer who thinks - * disabling their module is a good idea needs to be at least as - * careful as the SELinux team. - */ -static inline void security_delete_hooks(struct security_hook_list *hooks, - int count) -{ - int i; - - for (i = 0; i < count; i++) - hlist_del_rcu(&hooks[i].list); -} -#endif /* CONFIG_SECURITY_SELINUX_DISABLE */ - -/* Currently required to handle SELinux runtime hook disable. */ -#ifdef CONFIG_SECURITY_WRITABLE_HOOKS -#define __lsm_ro_after_init -#else -#define __lsm_ro_after_init __ro_after_init -#endif /* CONFIG_SECURITY_WRITABLE_HOOKS */ - extern int lsm_inode_alloc(struct inode *inode); #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/include/linux/mailbox/zynqmp-ipi-message.h b/include/linux/mailbox/zynqmp-ipi-message.h index 35ce84c8ca02..31d8046d945e 100644 --- a/include/linux/mailbox/zynqmp-ipi-message.h +++ b/include/linux/mailbox/zynqmp-ipi-message.h @@ -9,7 +9,7 @@ * @data: message payload * * This is the structure for data used in mbox_send_message - * the maximum length of data buffer is fixed to 12 bytes. + * the maximum length of data buffer is fixed to 32 bytes. * Client is supposed to be aware of this. */ struct zynqmp_ipi_message { diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h index 65229a45590f..734694912ef7 100644 --- a/include/linux/mailbox_client.h +++ b/include/linux/mailbox_client.h @@ -37,6 +37,7 @@ struct mbox_client { void (*tx_done)(struct mbox_client *cl, void *mssg, int r); }; +int mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl); struct mbox_chan *mbox_request_channel_byname(struct mbox_client *cl, const char *name); struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 50ad19662a32..f82ee3fac1cd 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -597,6 +597,8 @@ extern int hashdist; /* Distribute hashes across NUMA nodes? */ #endif #ifdef CONFIG_MEMTEST +extern phys_addr_t early_memtest_bad_size; /* Size of faulty ram found by memtest */ +extern bool early_memtest_done; /* Was early memtest done? */ extern void early_memtest(phys_addr_t start, phys_addr_t end); #else static inline void early_memtest(phys_addr_t start, phys_addr_t end) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b6eda2ab205d..222d7370134c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -97,6 +97,7 @@ struct shrinker_info { struct rcu_head rcu; atomic_long_t *nr_deferred; unsigned long *map; + int map_nr_max; }; struct lruvec_stats_percpu { @@ -1037,7 +1038,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); -void mem_cgroup_flush_stats_delayed(void); +void mem_cgroup_flush_stats_atomic(void); +void mem_cgroup_flush_stats_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1535,7 +1537,11 @@ static inline void mem_cgroup_flush_stats(void) { } -static inline void mem_cgroup_flush_stats_delayed(void) +static inline void mem_cgroup_flush_stats_atomic(void) +{ +} + +static inline void mem_cgroup_flush_stats_ratelimited(void) { } diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 4f1600413f91..e7abf6fa4c52 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -5,9 +5,9 @@ #include <linux/file.h> #ifdef CONFIG_MEMFD_CREATE -extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg); +extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); #else -static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned long a) +static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { return -EINVAL; } diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 2058194807bd..beb3f44f85c5 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -21,6 +21,7 @@ enum axp20x_variants { AXP806_ID, AXP809_ID, AXP813_ID, + AXP15060_ID, NR_AXP20X_VARIANTS, }; @@ -131,6 +132,39 @@ enum axp20x_variants { /* Other DCDC regulator control registers are the same as AXP803 */ #define AXP813_DCDC7_V_OUT 0x26 +#define AXP15060_STARTUP_SRC 0x00 +#define AXP15060_PWR_OUT_CTRL1 0x10 +#define AXP15060_PWR_OUT_CTRL2 0x11 +#define AXP15060_PWR_OUT_CTRL3 0x12 +#define AXP15060_DCDC1_V_CTRL 0x13 +#define AXP15060_DCDC2_V_CTRL 0x14 +#define AXP15060_DCDC3_V_CTRL 0x15 +#define AXP15060_DCDC4_V_CTRL 0x16 +#define AXP15060_DCDC5_V_CTRL 0x17 +#define AXP15060_DCDC6_V_CTRL 0x18 +#define AXP15060_ALDO1_V_CTRL 0x19 +#define AXP15060_DCDC_MODE_CTRL1 0x1a +#define AXP15060_DCDC_MODE_CTRL2 0x1b +#define AXP15060_OUTPUT_MONITOR_DISCHARGE 0x1e +#define AXP15060_IRQ_PWROK_VOFF 0x1f +#define AXP15060_ALDO2_V_CTRL 0x20 +#define AXP15060_ALDO3_V_CTRL 0x21 +#define AXP15060_ALDO4_V_CTRL 0x22 +#define AXP15060_ALDO5_V_CTRL 0x23 +#define AXP15060_BLDO1_V_CTRL 0x24 +#define AXP15060_BLDO2_V_CTRL 0x25 +#define AXP15060_BLDO3_V_CTRL 0x26 +#define AXP15060_BLDO4_V_CTRL 0x27 +#define AXP15060_BLDO5_V_CTRL 0x28 +#define AXP15060_CLDO1_V_CTRL 0x29 +#define AXP15060_CLDO2_V_CTRL 0x2a +#define AXP15060_CLDO3_V_CTRL 0x2b +#define AXP15060_CLDO4_V_CTRL 0x2d +#define AXP15060_CPUSLDO_V_CTRL 0x2e +#define AXP15060_PWR_WAKEUP_CTRL 0x31 +#define AXP15060_PWR_DISABLE_DOWN_SEQ 0x32 +#define AXP15060_PEK_KEY 0x36 + /* Interrupt */ #define AXP152_IRQ1_EN 0x40 #define AXP152_IRQ2_EN 0x41 @@ -152,6 +186,11 @@ enum axp20x_variants { #define AXP20X_IRQ5_STATE 0x4c #define AXP20X_IRQ6_STATE 0x4d +#define AXP15060_IRQ1_EN 0x40 +#define AXP15060_IRQ2_EN 0x41 +#define AXP15060_IRQ1_STATE 0x48 +#define AXP15060_IRQ2_STATE 0x49 + /* ADC */ #define AXP20X_ACIN_V_ADC_H 0x56 #define AXP20X_ACIN_V_ADC_L 0x57 @@ -222,6 +261,8 @@ enum axp20x_variants { #define AXP22X_GPIO_STATE 0x94 #define AXP22X_GPIO_PULL_DOWN 0x95 +#define AXP15060_CLDO4_GPIO2_MODESET 0x2c + /* Battery */ #define AXP20X_CHRG_CC_31_24 0xb0 #define AXP20X_CHRG_CC_23_16 0xb1 @@ -419,6 +460,33 @@ enum { AXP813_REG_ID_MAX, }; +enum { + AXP15060_DCDC1 = 0, + AXP15060_DCDC2, + AXP15060_DCDC3, + AXP15060_DCDC4, + AXP15060_DCDC5, + AXP15060_DCDC6, + AXP15060_ALDO1, + AXP15060_ALDO2, + AXP15060_ALDO3, + AXP15060_ALDO4, + AXP15060_ALDO5, + AXP15060_BLDO1, + AXP15060_BLDO2, + AXP15060_BLDO3, + AXP15060_BLDO4, + AXP15060_BLDO5, + AXP15060_CLDO1, + AXP15060_CLDO2, + AXP15060_CLDO3, + AXP15060_CLDO4, + AXP15060_CPUSLDO, + AXP15060_SW, + AXP15060_RTC_LDO, + AXP15060_REG_ID_MAX, +}; + /* IRQs */ enum { AXP152_IRQ_LDO0IN_CONNECT = 1, @@ -637,6 +705,23 @@ enum axp809_irqs { AXP809_IRQ_GPIO0_INPUT, }; +enum axp15060_irqs { + AXP15060_IRQ_DIE_TEMP_HIGH_LV1 = 1, + AXP15060_IRQ_DIE_TEMP_HIGH_LV2, + AXP15060_IRQ_DCDC1_V_LOW, + AXP15060_IRQ_DCDC2_V_LOW, + AXP15060_IRQ_DCDC3_V_LOW, + AXP15060_IRQ_DCDC4_V_LOW, + AXP15060_IRQ_DCDC5_V_LOW, + AXP15060_IRQ_DCDC6_V_LOW, + AXP15060_IRQ_PEK_LONG, + AXP15060_IRQ_PEK_SHORT, + AXP15060_IRQ_GPIO1_INPUT, + AXP15060_IRQ_PEK_FAL_EDGE, + AXP15060_IRQ_PEK_RIS_EDGE, + AXP15060_IRQ_GPIO2_INPUT, +}; + struct axp20x_dev { struct device *dev; int irq; diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 14ca7b471576..47e7a3a61ce6 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -68,9 +68,6 @@ struct mfd_cell { int id; int level; - int (*enable)(struct platform_device *dev); - int (*disable)(struct platform_device *dev); - int (*suspend)(struct platform_device *dev); int (*resume)(struct platform_device *dev); @@ -78,6 +75,9 @@ struct mfd_cell { void *platform_data; size_t pdata_size; + /* Matches ACPI */ + const struct mfd_cell_acpi_match *acpi_match; + /* Software node for the device. */ const struct software_node *swnode; @@ -97,9 +97,6 @@ struct mfd_cell { /* Set to 'true' to use 'of_reg' (above) - allows for of_reg=0 */ bool use_of_reg; - /* Matches ACPI */ - const struct mfd_cell_acpi_match *acpi_match; - /* * These resources can be specified relative to the parent device. * For accessing hardware you should use resources from the platform dev @@ -119,20 +116,11 @@ struct mfd_cell { /* A list of regulator supplies that should be mapped to the MFD * device rather than the child device when requested */ - const char * const *parent_supplies; int num_parent_supplies; + const char * const *parent_supplies; }; /* - * Convenience functions for clients using shared cells. Refcounting - * happens automatically, with the cell's enable/disable callbacks - * being called only when a device is first being enabled or no other - * clients are making use of it. - */ -extern int mfd_cell_enable(struct platform_device *pdev); -extern int mfd_cell_disable(struct platform_device *pdev); - -/* * Given a platform device that's been created by mfd_add_devices(), fetch * the mfd_cell that created it. */ diff --git a/include/linux/mfd/da9063/registers.h b/include/linux/mfd/da9063/registers.h index 6e0f66a2e727..7b8364bd08a0 100644 --- a/include/linux/mfd/da9063/registers.h +++ b/include/linux/mfd/da9063/registers.h @@ -1040,6 +1040,29 @@ /* DA9063_REG_CONFIG_J (addr=0x10F) */ #define DA9063_TWOWIRE_TO 0x40 +/* DA9063_REG_MON_REG_2 (addr=0x115) */ +#define DA9063_LDO1_MON_EN 0x01 +#define DA9063_LDO2_MON_EN 0x02 +#define DA9063_LDO3_MON_EN 0x04 +#define DA9063_LDO4_MON_EN 0x08 +#define DA9063_LDO5_MON_EN 0x10 +#define DA9063_LDO6_MON_EN 0x20 +#define DA9063_LDO7_MON_EN 0x40 +#define DA9063_LDO8_MON_EN 0x80 + +/* DA9063_REG_MON_REG_3 (addr=0x116) */ +#define DA9063_LDO9_MON_EN 0x01 +#define DA9063_LDO10_MON_EN 0x02 +#define DA9063_LDO11_MON_EN 0x04 + +/* DA9063_REG_MON_REG_4 (addr=0x117) */ +#define DA9063_BCORE1_MON_EN 0x04 +#define DA9063_BCORE2_MON_EN 0x08 +#define DA9063_BPRO_MON_EN 0x10 +#define DA9063_BIO_MON_EN 0x20 +#define DA9063_BMEM_MON_EN 0x40 +#define DA9063_BPERI_MON_EN 0x80 + /* DA9063_REG_MON_REG_5 (addr=0x116) */ #define DA9063_MON_A8_IDX_MASK 0x07 #define DA9063_MON_A8_IDX_NONE 0x00 diff --git a/include/linux/mfd/max597x.h b/include/linux/mfd/max597x.h new file mode 100644 index 000000000000..a850b2e02e6a --- /dev/null +++ b/include/linux/mfd/max597x.h @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Device driver for regulators in MAX5970 and MAX5978 IC + * + * Copyright (c) 2022 9elements GmbH + * + * Author: Patrick Rudolph <patrick.rudolph@9elements.com> + */ + +#ifndef _MFD_MAX597X_H +#define _MFD_MAX597X_H + +#include <linux/regmap.h> + +#define MAX5970_NUM_SWITCHES 2 +#define MAX5978_NUM_SWITCHES 1 +#define MAX597X_NUM_LEDS 4 + +struct max597x_data { + int num_switches; + u32 irng[MAX5970_NUM_SWITCHES]; + u32 mon_rng[MAX5970_NUM_SWITCHES]; + u32 shunt_micro_ohms[MAX5970_NUM_SWITCHES]; +}; + +enum max597x_chip_type { + MAX597x_TYPE_MAX5978 = 1, + MAX597x_TYPE_MAX5970, +}; + +#define MAX5970_REG_CURRENT_L(ch) (0x01 + (ch) * 4) +#define MAX5970_REG_CURRENT_H(ch) (0x00 + (ch) * 4) +#define MAX5970_REG_VOLTAGE_L(ch) (0x03 + (ch) * 4) +#define MAX5970_REG_VOLTAGE_H(ch) (0x02 + (ch) * 4) +#define MAX5970_REG_MON_RANGE 0x18 +#define MAX5970_MON_MASK 0x3 +#define MAX5970_MON(reg, ch) (((reg) >> ((ch) * 2)) & MAX5970_MON_MASK) +#define MAX5970_MON_MAX_RANGE_UV 16000000 + +#define MAX5970_REG_CH_UV_WARN_H(ch) (0x1A + (ch) * 10) +#define MAX5970_REG_CH_UV_WARN_L(ch) (0x1B + (ch) * 10) +#define MAX5970_REG_CH_UV_CRIT_H(ch) (0x1C + (ch) * 10) +#define MAX5970_REG_CH_UV_CRIT_L(ch) (0x1D + (ch) * 10) +#define MAX5970_REG_CH_OV_WARN_H(ch) (0x1E + (ch) * 10) +#define MAX5970_REG_CH_OV_WARN_L(ch) (0x1F + (ch) * 10) +#define MAX5970_REG_CH_OV_CRIT_H(ch) (0x20 + (ch) * 10) +#define MAX5970_REG_CH_OV_CRIT_L(ch) (0x21 + (ch) * 10) + +#define MAX5970_VAL2REG_H(x) (((x) >> 2) & 0xFF) +#define MAX5970_VAL2REG_L(x) ((x) & 0x3) + +#define MAX5970_REG_DAC_FAST(ch) (0x2E + (ch)) + +#define MAX5970_FAST2SLOW_RATIO 200 + +#define MAX5970_REG_STATUS0 0x31 +#define MAX5970_CB_IFAULTF(ch) (1 << (ch)) +#define MAX5970_CB_IFAULTS(ch) (1 << ((ch) + 4)) + +#define MAX5970_REG_STATUS1 0x32 +#define STATUS1_PROT_MASK 0x3 +#define STATUS1_PROT(reg) \ + (((reg) >> 6) & STATUS1_PROT_MASK) +#define STATUS1_PROT_SHUTDOWN 0 +#define STATUS1_PROT_CLEAR_PG 1 +#define STATUS1_PROT_ALERT_ONLY 2 + +#define MAX5970_REG_STATUS2 0x33 +#define MAX5970_IRNG_MASK 0x3 +#define MAX5970_IRNG(reg, ch) \ + (((reg) >> ((ch) * 2)) & MAX5970_IRNG_MASK) + +#define MAX5970_REG_STATUS3 0x34 +#define MAX5970_STATUS3_ALERT BIT(4) +#define MAX5970_STATUS3_PG(ch) BIT(ch) + +#define MAX5970_REG_FAULT0 0x35 +#define UV_STATUS_WARN(ch) (1 << (ch)) +#define UV_STATUS_CRIT(ch) (1 << ((ch) + 4)) + +#define MAX5970_REG_FAULT1 0x36 +#define OV_STATUS_WARN(ch) (1 << (ch)) +#define OV_STATUS_CRIT(ch) (1 << ((ch) + 4)) + +#define MAX5970_REG_FAULT2 0x37 +#define OC_STATUS_WARN(ch) (1 << (ch)) + +#define MAX5970_REG_CHXEN 0x3b +#define CHXEN(ch) (3 << ((ch) * 2)) + +#define MAX5970_REG_LED_FLASH 0x43 + +#define MAX_REGISTERS 0x49 +#define ADC_MASK 0x3FF + +#endif /* _MFD_MAX597X_H */ diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 117d02708439..eda1ffd99c1a 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -128,12 +128,6 @@ struct palmas_pmic_driver_data { struct regulator_config config); }; -struct palmas_adc_wakeup_property { - int adc_channel_number; - int adc_high_threshold; - int adc_low_threshold; -}; - struct palmas_gpadc_platform_data { /* Channel 3 current source is only enabled during conversion */ int ch3_current; /* 0: off; 1: 10uA; 2: 400uA; 3: 800 uA */ @@ -152,8 +146,6 @@ struct palmas_gpadc_platform_data { int start_polarity; int auto_conversion_period_ms; - struct palmas_adc_wakeup_property *adc_wakeup1_data; - struct palmas_adc_wakeup_property *adc_wakeup2_data; }; struct palmas_reg_init { diff --git a/include/linux/mfd/rsmu.h b/include/linux/mfd/rsmu.h index 6870de608233..0379aa207428 100644 --- a/include/linux/mfd/rsmu.h +++ b/include/linux/mfd/rsmu.h @@ -8,6 +8,9 @@ #ifndef __LINUX_MFD_RSMU_H #define __LINUX_MFD_RSMU_H +#define RSMU_MAX_WRITE_COUNT (255) +#define RSMU_MAX_READ_COUNT (255) + /* The supported devices are ClockMatrix, Sabre and SnowLotus */ enum rsmu_type { RSMU_CM = 0x34000, @@ -31,6 +34,6 @@ struct rsmu_ddata { struct regmap *regmap; struct mutex lock; enum rsmu_type type; - u16 page; + u32 page; }; #endif /* __LINUX_MFD_RSMU_H */ diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h index 2d1895c3efbf..6bb432f6a96c 100644 --- a/include/linux/mfd/rt5033-private.h +++ b/include/linux/mfd/rt5033-private.h @@ -107,14 +107,13 @@ enum rt5033_reg { #define RT5033_LDO_CTRL_MASK 0x1f /* RT5033 charger property - model, manufacturer */ - #define RT5033_CHARGER_MODEL "RT5033WSC Charger" #define RT5033_MANUFACTURER "Richtek Technology Corporation" /* - * RT5033 charger fast-charge current lmits (as in CHGCTRL1 register), - * AICR mode limits the input current for example, - * the AIRC 100 mode limits the input current to 100 mA. + * While RT5033 charger can limit the fast-charge current (as in CHGCTRL1 + * register), AICR mode limits the input current. For example, the AIRC 100 + * mode limits the input current to 100 mA. */ #define RT5033_AICR_100_MODE 0x20 #define RT5033_AICR_500_MODE 0x40 @@ -139,10 +138,9 @@ enum rt5033_reg { #define RT5033_TE_ENABLE_MASK 0x08 /* - * RT5033 charger opa mode. RT50300 have two opa mode charger mode - * and boost mode for OTG + * RT5033 charger opa mode. RT5033 has two opa modes for OTG: charger mode + * and boost mode. */ - #define RT5033_CHARGER_MODE 0x00 #define RT5033_BOOST_MODE 0x01 @@ -181,18 +179,17 @@ enum rt5033_reg { * RT5033 charger pre-charge threshold volt limits * (as in CHGCTRL5 register), uV */ - #define RT5033_CHARGER_PRE_THRESHOLD_LIMIT_MIN 2300000U #define RT5033_CHARGER_PRE_THRESHOLD_STEP_NUM 100000U #define RT5033_CHARGER_PRE_THRESHOLD_LIMIT_MAX 3800000U /* - * RT5033 charger enable UUG, If UUG enable MOS auto control by H/W charger + * RT5033 charger UUG. It enables MOS auto control by H/W charger * circuit. */ #define RT5033_CHARGER_UUG_ENABLE 0x02 -/* RT5033 charger High impedance mode */ +/* RT5033 charger high impedance mode */ #define RT5033_CHARGER_HZ_DISABLE 0x00 #define RT5033_CHARGER_HZ_ENABLE 0x01 diff --git a/include/linux/mfd/rt5033.h b/include/linux/mfd/rt5033.h index 3c23b6220c04..8f306ac15a27 100644 --- a/include/linux/mfd/rt5033.h +++ b/include/linux/mfd/rt5033.h @@ -49,10 +49,9 @@ struct rt5033_charger_data { }; struct rt5033_charger { - struct device *dev; - struct rt5033_dev *rt5033; - struct power_supply psy; - + struct device *dev; + struct rt5033_dev *rt5033; + struct power_supply psy; struct rt5033_charger_data *chg; }; diff --git a/include/linux/mfd/rz-mtu3.h b/include/linux/mfd/rz-mtu3.h new file mode 100644 index 000000000000..c5173bc06270 --- /dev/null +++ b/include/linux/mfd/rz-mtu3.h @@ -0,0 +1,257 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Renesas Electronics Corporation + */ +#ifndef __MFD_RZ_MTU3_H__ +#define __MFD_RZ_MTU3_H__ + +#include <linux/clk.h> +#include <linux/device.h> +#include <linux/mutex.h> + +/* 8-bit shared register offsets macros */ +#define RZ_MTU3_TSTRA 0x080 /* Timer start register A */ +#define RZ_MTU3_TSTRB 0x880 /* Timer start register B */ + +/* 16-bit shared register offset macros */ +#define RZ_MTU3_TDDRA 0x016 /* Timer dead time data register A */ +#define RZ_MTU3_TDDRB 0x816 /* Timer dead time data register B */ +#define RZ_MTU3_TCDRA 0x014 /* Timer cycle data register A */ +#define RZ_MTU3_TCDRB 0x814 /* Timer cycle data register B */ +#define RZ_MTU3_TCBRA 0x022 /* Timer cycle buffer register A */ +#define RZ_MTU3_TCBRB 0x822 /* Timer cycle buffer register B */ +#define RZ_MTU3_TCNTSA 0x020 /* Timer subcounter A */ +#define RZ_MTU3_TCNTSB 0x820 /* Timer subcounter B */ + +/* + * MTU5 contains 3 timer counter registers and is totaly different + * from other channels, so we must separate its offset + */ + +/* 8-bit register offset macros of MTU3 channels except MTU5 */ +#define RZ_MTU3_TIER 0 /* Timer interrupt register */ +#define RZ_MTU3_NFCR 1 /* Noise filter control register */ +#define RZ_MTU3_TSR 2 /* Timer status register */ +#define RZ_MTU3_TCR 3 /* Timer control register */ +#define RZ_MTU3_TCR2 4 /* Timer control register 2 */ + +/* Timer mode register 1 */ +#define RZ_MTU3_TMDR1 5 +#define RZ_MTU3_TMDR1_MD GENMASK(3, 0) +#define RZ_MTU3_TMDR1_MD_NORMAL FIELD_PREP(RZ_MTU3_TMDR1_MD, 0) +#define RZ_MTU3_TMDR1_MD_PWMMODE1 FIELD_PREP(RZ_MTU3_TMDR1_MD, 2) + +#define RZ_MTU3_TIOR 6 /* Timer I/O control register */ +#define RZ_MTU3_TIORH 6 /* Timer I/O control register H */ +#define RZ_MTU3_TIORL 7 /* Timer I/O control register L */ +/* Only MTU3/4/6/7 have TBTM registers */ +#define RZ_MTU3_TBTM 8 /* Timer buffer operation transfer mode register */ + +/* 8-bit MTU5 register offset macros */ +#define RZ_MTU3_TSTR 2 /* MTU5 Timer start register */ +#define RZ_MTU3_TCNTCMPCLR 3 /* MTU5 Timer compare match clear register */ +#define RZ_MTU3_TCRU 4 /* Timer control register U */ +#define RZ_MTU3_TCR2U 5 /* Timer control register 2U */ +#define RZ_MTU3_TIORU 6 /* Timer I/O control register U */ +#define RZ_MTU3_TCRV 7 /* Timer control register V */ +#define RZ_MTU3_TCR2V 8 /* Timer control register 2V */ +#define RZ_MTU3_TIORV 9 /* Timer I/O control register V */ +#define RZ_MTU3_TCRW 10 /* Timer control register W */ +#define RZ_MTU3_TCR2W 11 /* Timer control register 2W */ +#define RZ_MTU3_TIORW 12 /* Timer I/O control register W */ + +/* 16-bit register offset macros of MTU3 channels except MTU5 */ +#define RZ_MTU3_TCNT 0 /* Timer counter */ +#define RZ_MTU3_TGRA 1 /* Timer general register A */ +#define RZ_MTU3_TGRB 2 /* Timer general register B */ +#define RZ_MTU3_TGRC 3 /* Timer general register C */ +#define RZ_MTU3_TGRD 4 /* Timer general register D */ +#define RZ_MTU3_TGRE 5 /* Timer general register E */ +#define RZ_MTU3_TGRF 6 /* Timer general register F */ +/* Timer A/D converter start request registers */ +#define RZ_MTU3_TADCR 7 /* control register */ +#define RZ_MTU3_TADCORA 8 /* cycle set register A */ +#define RZ_MTU3_TADCORB 9 /* cycle set register B */ +#define RZ_MTU3_TADCOBRA 10 /* cycle set buffer register A */ +#define RZ_MTU3_TADCOBRB 11 /* cycle set buffer register B */ + +/* 16-bit MTU5 register offset macros */ +#define RZ_MTU3_TCNTU 0 /* MTU5 Timer counter U */ +#define RZ_MTU3_TGRU 1 /* MTU5 Timer general register U */ +#define RZ_MTU3_TCNTV 2 /* MTU5 Timer counter V */ +#define RZ_MTU3_TGRV 3 /* MTU5 Timer general register V */ +#define RZ_MTU3_TCNTW 4 /* MTU5 Timer counter W */ +#define RZ_MTU3_TGRW 5 /* MTU5 Timer general register W */ + +/* 32-bit register offset */ +#define RZ_MTU3_TCNTLW 0 /* Timer longword counter */ +#define RZ_MTU3_TGRALW 1 /* Timer longword general register A */ +#define RZ_MTU3_TGRBLW 2 /* Timer longowrd general register B */ + +#define RZ_MTU3_TMDR3 0x191 /* MTU1 Timer Mode Register 3 */ + +/* Macros for setting registers */ +#define RZ_MTU3_TCR_CCLR GENMASK(7, 5) +#define RZ_MTU3_TCR_CKEG GENMASK(4, 3) +#define RZ_MTU3_TCR_TPCS GENMASK(2, 0) +#define RZ_MTU3_TCR_CCLR_TGRA BIT(5) +#define RZ_MTU3_TCR_CCLR_TGRC FIELD_PREP(RZ_MTU3_TCR_CCLR, 5) +#define RZ_MTU3_TCR_CKEG_RISING FIELD_PREP(RZ_MTU3_TCR_CKEG, 0) + +#define RZ_MTU3_TIOR_IOB GENMASK(7, 4) +#define RZ_MTU3_TIOR_IOA GENMASK(3, 0) +#define RZ_MTU3_TIOR_OC_RETAIN 0 +#define RZ_MTU3_TIOR_OC_INIT_OUT_LO_HI_OUT 2 +#define RZ_MTU3_TIOR_OC_INIT_OUT_HI_TOGGLE_OUT 7 + +#define RZ_MTU3_TIOR_OC_IOA_H_COMP_MATCH \ + FIELD_PREP(RZ_MTU3_TIOR_IOA, RZ_MTU3_TIOR_OC_INIT_OUT_LO_HI_OUT) +#define RZ_MTU3_TIOR_OC_IOB_TOGGLE \ + FIELD_PREP(RZ_MTU3_TIOR_IOB, RZ_MTU3_TIOR_OC_INIT_OUT_HI_TOGGLE_OUT) + +enum rz_mtu3_channels { + RZ_MTU3_CHAN_0, + RZ_MTU3_CHAN_1, + RZ_MTU3_CHAN_2, + RZ_MTU3_CHAN_3, + RZ_MTU3_CHAN_4, + RZ_MTU3_CHAN_5, + RZ_MTU3_CHAN_6, + RZ_MTU3_CHAN_7, + RZ_MTU3_CHAN_8, + RZ_MTU_NUM_CHANNELS +}; + +/** + * struct rz_mtu3_channel - MTU3 channel private data + * + * @dev: device handle + * @channel_number: channel number + * @lock: Lock to protect channel state + * @is_busy: channel state + */ +struct rz_mtu3_channel { + struct device *dev; + unsigned int channel_number; + struct mutex lock; + bool is_busy; +}; + +/** + * struct rz_mtu3 - MTU3 core private data + * + * @clk: MTU3 module clock + * @rz_mtu3_channel: HW channels + * @priv_data: MTU3 core driver private data + */ +struct rz_mtu3 { + struct clk *clk; + struct rz_mtu3_channel channels[RZ_MTU_NUM_CHANNELS]; + + void *priv_data; +}; + +#if IS_ENABLED(CONFIG_RZ_MTU3) +static inline bool rz_mtu3_request_channel(struct rz_mtu3_channel *ch) +{ + mutex_lock(&ch->lock); + if (ch->is_busy) { + mutex_unlock(&ch->lock); + return false; + } + + ch->is_busy = true; + mutex_unlock(&ch->lock); + + return true; +} + +static inline void rz_mtu3_release_channel(struct rz_mtu3_channel *ch) +{ + mutex_lock(&ch->lock); + ch->is_busy = false; + mutex_unlock(&ch->lock); +} + +bool rz_mtu3_is_enabled(struct rz_mtu3_channel *ch); +void rz_mtu3_disable(struct rz_mtu3_channel *ch); +int rz_mtu3_enable(struct rz_mtu3_channel *ch); + +u8 rz_mtu3_8bit_ch_read(struct rz_mtu3_channel *ch, u16 off); +u16 rz_mtu3_16bit_ch_read(struct rz_mtu3_channel *ch, u16 off); +u32 rz_mtu3_32bit_ch_read(struct rz_mtu3_channel *ch, u16 off); +u16 rz_mtu3_shared_reg_read(struct rz_mtu3_channel *ch, u16 off); + +void rz_mtu3_8bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u8 val); +void rz_mtu3_16bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u16 val); +void rz_mtu3_32bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u32 val); +void rz_mtu3_shared_reg_write(struct rz_mtu3_channel *ch, u16 off, u16 val); +void rz_mtu3_shared_reg_update_bit(struct rz_mtu3_channel *ch, u16 off, + u16 pos, u8 val); +#else +static inline bool rz_mtu3_request_channel(struct rz_mtu3_channel *ch) +{ + return false; +} + +static inline void rz_mtu3_release_channel(struct rz_mtu3_channel *ch) +{ +} + +static inline bool rz_mtu3_is_enabled(struct rz_mtu3_channel *ch) +{ + return false; +} + +static inline void rz_mtu3_disable(struct rz_mtu3_channel *ch) +{ +} + +static inline int rz_mtu3_enable(struct rz_mtu3_channel *ch) +{ + return 0; +} + +static inline u8 rz_mtu3_8bit_ch_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline u16 rz_mtu3_16bit_ch_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline u32 rz_mtu3_32bit_ch_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline u16 rz_mtu3_shared_reg_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline void rz_mtu3_8bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u8 val) +{ +} + +static inline void rz_mtu3_16bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u16 val) +{ +} + +static inline void rz_mtu3_32bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u32 val) +{ +} + +static inline void rz_mtu3_shared_reg_write(struct rz_mtu3_channel *ch, u16 off, u16 val) +{ +} + +static inline void rz_mtu3_shared_reg_update_bit(struct rz_mtu3_channel *ch, + u16 off, u16 pos, u8 val) +{ +} +#endif + +#endif /* __MFD_RZ_MTU3_H__ */ diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index f92fe090473d..a212b9f72bc9 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -36,8 +36,6 @@ struct gpio_desc; enum sec_device_type { - S5M8751X, - S5M8763X, S5M8767X, S2MPA01, S2MPS11X, diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h index 6cfe4201a106..3fd2775eb9bb 100644 --- a/include/linux/mfd/samsung/irq.h +++ b/include/linux/mfd/samsung/irq.h @@ -194,54 +194,4 @@ enum s5m8767_irq { #define S5M8767_IRQ_RTC1S_MASK (1 << 4) #define S5M8767_IRQ_WTSR_MASK (1 << 5) -enum s5m8763_irq { - S5M8763_IRQ_DCINF, - S5M8763_IRQ_DCINR, - S5M8763_IRQ_JIGF, - S5M8763_IRQ_JIGR, - S5M8763_IRQ_PWRONF, - S5M8763_IRQ_PWRONR, - - S5M8763_IRQ_WTSREVNT, - S5M8763_IRQ_SMPLEVNT, - S5M8763_IRQ_ALARM1, - S5M8763_IRQ_ALARM0, - - S5M8763_IRQ_ONKEY1S, - S5M8763_IRQ_TOPOFFR, - S5M8763_IRQ_DCINOVPR, - S5M8763_IRQ_CHGRSTF, - S5M8763_IRQ_DONER, - S5M8763_IRQ_CHGFAULT, - - S5M8763_IRQ_LOBAT1, - S5M8763_IRQ_LOBAT2, - - S5M8763_IRQ_NR, -}; - -#define S5M8763_IRQ_DCINF_MASK (1 << 2) -#define S5M8763_IRQ_DCINR_MASK (1 << 3) -#define S5M8763_IRQ_JIGF_MASK (1 << 4) -#define S5M8763_IRQ_JIGR_MASK (1 << 5) -#define S5M8763_IRQ_PWRONF_MASK (1 << 6) -#define S5M8763_IRQ_PWRONR_MASK (1 << 7) - -#define S5M8763_IRQ_WTSREVNT_MASK (1 << 0) -#define S5M8763_IRQ_SMPLEVNT_MASK (1 << 1) -#define S5M8763_IRQ_ALARM1_MASK (1 << 2) -#define S5M8763_IRQ_ALARM0_MASK (1 << 3) - -#define S5M8763_IRQ_ONKEY1S_MASK (1 << 0) -#define S5M8763_IRQ_TOPOFFR_MASK (1 << 2) -#define S5M8763_IRQ_DCINOVPR_MASK (1 << 3) -#define S5M8763_IRQ_CHGRSTF_MASK (1 << 4) -#define S5M8763_IRQ_DONER_MASK (1 << 5) -#define S5M8763_IRQ_CHGFAULT_MASK (1 << 7) - -#define S5M8763_IRQ_LOBAT1_MASK (1 << 0) -#define S5M8763_IRQ_LOBAT2_MASK (1 << 1) - -#define S5M8763_ENRAMP (1 << 4) - #endif /* __LINUX_MFD_SEC_IRQ_H */ diff --git a/include/linux/mfd/samsung/s5m8763.h b/include/linux/mfd/samsung/s5m8763.h deleted file mode 100644 index c534f086ca16..000000000000 --- a/include/linux/mfd/samsung/s5m8763.h +++ /dev/null @@ -1,90 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * Copyright (c) 2011 Samsung Electronics Co., Ltd - * http://www.samsung.com - */ - -#ifndef __LINUX_MFD_S5M8763_H -#define __LINUX_MFD_S5M8763_H - -/* S5M8763 registers */ -enum s5m8763_reg { - S5M8763_REG_IRQ1, - S5M8763_REG_IRQ2, - S5M8763_REG_IRQ3, - S5M8763_REG_IRQ4, - S5M8763_REG_IRQM1, - S5M8763_REG_IRQM2, - S5M8763_REG_IRQM3, - S5M8763_REG_IRQM4, - S5M8763_REG_STATUS1, - S5M8763_REG_STATUS2, - S5M8763_REG_STATUSM1, - S5M8763_REG_STATUSM2, - S5M8763_REG_CHGR1, - S5M8763_REG_CHGR2, - S5M8763_REG_LDO_ACTIVE_DISCHARGE1, - S5M8763_REG_LDO_ACTIVE_DISCHARGE2, - S5M8763_REG_BUCK_ACTIVE_DISCHARGE3, - S5M8763_REG_ONOFF1, - S5M8763_REG_ONOFF2, - S5M8763_REG_ONOFF3, - S5M8763_REG_ONOFF4, - S5M8763_REG_BUCK1_VOLTAGE1, - S5M8763_REG_BUCK1_VOLTAGE2, - S5M8763_REG_BUCK1_VOLTAGE3, - S5M8763_REG_BUCK1_VOLTAGE4, - S5M8763_REG_BUCK2_VOLTAGE1, - S5M8763_REG_BUCK2_VOLTAGE2, - S5M8763_REG_BUCK3, - S5M8763_REG_BUCK4, - S5M8763_REG_LDO1_LDO2, - S5M8763_REG_LDO3, - S5M8763_REG_LDO4, - S5M8763_REG_LDO5, - S5M8763_REG_LDO6, - S5M8763_REG_LDO7, - S5M8763_REG_LDO7_LDO8, - S5M8763_REG_LDO9_LDO10, - S5M8763_REG_LDO11, - S5M8763_REG_LDO12, - S5M8763_REG_LDO13, - S5M8763_REG_LDO14, - S5M8763_REG_LDO15, - S5M8763_REG_LDO16, - S5M8763_REG_BKCHR, - S5M8763_REG_LBCNFG1, - S5M8763_REG_LBCNFG2, -}; - -/* S5M8763 regulator ids */ -enum s5m8763_regulators { - S5M8763_LDO1, - S5M8763_LDO2, - S5M8763_LDO3, - S5M8763_LDO4, - S5M8763_LDO5, - S5M8763_LDO6, - S5M8763_LDO7, - S5M8763_LDO8, - S5M8763_LDO9, - S5M8763_LDO10, - S5M8763_LDO11, - S5M8763_LDO12, - S5M8763_LDO13, - S5M8763_LDO14, - S5M8763_LDO15, - S5M8763_LDO16, - S5M8763_BUCK1, - S5M8763_BUCK2, - S5M8763_BUCK3, - S5M8763_BUCK4, - S5M8763_AP_EN32KHZ, - S5M8763_CP_EN32KHZ, - S5M8763_ENCHGVI, - S5M8763_ESAFEUSB1, - S5M8763_ESAFEUSB2, -}; - -#define S5M8763_ENRAMP (1 << 4) -#endif /* __LINUX_MFD_S5M8763_H */ diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index 5f5c43fd69dd..1b94325febb3 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -31,6 +31,7 @@ #define TIM_BDTR 0x44 /* Break and Dead-Time Reg */ #define TIM_DCR 0x48 /* DMA control register */ #define TIM_DMAR 0x4C /* DMA register for transfer */ +#define TIM_TISEL 0x68 /* Input Selection */ #define TIM_CR1_CEN BIT(0) /* Counter Enable */ #define TIM_CR1_DIR BIT(4) /* Counter Direction */ diff --git a/include/linux/mfd/ucb1x00.h b/include/linux/mfd/ucb1x00.h index 43bcf35afe27..ede237384723 100644 --- a/include/linux/mfd/ucb1x00.h +++ b/include/linux/mfd/ucb1x00.h @@ -10,6 +10,7 @@ #include <linux/device.h> #include <linux/mfd/mcp.h> #include <linux/gpio.h> +#include <linux/gpio/driver.h> #include <linux/mutex.h> #define UCB_IO_DATA 0x00 diff --git a/include/linux/mhi.h b/include/linux/mhi.h index a5441ad33c74..f6de4b6ecfc7 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -766,13 +766,6 @@ int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev); void mhi_unprepare_from_transfer(struct mhi_device *mhi_dev); /** - * mhi_poll - Poll for any available data in DL direction - * @mhi_dev: Device associated with the channels - * @budget: # of events to process - */ -int mhi_poll(struct mhi_device *mhi_dev, u32 budget); - -/** * mhi_queue_dma - Send or receive DMA mapped buffers from client device * over MHI channel * @mhi_dev: Device associated with the channels diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 71b06ebad402..c0af74efd3cb 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -36,6 +36,7 @@ #include <linux/types.h> #include <rdma/ib_verbs.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/bitfield.h> #if defined(__LITTLE_ENDIAN) #define MLX5_SET_HOST_ENDIANNESS 0 @@ -442,6 +443,8 @@ enum { MLX5_OPCODE_UMR = 0x25, + MLX5_OPCODE_FLOW_TBL_ACCESS = 0x2c, + MLX5_OPCODE_ACCESS_ASO = 0x2d, }; @@ -980,14 +983,23 @@ enum { }; enum { - CQE_RSS_HTYPE_IP = 0x3 << 2, + CQE_RSS_HTYPE_IP = GENMASK(3, 2), /* cqe->rss_hash_type[3:2] - IP destination selected for hash * (00 = none, 01 = IPv4, 10 = IPv6, 11 = Reserved) */ - CQE_RSS_HTYPE_L4 = 0x3 << 6, + CQE_RSS_IP_NONE = 0x0, + CQE_RSS_IPV4 = 0x1, + CQE_RSS_IPV6 = 0x2, + CQE_RSS_RESERVED = 0x3, + + CQE_RSS_HTYPE_L4 = GENMASK(7, 6), /* cqe->rss_hash_type[7:6] - L4 destination selected for hash * (00 = none, 01 = TCP. 10 = UDP, 11 = IPSEC.SPI */ + CQE_RSS_L4_NONE = 0x0, + CQE_RSS_L4_TCP = 0x1, + CQE_RSS_L4_UDP = 0x2, + CQE_RSS_L4_IPSEC = 0x3, }; enum { @@ -1357,6 +1369,12 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW_INGRESS_ACL_MAX(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_ingress.cap) +#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \ + MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap) + +#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2_MAX(mdev, cap) \ + MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, ft_field_support_2_esw_fdb.cap) + #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f33389b42209..4b9626cd83e4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -134,6 +134,7 @@ enum { MLX5_REG_PCAM = 0x507f, MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, + MLX5_REG_MTMP = 0x900A, MLX5_REG_MCIA = 0x9014, MLX5_REG_MFRL = 0x9028, MLX5_REG_MLCR = 0x902b, @@ -438,6 +439,7 @@ struct mlx5_core_health { struct work_struct report_work; struct devlink_health_reporter *fw_reporter; struct devlink_health_reporter *fw_fatal_reporter; + struct devlink_health_reporter *vnic_reporter; struct delayed_work update_fw_log_ts_work; }; @@ -731,6 +733,7 @@ struct mlx5_fw_tracer; struct mlx5_vxlan; struct mlx5_geneve; struct mlx5_hv_vhca; +struct mlx5_thermal; #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity)) #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) @@ -749,6 +752,7 @@ enum { struct mlx5_profile { u64 mask; u8 log_max_qp; + u8 num_cmd_caches; struct { int size; int limit; @@ -808,6 +812,7 @@ struct mlx5_core_dev { struct mlx5_rsc_dump *rsc_dump; u32 vsc_addr; struct mlx5_hv_vhca *hv_vhca; + struct mlx5_thermal *thermal; }; struct mlx5_db { @@ -1088,6 +1093,7 @@ void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn, int npsvs, u32 *sig_index); int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); +__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); @@ -1211,11 +1217,6 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } -static inline bool mlx5_core_is_management_pf(const struct mlx5_core_dev *dev) -{ - return MLX5_CAP_GEN(dev, num_ports) == 1 && !MLX5_CAP_GEN(dev, native_port_num); -} - static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; @@ -1237,6 +1238,18 @@ static inline u16 mlx5_core_max_vfs(const struct mlx5_core_dev *dev) return dev->priv.sriov.max_vfs; } +static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) +{ + /* LACP owner conditions: + * 1) Function is physical. + * 2) LAG is supported by FW. + * 3) LAG is managed by driver (currently the only option). + */ + return MLX5_CAP_GEN(dev, vport_group_manager) && + (MLX5_CAP_GEN(dev, num_lag_ports) > 1) && + MLX5_CAP_GEN(dev, lag_master); +} + static inline int mlx5_get_gid_table_len(u16 param) { if (param > 4) { @@ -1308,4 +1321,10 @@ enum { MLX5_OCTWORD = 16, }; +struct msi_map mlx5_msix_alloc(struct mlx5_core_dev *dev, + irqreturn_t (*handler)(int, void *), + const struct irq_affinity_desc *affdesc, + const char *name); +void mlx5_msix_free(struct mlx5_core_dev *dev, struct msi_map map); + #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 66d76e97a087..b89778d0d326 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -69,7 +69,7 @@ enum { MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, MLX5_SET_HCA_CAP_OP_MOD_ROCE = 0x4, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2 = 0x20, - MLX5_SET_HCA_CAP_OP_MODE_PORT_SELECTION = 0x25, + MLX5_SET_HCA_CAP_OP_MOD_PORT_SELECTION = 0x25, }; enum { @@ -78,12 +78,15 @@ enum { enum { MLX5_OBJ_TYPE_SW_ICM = 0x0008, + MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT = 0x23, }; enum { MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11), MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13), + MLX5_GENERAL_OBJ_TYPES_CAP_HEADER_MODIFY_ARGUMENT = + (1ULL << MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT), MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39), }; @@ -321,6 +324,10 @@ enum { MLX5_FT_NIC_TX_RDMA_2_NIC_TX = BIT(1), }; +enum { + MLX5_CMD_OP_MOD_UPDATE_HEADER_MODIFY_ARGUMENT = 0x1, +}; + struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_dmac[0x1]; u8 outer_smac[0x1]; @@ -404,10 +411,13 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 metadata_reg_c_0[0x1]; }; +/* Table 2170 - Flow Table Fields Supported 2 Format */ struct mlx5_ifc_flow_table_fields_supported_2_bits { u8 reserved_at_0[0xe]; u8 bth_opcode[0x1]; - u8 reserved_at_f[0x11]; + u8 reserved_at_f[0x1]; + u8 tunnel_header_0_1[0x1]; + u8 reserved_at_11[0xf]; u8 reserved_at_20[0x60]; }; @@ -453,9 +463,11 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 max_ft_level[0x8]; u8 reformat_add_esp_trasport[0x1]; - u8 reserved_at_41[0x2]; + u8 reformat_l2_to_l3_esp_tunnel[0x1]; + u8 reserved_at_42[0x1]; u8 reformat_del_esp_trasport[0x1]; - u8 reserved_at_44[0x2]; + u8 reformat_l3_esp_tunnel_to_l2[0x1]; + u8 reserved_at_45[0x1]; u8 execute_aso[0x1]; u8 reserved_at_47[0x19]; @@ -877,7 +889,12 @@ enum { struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 fdb_to_vport_reg_c_id[0x8]; - u8 reserved_at_8[0xd]; + u8 reserved_at_8[0x5]; + u8 fdb_uplink_hairpin[0x1]; + u8 fdb_multi_path_any_table_limit_regc[0x1]; + u8 reserved_at_f[0x3]; + u8 fdb_multi_path_any_table[0x1]; + u8 reserved_at_13[0x2]; u8 fdb_modify_header_fwd_to_table[0x1]; u8 fdb_ipv4_ttl_modify[0x1]; u8 flow_source[0x1]; @@ -895,7 +912,13 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress; - u8 reserved_at_800[0x1000]; + u8 reserved_at_800[0xC00]; + + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_esw_fdb; + + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_bitmask_support_2_esw_fdb; + + u8 reserved_at_1500[0x300]; u8 sw_steering_fdb_action_drop_icm_address_rx[0x40]; @@ -1077,7 +1100,9 @@ struct mlx5_ifc_roce_cap_bits { u8 sw_r_roce_src_udp_port[0x1]; u8 fl_rc_qp_when_roce_disabled[0x1]; u8 fl_rc_qp_when_roce_enabled[0x1]; - u8 reserved_at_7[0x17]; + u8 reserved_at_7[0x1]; + u8 qp_ooo_transmit_default[0x1]; + u8 reserved_at_9[0x15]; u8 qp_ts_format[0x2]; u8 reserved_at_20[0x60]; @@ -1493,7 +1518,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_b0[0x1]; u8 uplink_follow[0x1]; u8 ts_cqe_to_dest_cqn[0x1]; - u8 reserved_at_b3[0x7]; + u8 reserved_at_b3[0x6]; + u8 go_back_n[0x1]; u8 shampo[0x1]; u8 reserved_at_bb[0x5]; @@ -1508,7 +1534,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_eq_sz[0x8]; u8 relaxed_ordering_write[0x1]; - u8 relaxed_ordering_read[0x1]; + u8 relaxed_ordering_read_pci_enabled[0x1]; u8 log_max_mkey[0x6]; u8 reserved_at_f0[0x6]; u8 terminate_scatter_list_mkey[0x1]; @@ -1679,7 +1705,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 rc[0x1]; u8 uar_4k[0x1]; - u8 reserved_at_241[0x9]; + u8 reserved_at_241[0x7]; + u8 fl_rc_qp_when_roce_disabled[0x1]; + u8 regexp_params[0x1]; u8 uar_sz[0x6]; u8 port_selection_cap[0x1]; u8 reserved_at_248[0x1]; @@ -1724,9 +1752,12 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_320[0x3]; u8 log_max_transport_domain[0x5]; - u8 reserved_at_328[0x3]; + u8 reserved_at_328[0x2]; + u8 relaxed_ordering_read[0x1]; u8 log_max_pd[0x5]; - u8 reserved_at_330[0xb]; + u8 reserved_at_330[0x9]; + u8 q_counter_aggregation[0x1]; + u8 q_counter_other_vport[0x1]; u8 log_max_xrcd[0x5]; u8 nic_receive_steering_discard[0x1]; @@ -1913,7 +1944,14 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_750[0x4]; u8 max_dynamic_vf_msix_table_size[0xc]; - u8 reserved_at_760[0x20]; + u8 reserved_at_760[0x3]; + u8 log_max_num_header_modify_argument[0x5]; + u8 reserved_at_768[0x4]; + u8 log_header_modify_argument_granularity[0x4]; + u8 reserved_at_770[0x3]; + u8 log_header_modify_argument_max_alloc[0x5]; + u8 reserved_at_778[0x8]; + u8 vhca_tunnel_commands[0x40]; u8 match_definer_format_supported[0x40]; }; @@ -3261,7 +3299,8 @@ struct mlx5_ifc_qpc_bits { u8 log_rq_stride[0x3]; u8 no_sq[0x1]; u8 log_sq_size[0x4]; - u8 reserved_at_55[0x3]; + u8 reserved_at_55[0x1]; + u8 retry_mode[0x2]; u8 ts_format[0x2]; u8 reserved_at_5a[0x1]; u8 rlky[0x1]; @@ -5599,10 +5638,15 @@ struct mlx5_ifc_query_q_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x80]; + u8 other_vport[0x1]; + u8 reserved_at_41[0xf]; + u8 vport_number[0x10]; + + u8 reserved_at_60[0x60]; u8 clear[0x1]; - u8 reserved_at_c1[0x1f]; + u8 aggregate[0x1]; + u8 reserved_at_c2[0x1e]; u8 reserved_at_e0[0x18]; u8 counter_set_id[0x8]; @@ -6347,6 +6391,18 @@ struct mlx5_ifc_general_obj_out_cmd_hdr_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_modify_header_arg_bits { + u8 reserved_at_0[0x80]; + + u8 reserved_at_80[0x8]; + u8 access_pd[0x18]; +}; + +struct mlx5_ifc_create_modify_header_arg_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_modify_header_arg_bits arg; +}; + struct mlx5_ifc_create_match_definer_in_bits { struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; @@ -6590,7 +6646,9 @@ enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3, MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4 = 0x5, + MLX5_REFORMAT_TYPE_L2_TO_L3_ESP_TUNNEL = 0x6, MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT = 0x8, + MLX5_REFORMAT_TYPE_L3_ESP_TUNNEL_TO_L2 = 0x9, MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6 = 0xb, MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, @@ -9271,7 +9329,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x38]; + u8 reserved_at_40[0x33]; + u8 flow_counter_bulk_log_size[0x5]; u8 flow_counter_bulk[0x8]; }; @@ -10869,6 +10928,31 @@ struct mlx5_ifc_mrtc_reg_bits { u8 time_l[0x20]; }; +struct mlx5_ifc_mtmp_reg_bits { + u8 reserved_at_0[0x14]; + u8 sensor_index[0xc]; + + u8 reserved_at_20[0x10]; + u8 temperature[0x10]; + + u8 mte[0x1]; + u8 mtr[0x1]; + u8 reserved_at_42[0xe]; + u8 max_temperature[0x10]; + + u8 tee[0x2]; + u8 reserved_at_62[0xe]; + u8 temp_threshold_hi[0x10]; + + u8 reserved_at_80[0x10]; + u8 temp_threshold_lo[0x10]; + + u8 reserved_at_a0[0x20]; + + u8 sensor_name_hi[0x20]; + u8 sensor_name_lo[0x20]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -10931,6 +11015,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mfrl_reg_bits mfrl_reg; struct mlx5_ifc_mtutc_reg_bits mtutc_reg; struct mlx5_ifc_mrtc_reg_bits mrtc_reg; + struct mlx5_ifc_mtmp_reg_bits mtmp_reg; u8 reserved_at_0[0x60e0]; }; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index e96ee1e348cb..98b2e1e149f9 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -141,6 +141,12 @@ enum mlx5_ptys_width { MLX5_PTYS_WIDTH_12X = 1 << 4, }; +struct mlx5_port_eth_proto { + u32 cap; + u32 admin; + u32 oper; +}; + #define MLX5E_PROT_MASK(link_mode) (1U << link_mode) #define MLX5_GET_ETH_PROTO(reg, out, ext, field) \ (ext ? MLX5_GET(reg, out, ext_##field) : \ @@ -218,4 +224,14 @@ int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state); int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state); int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio); int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio); + +int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, + struct mlx5_port_eth_proto *eproto); +bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev); +u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper, + bool force_legacy); +u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed, + bool force_legacy); +int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); + #endif /* __MLX5_PORT_H__ */ diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index df55fbb65717..bd53cf4be7bd 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -499,6 +499,16 @@ struct mlx5_stride_block_ctrl_seg { __be16 num_entries; }; +struct mlx5_wqe_flow_update_ctrl_seg { + __be32 flow_idx_update; + __be32 dest_handle; + u8 reserved0[40]; +}; + +struct mlx5_wqe_header_modify_argument_update_seg { + u8 argument_list[64]; +}; + struct mlx5_core_qp { struct mlx5_core_rsc_common common; /* must be first */ void (*event) (struct mlx5_core_qp *, int); diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f79667824eb..27ce77080c79 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -29,6 +29,7 @@ #include <linux/pgtable.h> #include <linux/kasan.h> #include <linux/memremap.h> +#include <linux/slab.h> struct mempolicy; struct anon_vma; @@ -38,6 +39,7 @@ struct pt_regs; extern int sysctl_page_lock_unfairness; +void mm_core_init(void); void init_mm_internals(void); #ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ @@ -96,17 +98,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #include <asm/page.h> #include <asm/processor.h> -/* - * Architectures that support memory tagging (assigning tags to memory regions, - * embedding these tags into addresses that point to these memory regions, and - * checking that the memory and the pointer tags match on memory accesses) - * redefine this macro to strip tags from pointers. - * It's defined as noop for architectures that don't support memory tagging. - */ -#ifndef untagged_addr -#define untagged_addr(addr) (addr) -#endif - #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif @@ -256,6 +247,8 @@ void setup_initial_init_mm(void *start_code, void *end_code, struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); +/* Use only if VMA has no other users */ +void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; @@ -478,7 +471,8 @@ static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ - { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } + { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ + { FAULT_FLAG_VMA_LOCK, "VMA_LOCK" } /* * vm_fault is filled by the pagefault handler and passed to the vma's @@ -623,6 +617,131 @@ struct vm_operations_struct { unsigned long addr); }; +#ifdef CONFIG_NUMA_BALANCING +static inline void vma_numab_state_init(struct vm_area_struct *vma) +{ + vma->numab_state = NULL; +} +static inline void vma_numab_state_free(struct vm_area_struct *vma) +{ + kfree(vma->numab_state); +} +#else +static inline void vma_numab_state_init(struct vm_area_struct *vma) {} +static inline void vma_numab_state_free(struct vm_area_struct *vma) {} +#endif /* CONFIG_NUMA_BALANCING */ + +#ifdef CONFIG_PER_VMA_LOCK +/* + * Try to read-lock a vma. The function is allowed to occasionally yield false + * locked result to avoid performance overhead, in which case we fall back to + * using mmap_lock. The function should never yield false unlocked result. + */ +static inline bool vma_start_read(struct vm_area_struct *vma) +{ + /* Check before locking. A race might cause false locked result. */ + if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq)) + return false; + + if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) + return false; + + /* + * Overflow might produce false locked result. + * False unlocked result is impossible because we modify and check + * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq + * modification invalidates all existing locks. + */ + if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) { + up_read(&vma->vm_lock->lock); + return false; + } + return true; +} + +static inline void vma_end_read(struct vm_area_struct *vma) +{ + rcu_read_lock(); /* keeps vma alive till the end of up_read */ + up_read(&vma->vm_lock->lock); + rcu_read_unlock(); +} + +static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) +{ + mmap_assert_write_locked(vma->vm_mm); + + /* + * current task is holding mmap_write_lock, both vma->vm_lock_seq and + * mm->mm_lock_seq can't be concurrently modified. + */ + *mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq); + return (vma->vm_lock_seq == *mm_lock_seq); +} + +static inline void vma_start_write(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + if (__is_vma_write_locked(vma, &mm_lock_seq)) + return; + + down_write(&vma->vm_lock->lock); + vma->vm_lock_seq = mm_lock_seq; + up_write(&vma->vm_lock->lock); +} + +static inline bool vma_try_start_write(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + if (__is_vma_write_locked(vma, &mm_lock_seq)) + return true; + + if (!down_write_trylock(&vma->vm_lock->lock)) + return false; + + vma->vm_lock_seq = mm_lock_seq; + up_write(&vma->vm_lock->lock); + return true; +} + +static inline void vma_assert_write_locked(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); +} + +static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) +{ + /* When detaching vma should be write-locked */ + if (detached) + vma_assert_write_locked(vma); + vma->detached = detached; +} + +struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, + unsigned long address); + +#else /* CONFIG_PER_VMA_LOCK */ + +static inline void vma_init_lock(struct vm_area_struct *vma) {} +static inline bool vma_start_read(struct vm_area_struct *vma) + { return false; } +static inline void vma_end_read(struct vm_area_struct *vma) {} +static inline void vma_start_write(struct vm_area_struct *vma) {} +static inline bool vma_try_start_write(struct vm_area_struct *vma) + { return true; } +static inline void vma_assert_write_locked(struct vm_area_struct *vma) {} +static inline void vma_mark_detached(struct vm_area_struct *vma, + bool detached) {} + +#endif /* CONFIG_PER_VMA_LOCK */ + +/* + * WARNING: vma_init does not initialize vma->vm_lock. + * Use vm_area_alloc()/vm_area_free() if vma needs locking. + */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; @@ -631,6 +750,8 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); + vma_mark_detached(vma, false); + vma_numab_state_init(vma); } /* Use when VMA is not part of the VMA tree and needs no locking */ @@ -644,28 +765,28 @@ static inline void vm_flags_init(struct vm_area_struct *vma, static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); vm_flags_init(vma, flags); } static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); } static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) |= flags; } static inline void vm_flags_clear(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; } @@ -686,7 +807,7 @@ static inline void __vm_flags_mod(struct vm_area_struct *vma, static inline void vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); __vm_flags_mod(vma, set, clear); } @@ -1554,6 +1675,16 @@ static inline int xchg_page_access_time(struct page *page, int time) last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS); return last_time << PAGE_ACCESS_TIME_BUCKETS; } + +static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) +{ + unsigned int pid_bit; + + pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG)); + if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) { + __set_bit(pid_bit, &vma->numab_state->access_pids[1]); + } +} #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { @@ -1603,6 +1734,10 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } + +static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) +{ +} #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) @@ -2636,12 +2771,6 @@ static inline bool ptlock_init(struct page *page) { return true; } static inline void ptlock_free(struct page *page) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ -static inline void pgtable_init(void) -{ - ptlock_cache_init(); - pgtable_cache_init(); -} - static inline bool pgtable_pte_page_ctor(struct page *page) { if (!ptlock_init(page)) @@ -2785,7 +2914,6 @@ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); extern void adjust_managed_page_count(struct page *page, long count); -extern void mem_init_print_info(void); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); @@ -2896,7 +3024,6 @@ extern void setup_per_cpu_pageset(void); extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; -extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; @@ -3185,8 +3312,6 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); -vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); @@ -3256,7 +3381,6 @@ extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -extern void __init init_mem_debugging_and_hardening(void); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); @@ -3425,6 +3549,22 @@ void vmemmap_populate_print_last(void); void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif + +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP +static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) +{ + return is_power_of_2(sizeof(struct page)) && + pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap; +} +#else +static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) +{ + return false; +} +#endif + void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); @@ -3442,8 +3582,6 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); -extern int sysctl_memory_failure_early_kill; -extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); @@ -3453,6 +3591,7 @@ extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void num_poisoned_pages_inc(unsigned long pfn); void num_poisoned_pages_sub(unsigned long pfn, long i); +struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { @@ -3473,6 +3612,12 @@ static inline void num_poisoned_pages_sub(unsigned long pfn, long i) } #endif +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_KSM) +void add_to_kill_ksm(struct task_struct *tsk, struct page *p, + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long ksm_addr); +#endif + #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); @@ -3542,14 +3687,12 @@ extern const struct attribute_group memory_failure_attr_group; extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); -extern void copy_user_huge_page(struct page *dst, struct page *src, - unsigned long addr_hint, - struct vm_area_struct *vma, - unsigned int pages_per_huge_page); -extern long copy_huge_page_from_user(struct page *dst_page, - const void __user *usr_src, - unsigned int pages_per_huge_page, - bool allow_pagefault); +int copy_user_large_folio(struct folio *dst, struct folio *src, + unsigned long addr_hint, + struct vm_area_struct *vma); +long copy_folio_from_user(struct folio *dst_folio, + const void __user *usr_src, + bool allow_pagefault); /** * vma_is_special_huge - Are transhuge page-table entries considered special? diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index de1e622dd366..0e1d239a882c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -557,6 +557,12 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(*pte)); + /* + * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole + * thing, because when zapping either it means it's dropping the + * page, or in TTU where the present pte will be quickly replaced + * with a swap pte. There's no way of leaking the bit. + */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0722859c3647..306a3d1a0fa6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -471,6 +471,16 @@ struct anon_vma_name { char name[]; }; +struct vma_lock { + struct rw_semaphore lock; +}; + +struct vma_numab_state { + unsigned long next_scan; + unsigned long next_pid_reset; + unsigned long access_pids[2]; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -480,17 +490,19 @@ struct anon_vma_name { struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ - unsigned long vm_start; /* Our start address within vm_mm. */ - unsigned long vm_end; /* The first byte after our end address - within vm_mm. */ + union { + struct { + /* VMA covers [vm_start; vm_end) addresses within mm */ + unsigned long vm_start; + unsigned long vm_end; + }; +#ifdef CONFIG_PER_VMA_LOCK + struct rcu_head vm_rcu; /* Used for deferred freeing. */ +#endif + }; struct mm_struct *vm_mm; /* The address space we belong to. */ - - /* - * Access permissions of this VMA. - * See vmf_insert_mixed_prot() for discussion. - */ - pgprot_t vm_page_prot; + pgprot_t vm_page_prot; /* Access permissions of this VMA. */ /* * Flags, see mm.h. @@ -501,6 +513,14 @@ struct vm_area_struct { vm_flags_t __private __vm_flags; }; +#ifdef CONFIG_PER_VMA_LOCK + int vm_lock_seq; + struct vma_lock *vm_lock; + + /* Flag to indicate areas detached from the mm->mm_mt tree */ + bool detached; +#endif + /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. @@ -547,9 +567,19 @@ struct vm_area_struct { #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif +#ifdef CONFIG_NUMA_BALANCING + struct vma_numab_state *numab_state; /* NUMA Balancing state */ +#endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; +#ifdef CONFIG_SCHED_MM_CID +struct mm_cid { + u64 time; + int cid; +}; +#endif + struct kioctx_table; struct mm_struct { struct { @@ -600,15 +630,19 @@ struct mm_struct { atomic_t mm_count; #ifdef CONFIG_SCHED_MM_CID /** - * @cid_lock: Protect cid bitmap updates vs lookups. + * @pcpu_cid: Per-cpu current cid. * - * Prevent situations where updates to the cid bitmap happen - * concurrently with lookups. Those can lead to situations - * where a lookup cannot find a free bit simply because it was - * unlucky enough to load, non-atomically, bitmap words as they - * were being concurrently updated by the updaters. + * Keep track of the currently allocated mm_cid for each cpu. + * The per-cpu mm_cid values are serialized by their respective + * runqueue locks. */ - raw_spinlock_t cid_lock; + struct mm_cid __percpu *pcpu_cid; + /* + * @mm_cid_next_scan: Next mm_cid scan (in jiffies). + * + * When the next mm_cid scan is due (in jiffies). + */ + unsigned long mm_cid_next_scan; #endif #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ @@ -637,6 +671,9 @@ struct mm_struct { * init_mm.mmlist, and are protected * by mmlist_lock */ +#ifdef CONFIG_PER_VMA_LOCK + int mm_lock_seq; +#endif unsigned long hiwater_rss; /* High-watermark of RSS usage */ @@ -774,7 +811,8 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; -#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \ + MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ @@ -872,6 +910,37 @@ static inline void vma_iter_init(struct vma_iterator *vmi, } #ifdef CONFIG_SCHED_MM_CID + +enum mm_cid_state { + MM_CID_UNSET = -1U, /* Unset state has lazy_put flag set. */ + MM_CID_LAZY_PUT = (1U << 31), +}; + +static inline bool mm_cid_is_unset(int cid) +{ + return cid == MM_CID_UNSET; +} + +static inline bool mm_cid_is_lazy_put(int cid) +{ + return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT); +} + +static inline bool mm_cid_is_valid(int cid) +{ + return !(cid & MM_CID_LAZY_PUT); +} + +static inline int mm_cid_set_lazy_put(int cid) +{ + return cid | MM_CID_LAZY_PUT; +} + +static inline int mm_cid_clear_lazy_put(int cid) +{ + return cid & ~MM_CID_LAZY_PUT; +} + /* Accessor for struct mm_struct's cidmask. */ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) { @@ -885,16 +954,40 @@ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) static inline void mm_init_cid(struct mm_struct *mm) { - raw_spin_lock_init(&mm->cid_lock); + int i; + + for_each_possible_cpu(i) { + struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i); + + pcpu_cid->cid = MM_CID_UNSET; + pcpu_cid->time = 0; + } cpumask_clear(mm_cidmask(mm)); } +static inline int mm_alloc_cid(struct mm_struct *mm) +{ + mm->pcpu_cid = alloc_percpu(struct mm_cid); + if (!mm->pcpu_cid) + return -ENOMEM; + mm_init_cid(mm); + return 0; +} + +static inline void mm_destroy_cid(struct mm_struct *mm) +{ + free_percpu(mm->pcpu_cid); + mm->pcpu_cid = NULL; +} + static inline unsigned int mm_cid_size(void) { return cpumask_size(); } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm) { } +static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; } +static inline void mm_destroy_cid(struct mm_struct *mm) { } static inline unsigned int mm_cid_size(void) { return 0; @@ -1036,6 +1129,7 @@ typedef struct { * mapped after the fault. * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. * We should only access orig_pte if this flag set. + * @FAULT_FLAG_VMA_LOCK: The fault is handled under VMA lock. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -1073,6 +1167,7 @@ enum fault_flag { FAULT_FLAG_INTERRUPTIBLE = 1 << 9, FAULT_FLAG_UNSHARE = 1 << 10, FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, + FAULT_FLAG_VMA_LOCK = 1 << 12, }; typedef unsigned int __bitwise zap_flags_t; diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 96e113e23d04..aab8f1b28d26 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -60,6 +60,29 @@ static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) #endif /* CONFIG_TRACING */ +static inline void mmap_assert_locked(struct mm_struct *mm) +{ + lockdep_assert_held(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); +} + +static inline void mmap_assert_write_locked(struct mm_struct *mm) +{ + lockdep_assert_held_write(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); +} + +#ifdef CONFIG_PER_VMA_LOCK +static inline void vma_end_write_all(struct mm_struct *mm) +{ + mmap_assert_write_locked(mm); + /* No races during update due to exclusive mmap_lock being held */ + WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1); +} +#else +static inline void vma_end_write_all(struct mm_struct *mm) {} +#endif + static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); @@ -102,12 +125,14 @@ static inline bool mmap_write_trylock(struct mm_struct *mm) static inline void mmap_write_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, true); + vma_end_write_all(mm); up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { __mmap_lock_trace_acquire_returned(mm, false, true); + vma_end_write_all(mm); downgrade_write(&mm->mmap_lock); } @@ -150,18 +175,6 @@ static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) up_read_non_owner(&mm->mmap_lock); } -static inline void mmap_assert_locked(struct mm_struct *mm) -{ - lockdep_assert_held(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); -} - -static inline void mmap_assert_write_locked(struct mm_struct *mm) -{ - lockdep_assert_held_write(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); -} - static inline int mmap_lock_is_contended(struct mm_struct *mm) { return rwsem_is_contended(&mm->mmap_lock); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 812e6b583b25..461d1543893b 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -450,6 +450,7 @@ struct mmc_host { unsigned int retune_paused:1; /* re-tuning is temporarily disabled */ unsigned int retune_crc_disable:1; /* don't trigger retune upon crc */ unsigned int can_dma_map_merge:1; /* merging can be used */ + unsigned int vqmmc_enabled:1; /* vqmmc regulator is enabled */ int rescan_disable; /* disable card detection */ int rescan_entered; /* used with nonremovable devices */ @@ -598,6 +599,8 @@ static inline int mmc_regulator_set_vqmmc(struct mmc_host *mmc, #endif int mmc_regulator_get_supply(struct mmc_host *mmc); +int mmc_regulator_enable_vqmmc(struct mmc_host *mmc); +void mmc_regulator_disable_vqmmc(struct mmc_host *mmc); static inline int mmc_card_is_removable(struct mmc_host *host) { diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 0e4ef9c5127a..c653accdc7fd 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -74,10 +74,13 @@ #define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 #define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 #define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 -#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43439 0xa9af +#define SDIO_DEVICE_ID_BROADCOM_43439 0xa9af #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752 0xaae8 +#define SDIO_VENDOR_ID_CYPRESS 0x04b4 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43439 0xbd3d + #define SDIO_VENDOR_ID_MARVELL 0x02df #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 #define SDIO_DEVICE_ID_MARVELL_8688_WLAN 0x9104 @@ -112,6 +115,15 @@ #define SDIO_VENDOR_ID_MICROCHIP_WILC 0x0296 #define SDIO_DEVICE_ID_MICROCHIP_WILC1000 0x5347 +#define SDIO_VENDOR_ID_REALTEK 0x024c +#define SDIO_DEVICE_ID_REALTEK_RTW8723BS 0xb723 +#define SDIO_DEVICE_ID_REALTEK_RTW8821BS 0xb821 +#define SDIO_DEVICE_ID_REALTEK_RTW8822BS 0xb822 +#define SDIO_DEVICE_ID_REALTEK_RTW8821CS 0xc821 +#define SDIO_DEVICE_ID_REALTEK_RTW8822CS 0xc822 +#define SDIO_DEVICE_ID_REALTEK_RTW8723DS 0xd723 +#define SDIO_DEVICE_ID_REALTEK_RTW8821DS 0xd821 + #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 #define SDIO_DEVICE_ID_SIANO_NICE 0x0202 diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index b9b970f7ab45..f2b7a3f04099 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -28,4 +28,18 @@ static inline void leave_mm(int cpu) { } # define task_cpu_possible(cpu, p) cpumask_test_cpu((cpu), task_cpu_possible_mask(p)) #endif +#ifndef mm_untag_mask +static inline unsigned long mm_untag_mask(struct mm_struct *mm) +{ + return -1UL; +} +#endif + +#ifndef arch_pgtable_dma_compat +static inline bool arch_pgtable_dma_compat(struct mm_struct *mm) +{ + return true; +} +#endif + #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9fb1b03b83b2..a4889c9d4055 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -26,11 +26,13 @@ /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER -#define MAX_ORDER 11 +#define MAX_ORDER 10 #else #define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif -#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) +#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER) + +#define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed @@ -93,7 +95,7 @@ static inline bool migratetype_is_mergeable(int mt) } #define for_each_migratetype_order(order, type) \ - for (order = 0; order < MAX_ORDER; order++) \ + for (order = 0; order <= MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; @@ -108,18 +110,6 @@ struct free_area { unsigned long nr_free; }; -static inline struct page *get_page_from_free_area(struct free_area *area, - int migratetype) -{ - return list_first_entry_or_null(&area->free_list[migratetype], - struct page, lru); -} - -static inline bool free_area_empty(struct free_area *area, int migratetype) -{ - return list_empty(&area->free_list[migratetype]); -} - struct pglist_data; #ifdef CONFIG_NUMA @@ -453,18 +443,14 @@ enum { struct lru_gen_mm_state { /* set to max_seq after each iteration */ unsigned long seq; - /* where the current iteration continues (inclusive) */ + /* where the current iteration continues after */ struct list_head *head; - /* where the last iteration ended (exclusive) */ + /* where the last iteration ended before */ struct list_head *tail; - /* to wait for the last page table walker to finish */ - struct wait_queue_head wait; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; - /* the number of concurrent page table walkers */ - int nr_walkers; }; struct lru_gen_mm_walk { @@ -922,7 +908,7 @@ struct zone { CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ - struct free_area free_area[MAX_ORDER]; + struct free_area free_area[MAX_ORDER + 1]; /* zone flags, see below */ unsigned long flags; @@ -1369,7 +1355,7 @@ typedef struct pglist_data { #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ - struct lru_gen_mm_walk mm_walk; + struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif @@ -1745,7 +1731,7 @@ static inline bool movable_only_nodes(nodemask_t *nodes) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) -#if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS +#if (MAX_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 549590e9c644..ccaaeda792c0 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -9,6 +9,7 @@ #define LINUX_MOD_DEVICETABLE_H #ifdef __KERNEL__ +#include <linux/mei.h> #include <linux/types.h> #include <linux/uuid.h> typedef unsigned long kernel_ulong_t; @@ -911,4 +912,19 @@ struct ishtp_device_id { kernel_ulong_t driver_data; }; +/** + * struct cdx_device_id - CDX device identifier + * @vendor: Vendor ID + * @device: Device ID + * @override_only: Match only when dev->driver_override is this driver. + * + * Type of entries in the "device Id" table for CDX devices supported by + * a CDX device driver. + */ +struct cdx_device_id { + __u16 vendor; + __u16 device; + __u32 override_only; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/module.h b/include/linux/module.h index 4435ad9439ab..9e56763dff81 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -27,6 +27,7 @@ #include <linux/tracepoint-defs.h> #include <linux/srcu.h> #include <linux/static_call_types.h> +#include <linux/dynamic_debug.h> #include <linux/percpu.h> #include <asm/module.h> @@ -320,17 +321,47 @@ struct mod_tree_node { struct latch_tree_node node; }; -struct module_layout { - /* The actual code + data. */ +enum mod_mem_type { + MOD_TEXT = 0, + MOD_DATA, + MOD_RODATA, + MOD_RO_AFTER_INIT, + MOD_INIT_TEXT, + MOD_INIT_DATA, + MOD_INIT_RODATA, + + MOD_MEM_NUM_TYPES, + MOD_INVALID = -1, +}; + +#define mod_mem_type_is_init(type) \ + ((type) == MOD_INIT_TEXT || \ + (type) == MOD_INIT_DATA || \ + (type) == MOD_INIT_RODATA) + +#define mod_mem_type_is_core(type) (!mod_mem_type_is_init(type)) + +#define mod_mem_type_is_text(type) \ + ((type) == MOD_TEXT || \ + (type) == MOD_INIT_TEXT) + +#define mod_mem_type_is_data(type) (!mod_mem_type_is_text(type)) + +#define mod_mem_type_is_core_data(type) \ + (mod_mem_type_is_core(type) && \ + mod_mem_type_is_data(type)) + +#define for_each_mod_mem_type(type) \ + for (enum mod_mem_type (type) = 0; \ + (type) < MOD_MEM_NUM_TYPES; (type)++) + +#define for_class_mod_mem_type(type, class) \ + for_each_mod_mem_type(type) \ + if (mod_mem_type_is_##class(type)) + +struct module_memory { void *base; - /* Total size. */ unsigned int size; - /* The size of the executable code. */ - unsigned int text_size; - /* Size of RO section of the module (text+rodata) */ - unsigned int ro_size; - /* Size of RO after init section */ - unsigned int ro_after_init_size; #ifdef CONFIG_MODULES_TREE_LOOKUP struct mod_tree_node mtn; @@ -339,9 +370,9 @@ struct module_layout { #ifdef CONFIG_MODULES_TREE_LOOKUP /* Only touch one cacheline for common rbtree-for-core-layout case. */ -#define __module_layout_align ____cacheline_aligned +#define __module_memory_align ____cacheline_aligned #else -#define __module_layout_align +#define __module_memory_align #endif struct mod_kallsyms { @@ -353,9 +384,9 @@ struct mod_kallsyms { #ifdef CONFIG_LIVEPATCH /** - * struct klp_modinfo - Elf information preserved from the livepatch module + * struct klp_modinfo - ELF information preserved from the livepatch module * - * @hdr: Elf header + * @hdr: ELF header * @sechdrs: Section header table * @secstrings: String table for the section headers * @symndx: The symbol table section index @@ -426,12 +457,7 @@ struct module { /* Startup function. */ int (*init)(void); - /* Core layout: rbtree is accessed frequently, so keep together. */ - struct module_layout core_layout __module_layout_align; - struct module_layout init_layout; -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - struct module_layout data_layout; -#endif + struct module_memory mem[MOD_MEM_NUM_TYPES] __module_memory_align; /* Arch-specific module values */ struct mod_arch_specific arch; @@ -523,7 +549,7 @@ struct module { bool klp; /* Is this a livepatch module? */ bool klp_alive; - /* Elf information */ + /* ELF information */ struct klp_modinfo *klp_info; #endif @@ -554,6 +580,9 @@ struct module { struct error_injection_entry *ei_funcs; unsigned int num_ei_funcs; #endif +#ifdef CONFIG_DYNAMIC_DEBUG_CORE + struct _ddebug_info dyndbg_info; +#endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} @@ -581,23 +610,35 @@ bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr); bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); +static inline bool within_module_mem_type(unsigned long addr, + const struct module *mod, + enum mod_mem_type type) +{ + unsigned long base, size; + + base = (unsigned long)mod->mem[type].base; + size = mod->mem[type].size; + return addr - base < size; +} + static inline bool within_module_core(unsigned long addr, const struct module *mod) { -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - if ((unsigned long)mod->data_layout.base <= addr && - addr < (unsigned long)mod->data_layout.base + mod->data_layout.size) - return true; -#endif - return (unsigned long)mod->core_layout.base <= addr && - addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; + for_class_mod_mem_type(type, core) { + if (within_module_mem_type(addr, mod, type)) + return true; + } + return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { - return (unsigned long)mod->init_layout.base <= addr && - addr < (unsigned long)mod->init_layout.base + mod->init_layout.size; + for_class_mod_mem_type(type, init) { + if (within_module_mem_type(addr, mod, type)) + return true; + } + return false; } static inline bool within_module(unsigned long addr, const struct module *mod) @@ -608,14 +649,6 @@ static inline bool within_module(unsigned long addr, const struct module *mod) /* Search for module by name: must be in a RCU-sched critical section. */ struct module *find_module(const char *name); -/* Returns 0 and fills in value, defined and namebuf, or -ERANGE if - symnum out of range. */ -int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, - char *name, char *module_name, int *exported); - -/* Look for this name: can be of form module:name. */ -unsigned long module_kallsyms_lookup_name(const char *name); - extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); #define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) @@ -630,10 +663,46 @@ void symbol_put_addr(void *addr); to handle the error case (which only happens with rmmod --wait). */ extern void __module_get(struct module *module); -/* This is the Right Way to get a module: if it fails, it's being removed, - * so pretend it's not there. */ +/** + * try_module_get() - take module refcount unless module is being removed + * @module: the module we should check for + * + * Only try to get a module reference count if the module is not being removed. + * This call will fail if the module is already being removed. + * + * Care must also be taken to ensure the module exists and is alive prior to + * usage of this call. This can be gauranteed through two means: + * + * 1) Direct protection: you know an earlier caller must have increased the + * module reference through __module_get(). This can typically be achieved + * by having another entity other than the module itself increment the + * module reference count. + * + * 2) Implied protection: there is an implied protection against module + * removal. An example of this is the implied protection used by kernfs / + * sysfs. The sysfs store / read file operations are guaranteed to exist + * through the use of kernfs's active reference (see kernfs_active()) and a + * sysfs / kernfs file removal cannot happen unless the same file is not + * active. Therefore, if a sysfs file is being read or written to the module + * which created it must still exist. It is therefore safe to use + * try_module_get() on module sysfs store / read ops. + * + * One of the real values to try_module_get() is the module_is_live() check + * which ensures that the caller of try_module_get() can yield to userspace + * module removal requests and gracefully fail if the module is on its way out. + * + * Returns true if the reference count was successfully incremented. + */ extern bool try_module_get(struct module *module); +/** + * module_put() - release a reference count to a module + * @module: the module we should release a reference count for + * + * If you successfully bump a reference count to a module with try_module_get(), + * when you are finished you must call module_put() to release that reference + * count. + */ extern void module_put(struct module *module); #else /*!CONFIG_MODULE_UNLOAD*/ @@ -662,17 +731,6 @@ static inline void __module_get(struct module *module) /* Dereference module function descriptor */ void *dereference_module_function_descriptor(struct module *mod, void *ptr); -/* For kallsyms to ask for address resolution. namebuf should be at - * least KSYM_NAME_LEN long: a pointer to namebuf is returned if - * found, otherwise NULL. */ -const char *module_address_lookup(unsigned long addr, - unsigned long *symbolsize, - unsigned long *offset, - char **modname, const unsigned char **modbuildid, - char *namebuf); -int lookup_module_symbol_name(unsigned long addr, char *symname); -int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); - int register_module_notifier(struct notifier_block *nb); int unregister_module_notifier(struct notifier_block *nb); @@ -763,39 +821,6 @@ static inline void module_put(struct module *module) #define module_name(mod) "kernel" -/* For kallsyms to ask for address resolution. NULL means not found. */ -static inline const char *module_address_lookup(unsigned long addr, - unsigned long *symbolsize, - unsigned long *offset, - char **modname, - const unsigned char **modbuildid, - char *namebuf) -{ - return NULL; -} - -static inline int lookup_module_symbol_name(unsigned long addr, char *symname) -{ - return -ERANGE; -} - -static inline int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name) -{ - return -ERANGE; -} - -static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, - char *type, char *name, - char *module_name, int *exported) -{ - return -ERANGE; -} - -static inline unsigned long module_kallsyms_lookup_name(const char *name) -{ - return 0; -} - static inline int register_module_notifier(struct notifier_block *nb) { /* no events will happen anyway, so this can always succeed */ @@ -834,7 +859,7 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr) #ifdef CONFIG_SYSFS extern struct kset *module_kset; -extern struct kobj_type module_ktype; +extern const struct kobj_type module_ktype; #endif /* CONFIG_SYSFS */ #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) @@ -888,17 +913,88 @@ static inline bool module_sig_ok(struct module *module) #if defined(CONFIG_MODULES) && defined(CONFIG_KALLSYMS) int module_kallsyms_on_each_symbol(const char *modname, - int (*fn)(void *, const char *, - struct module *, unsigned long), + int (*fn)(void *, const char *, unsigned long), void *data); -#else + +/* For kallsyms to ask for address resolution. namebuf should be at + * least KSYM_NAME_LEN long: a pointer to namebuf is returned if + * found, otherwise NULL. + */ +const char *module_address_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, const unsigned char **modbuildid, + char *namebuf); +int lookup_module_symbol_name(unsigned long addr, char *symname); +int lookup_module_symbol_attrs(unsigned long addr, + unsigned long *size, + unsigned long *offset, + char *modname, + char *name); + +/* Returns 0 and fills in value, defined and namebuf, or -ERANGE if + * symnum out of range. + */ +int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, + char *name, char *module_name, int *exported); + +/* Look for this name: can be of form module:name. */ +unsigned long module_kallsyms_lookup_name(const char *name); + +unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name); + +#else /* CONFIG_MODULES && CONFIG_KALLSYMS */ + static inline int module_kallsyms_on_each_symbol(const char *modname, - int (*fn)(void *, const char *, - struct module *, unsigned long), + int (*fn)(void *, const char *, unsigned long), void *data) { return -EOPNOTSUPP; } + +/* For kallsyms to ask for address resolution. NULL means not found. */ +static inline const char *module_address_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, + const unsigned char **modbuildid, + char *namebuf) +{ + return NULL; +} + +static inline int lookup_module_symbol_name(unsigned long addr, char *symname) +{ + return -ERANGE; +} + +static inline int lookup_module_symbol_attrs(unsigned long addr, + unsigned long *size, + unsigned long *offset, + char *modname, + char *name) +{ + return -ERANGE; +} + +static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, + char *type, char *name, + char *module_name, int *exported) +{ + return -ERANGE; +} + +static inline unsigned long module_kallsyms_lookup_name(const char *name) +{ + return 0; +} + +static inline unsigned long find_kallsyms_symbol_value(struct module *mod, + const char *name) +{ + return 0; +} + #endif /* CONFIG_MODULES && CONFIG_KALLSYMS */ #endif /* _LINUX_MODULE_H */ diff --git a/include/linux/module_symbol.h b/include/linux/module_symbol.h new file mode 100644 index 000000000000..7ace7ba30203 --- /dev/null +++ b/include/linux/module_symbol.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LINUX_MODULE_SYMBOL_H +#define _LINUX_MODULE_SYMBOL_H + +/* This ignores the intensely annoying "mapping symbols" found in ELF files. */ +static inline int is_mapping_symbol(const char *str) +{ + if (str[0] == '.' && str[1] == 'L') + return true; + if (str[0] == 'L' && str[1] == '0') + return true; + return str[0] == '$' && + (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x') + && (str[2] == '\0' || str[2] == '.'); +} + +#endif /* _LINUX_MODULE_SYMBOL_H */ diff --git a/include/linux/msi.h b/include/linux/msi.h index cdb14a1ef268..a50ea79522f8 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -383,6 +383,13 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ + +/* + * Xen uses non-default msi_domain_ops and hence needs a way to populate sysfs + * entries of MSI IRQs. + */ +#if defined(CONFIG_PCI_XEN) || defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) #ifdef CONFIG_SYSFS int msi_device_populate_sysfs(struct device *dev); void msi_device_destroy_sysfs(struct device *dev); @@ -390,7 +397,7 @@ void msi_device_destroy_sysfs(struct device *dev); static inline int msi_device_populate_sysfs(struct device *dev) { return 0; } static inline void msi_device_destroy_sysfs(struct device *dev) { } #endif /* !CONFIG_SYSFS */ -#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ +#endif /* CONFIG_PCI_XEN || CONFIG_PCI_MSI_ARCH_FALLBACKS */ /* * The restore hook is still available even for fully irq domain based diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f8d4be9c587a..5159d692f9ce 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1075,7 +1075,7 @@ static inline void nand_op_trace(const char *prefix, * @exec_op: controller specific method to execute NAND operations. * This method replaces chip->legacy.cmdfunc(), * chip->legacy.{read,write}_{buf,byte,word}(), - * chip->legacy.dev_ready() and chip->legacy.waifunc(). + * chip->legacy.dev_ready() and chip->legacy.waitfunc(). * @setup_interface: setup the data interface and timing. If chipnr is set to * %NAND_DATA_IFACE_CHECK_ONLY this means the configuration * should not be applied but only checked. diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index a3f8cdca90c8..cdcfe0fd2e7d 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -343,6 +343,12 @@ struct spi_nor_flash_parameter; * struct spi_nor - Structure for defining the SPI NOR layer * @mtd: an mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations + * @rww: Read-While-Write (RWW) sync lock + * @rww.wait: wait queue for the RWW sync + * @rww.ongoing_io: the bus is busy + * @rww.ongoing_rd: a read is ongoing on the chip + * @rww.ongoing_pe: a program/erase is ongoing on the chip + * @rww.used_banks: bitmap of the banks in use * @dev: pointer to an SPI device or an SPI NOR controller device * @spimem: pointer to the SPI memory device * @bouncebuf: bounce buffer used when the buffer passed by the MTD @@ -376,6 +382,13 @@ struct spi_nor_flash_parameter; struct spi_nor { struct mtd_info mtd; struct mutex lock; + struct spi_nor_rww { + wait_queue_head_t wait; + bool ongoing_io; + bool ongoing_rd; + bool ongoing_pe; + unsigned int used_banks; + } rww; struct device *dev; struct spi_mem *spimem; u8 *bouncebuf; @@ -437,10 +450,4 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) int spi_nor_scan(struct spi_nor *nor, const char *name, const struct spi_nor_hwcaps *hwcaps); -/** - * spi_nor_restore_addr_mode() - restore the status of SPI NOR - * @nor: the spi_nor structure - */ -void spi_nor_restore(struct spi_nor *nor); - #endif diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 01be9f0f008a..3e285c09d16d 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -262,6 +262,7 @@ struct spinand_manufacturer { /* SPI NAND manufacturers */ extern const struct spinand_manufacturer alliancememory_spinand_manufacturer; extern const struct spinand_manufacturer ato_spinand_manufacturer; +extern const struct spinand_manufacturer esmt_c8_spinand_manufacturer; extern const struct spinand_manufacturer gigadevice_spinand_manufacturer; extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; diff --git a/include/linux/namei.h b/include/linux/namei.h index 0d797f3367ca..1463cbda4888 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -57,12 +57,20 @@ static inline int user_path_at(int dfd, const char __user *name, unsigned flags, return user_path_at_empty(dfd, name, flags, path, NULL); } +struct dentry *lookup_one_qstr_excl(const struct qstr *name, + struct dentry *base, + unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); +int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, + struct path *parent, struct qstr *last, int *type, + const struct path *root); +int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, + unsigned int, struct path *); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); @@ -81,6 +89,7 @@ extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); +extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); extern int __must_check nd_jump_link(const struct path *path); diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h new file mode 100644 index 000000000000..fd67f3cc0c4b --- /dev/null +++ b/include/linux/net_tstamp.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_NET_TIMESTAMPING_H_ +#define _LINUX_NET_TIMESTAMPING_H_ + +#include <uapi/linux/net_tstamp.h> + +/** + * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config + * + * @flags: see struct hwtstamp_config + * @tx_type: see struct hwtstamp_config + * @rx_filter: see struct hwtstamp_config + * + * Prefer using this structure for in-kernel processing of hardware + * timestamping configuration, over the inextensible struct hwtstamp_config + * exposed to the %SIOCGHWTSTAMP and %SIOCSHWTSTAMP ioctl UAPI. + */ +struct kernel_hwtstamp_config { + int flags; + int tx_type; + int rx_filter; +}; + +static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg, + const struct hwtstamp_config *cfg) +{ + kernel_cfg->flags = cfg->flags; + kernel_cfg->tx_type = cfg->tx_type; + kernel_cfg->rx_filter = cfg->rx_filter; +} + +#endif /* _LINUX_NET_TIMESTAMPING_H_ */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6a14b7b11766..c2f0c6002a84 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -52,6 +52,7 @@ #include <linux/rbtree.h> #include <net/net_trackers.h> #include <net/net_debug.h> +#include <net/dropreason-core.h> struct netpoll_info; struct device; @@ -297,9 +298,11 @@ struct hh_cache { * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ - ((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, @@ -357,18 +360,22 @@ struct napi_struct { unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL + /* CPU actively polling if netpoll is configured */ int poll_owner; #endif + /* CPU on which NAPI has been scheduled for processing */ + int list_owner; struct net_device *dev; struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; struct list_head rx_list; /* Pending GRO_NORMAL skbs */ int rx_count; /* length of rx_list */ + unsigned int napi_id; struct hrtimer timer; + struct task_struct *thread; + /* control-path-only fields follow */ struct list_head dev_list; struct hlist_node napi_hash_node; - unsigned int napi_id; - struct task_struct *thread; }; enum { @@ -506,15 +513,18 @@ static inline bool napi_reschedule(struct napi_struct *napi) return false; } -bool napi_complete_done(struct napi_struct *n, int work_done); /** - * napi_complete - NAPI processing complete - * @n: NAPI context + * napi_complete_done - NAPI processing complete + * @n: NAPI context + * @work_done: number of packets processed * - * Mark NAPI processing as complete. - * Consider using napi_complete_done() instead. + * Mark NAPI processing as complete. Should only be called if poll budget + * has not been completely consumed. + * Prefer over napi_complete(). * Return false if device should avoid rearming interrupts. */ +bool napi_complete_done(struct napi_struct *n, int work_done); + static inline bool napi_complete(struct napi_struct *n) { return napi_complete_done(n, 0); @@ -610,7 +620,7 @@ struct netdev_queue { netdevice_tracker dev_tracker; struct Qdisc __rcu *qdisc; - struct Qdisc *qdisc_sleeping; + struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; #endif @@ -758,8 +768,11 @@ static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, /* We only give a hint, preemption can change CPU under us */ val |= raw_smp_processor_id(); - if (table->ents[index] != val) - table->ents[index] = val; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in get_rps_cpu(). + */ + if (READ_ONCE(table->ents[index]) != val) + WRITE_ONCE(table->ents[index], val); } } @@ -1306,6 +1319,17 @@ struct netdev_net_notifier { * Used to add FDB entries to dump requests. Implementers should add * entries to skb and update idx with the number of entries. * + * int (*ndo_mdb_add)(struct net_device *dev, struct nlattr *tb[], + * u16 nlmsg_flags, struct netlink_ext_ack *extack); + * Adds an MDB entry to dev. + * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], + * struct netlink_ext_ack *extack); + * Deletes the MDB entry from dev. + * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, + * struct netlink_callback *cb); + * Dumps MDB entries from dev. The first argument (marker) in the netlink + * callback is used by core rtnetlink code. + * * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags, struct netlink_ext_ack *extack) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, @@ -1568,6 +1592,16 @@ struct net_device_ops { const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack); + int (*ndo_mdb_add)(struct net_device *dev, + struct nlattr *tb[], + u16 nlmsg_flags, + struct netlink_ext_ack *extack); + int (*ndo_mdb_del)(struct net_device *dev, + struct nlattr *tb[], + struct netlink_ext_ack *extack); + int (*ndo_mdb_dump)(struct net_device *dev, + struct sk_buff *skb, + struct netlink_callback *cb); int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, @@ -1622,7 +1656,8 @@ struct net_device_ops { struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); - int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash); + int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type); }; /** @@ -2460,6 +2495,7 @@ static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { + DEBUG_NET_WARN_ON_ONCE(index >= dev->num_tx_queues); return &dev->_tx[index]; } @@ -2955,7 +2991,8 @@ netdev_notifier_info_to_extack(const struct netdev_notifier_info *info) } int call_netdevice_notifiers(unsigned long val, struct net_device *dev); - +int call_netdevice_notifiers_info(unsigned long val, + struct netdev_notifier_info *info); extern rwlock_t dev_base_lock; /* Device list lock */ @@ -3160,6 +3197,10 @@ struct softnet_data { #ifdef CONFIG_RPS struct softnet_data *rps_ipi_list; #endif + + bool in_net_rx_action; + bool in_napi_threaded_poll; + #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit __rcu *flow_limit; #endif @@ -3304,6 +3345,7 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { + /* Must be an atomic op see netif_txq_try_stop() */ set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } @@ -3500,7 +3542,7 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, * netdev_tx_sent_queue will miss the update and cause the queue to * be stopped forever */ - smp_mb(); + smp_mb(); /* NOTE: netdev_txq_completed_mb() assumes this exists */ if (unlikely(dql_avail(&dev_queue->dql) < 0)) return; @@ -3804,13 +3846,8 @@ static inline unsigned int get_netdev_rx_queue_index( int netif_get_num_default_rss_queues(void); -enum skb_free_reason { - SKB_REASON_CONSUMED, - SKB_REASON_DROPPED, -}; - -void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason); -void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); +void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason); +void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason); /* * It is not allowed to call kfree_skb() or consume_skb() from hardware @@ -3833,22 +3870,22 @@ void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); */ static inline void dev_kfree_skb_irq(struct sk_buff *skb) { - __dev_kfree_skb_irq(skb, SKB_REASON_DROPPED); + dev_kfree_skb_irq_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } static inline void dev_consume_skb_irq(struct sk_buff *skb) { - __dev_kfree_skb_irq(skb, SKB_REASON_CONSUMED); + dev_kfree_skb_irq_reason(skb, SKB_CONSUMED); } static inline void dev_kfree_skb_any(struct sk_buff *skb) { - __dev_kfree_skb_any(skb, SKB_REASON_DROPPED); + dev_kfree_skb_any_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } static inline void dev_consume_skb_any(struct sk_buff *skb) { - __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); + dev_kfree_skb_any_reason(skb, SKB_CONSUMED); } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index c8e03bcaecaa..0762444e3767 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -80,6 +80,7 @@ typedef unsigned int nf_hookfn(void *priv, enum nf_hook_ops_type { NF_HOOK_OP_UNDEFINED, NF_HOOK_OP_NF_TABLES, + NF_HOOK_OP_BPF, }; struct nf_hook_ops { diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 241e005f290a..e9a9ab34a7cc 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -45,7 +45,6 @@ struct nfnetlink_subsystem { int (*commit)(struct net *net, struct sk_buff *skb); int (*abort)(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action); - void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 48314ade1506..7834c0be2831 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -197,6 +197,8 @@ static inline int nf_cookie_v6_check(const struct ipv6hdr *iph, __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); +int nf_ip6_check_hbh_len(struct sk_buff *skb, u32 *plen); + int ipv6_netfilter_init(void); void ipv6_netfilter_fini(void); diff --git a/include/linux/netlink.h b/include/linux/netlink.h index c43ac7690eca..19c0791ed9d5 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -50,7 +50,6 @@ struct netlink_kernel_cfg { struct mutex *cb_mutex; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); - bool (*compare)(struct net *net, struct sock *sk); }; struct sock *__netlink_kernel_create(struct net *net, int unit, @@ -162,9 +161,31 @@ struct netlink_ext_ack { } \ } while (0) +#define NL_SET_ERR_MSG_ATTR_POL_FMT(extack, attr, pol, fmt, args...) do { \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (!__extack) \ + break; \ + \ + if (snprintf(__extack->_msg_buf, NETLINK_MAX_FMTMSG_LEN, \ + "%s" fmt "%s", "", ##args, "") >= \ + NETLINK_MAX_FMTMSG_LEN) \ + net_warn_ratelimited("%s" fmt "%s", "truncated extack: ", \ + ##args, "\n"); \ + \ + do_trace_netlink_extack(__extack->_msg_buf); \ + \ + __extack->_msg = __extack->_msg_buf; \ + __extack->bad_attr = (attr); \ + __extack->policy = (pol); \ +} while (0) + #define NL_SET_ERR_MSG_ATTR(extack, attr, msg) \ NL_SET_ERR_MSG_ATTR_POL(extack, attr, NULL, msg) +#define NL_SET_ERR_MSG_ATTR_FMT(extack, attr, msg, args...) \ + NL_SET_ERR_MSG_ATTR_POL_FMT(extack, attr, NULL, msg, ##args) + #define NL_SET_ERR_ATTR_MISS(extack, nest, type) do { \ struct netlink_ext_ack *__extack = (extack); \ \ diff --git a/include/linux/nfs.h b/include/linux/nfs.h index b06375e88e58..ceb70a926b95 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -10,6 +10,7 @@ #include <linux/sunrpc/msg_prot.h> #include <linux/string.h> +#include <linux/crc32.h> #include <uapi/linux/nfs.h> /* @@ -44,4 +45,23 @@ enum nfs3_stable_how { /* used by direct.c to mark verf as invalid */ NFS_INVALID_STABLE_HOW = -1 }; + +#ifdef CONFIG_CRC32 +/** + * nfs_fhandle_hash - calculate the crc32 hash for the filehandle + * @fh - pointer to filehandle + * + * returns a crc32 hash for the filehandle that is compatible with + * the one displayed by "wireshark". + */ +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); +} +#else /* CONFIG_CRC32 */ +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return 0; +} +#endif /* CONFIG_CRC32 */ #endif /* _LINUX_NFS_H */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bf89fe6fc3ba..279262057a92 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -31,6 +31,10 @@ #include <linux/sunrpc/auth.h> #include <linux/sunrpc/clnt.h> +#ifdef CONFIG_NFS_FSCACHE +#include <linux/netfs.h> +#endif + #include <linux/nfs.h> #include <linux/nfs2.h> #include <linux/nfs3.h> @@ -191,6 +195,39 @@ struct nfs_inode { /* Open contexts for shared mmap writes */ struct list_head open_files; + /* Keep track of out-of-order replies. + * The ooo array contains start/end pairs of + * numbers from the changeid sequence when + * the inode's iversion has been updated. + * It also contains end/start pair (i.e. reverse order) + * of sections of the changeid sequence that have + * been seen in replies from the server. + * Normally these should match and when both + * A:B and B:A are found in ooo, they are both removed. + * And if a reply with A:B causes an iversion update + * of A:B, then neither are added. + * When a reply has pre_change that doesn't match + * iversion, then the changeid pair and any consequent + * change in iversion ARE added. Later replies + * might fill in the gaps, or possibly a gap is caused + * by a change from another client. + * When a file or directory is opened, if the ooo table + * is not empty, then we assume the gaps were due to + * another client and we invalidate the cached data. + * + * We can only track a limited number of concurrent gaps. + * Currently that limit is 16. + * We allocate the table on demand. If there is insufficient + * memory, then we probably cannot cache the file anyway + * so there is no loss. + */ + struct { + int cnt; + struct { + u64 start, end; + } gap[16]; + } *ooo; + #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ @@ -204,14 +241,15 @@ struct nfs_inode { /* how many bytes have been written/read and how many bytes queued up */ __u64 write_io; __u64 read_io; -#ifdef CONFIG_NFS_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; - #ifdef CONFIG_NFS_V4_2 struct nfs4_xattr_cache *xattr_cache; #endif + union { + struct inode vfs_inode; +#ifdef CONFIG_NFS_FSCACHE + struct netfs_inode netfs; /* netfs context and VFS inode */ +#endif + }; }; struct nfs4_copy_state { @@ -276,7 +314,6 @@ struct nfs4_copy_state { #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ -#define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ @@ -329,15 +366,6 @@ static inline int NFS_STALE(const struct inode *inode) return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags); } -static inline struct fscache_cookie *nfs_i_fscache(struct inode *inode) -{ -#ifdef CONFIG_NFS_FSCACHE - return NFS_I(inode)->fscache; -#else - return NULL; -#endif -} - static inline __u64 NFS_FILEID(const struct inode *inode) { return NFS_I(inode)->fileid; @@ -617,6 +645,20 @@ nfs_fileid_to_ino_t(u64 fileid) return ino; } +static inline void nfs_ooo_clear(struct nfs_inode *nfsi) +{ + nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; + kfree(nfsi->ooo); + nfsi->ooo = NULL; +} + +static inline bool nfs_ooo_test(struct nfs_inode *nfsi) +{ + return (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) || + (nfsi->ooo && nfsi->ooo->cnt > 0); + +} + #define NFS_JUKEBOX_RETRY_TIME (5 * HZ) /* We need to block new opens while a file is being unlinked. diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h index 027874c36c88..8d946089d151 100644 --- a/include/linux/nfs_iostat.h +++ b/include/linux/nfs_iostat.h @@ -119,16 +119,4 @@ enum nfs_stat_eventcounters { __NFSIOS_COUNTSMAX, }; -/* - * NFS local caching servicing counters - */ -enum nfs_stat_fscachecounters { - NFSIOS_FSCACHE_PAGES_READ_OK, - NFSIOS_FSCACHE_PAGES_READ_FAIL, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, - NFSIOS_FSCACHE_PAGES_UNCACHED, - __NFSIOS_FSCACHEMAX, -}; - #endif /* _LINUX_NFS_IOSTAT */ diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index a2f1ca657623..aa9f4c6ebe26 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -105,6 +105,9 @@ struct nfs_pageio_descriptor { struct pnfs_layout_segment *pg_lseg; struct nfs_io_completion *pg_io_completion; struct nfs_direct_req *pg_dreq; +#ifdef CONFIG_NFS_FSCACHE + void *pg_netfs; +#endif unsigned int pg_bsize; /* default bsize for mirrors */ u32 pg_mirror_count; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e86cf6642d21..29a1b39794bf 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -670,6 +670,7 @@ struct nfs_pgio_res { struct { unsigned int replen; /* used by read */ int eof; /* used by read */ + void * scratch; /* used by read */ }; struct { struct nfs_writeverf * verf; /* used by write */ @@ -1619,6 +1620,9 @@ struct nfs_pgio_header { const struct nfs_rw_ops *rw_ops; struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; +#ifdef CONFIG_NFS_FSCACHE + void *netfs; +#endif int pnfs_error; int error; /* merge with pnfs_error */ diff --git a/include/linux/notifier.h b/include/linux/notifier.h index aef88c2d1173..86544707236a 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -73,6 +73,9 @@ struct raw_notifier_head { struct srcu_notifier_head { struct mutex mutex; +#ifdef CONFIG_TREE_SRCU + struct srcu_usage srcuu; +#endif struct srcu_struct srcu; struct notifier_block __rcu *head; }; @@ -103,12 +106,22 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } +#ifdef CONFIG_TREE_SRCU +#define SRCU_NOTIFIER_INIT(name, pcpu) \ + { \ + .mutex = __MUTEX_INITIALIZER(name.mutex), \ + .head = NULL, \ + .srcuu = __SRCU_USAGE_INIT(name.srcuu), \ + .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \ + } +#else #define SRCU_NOTIFIER_INIT(name, pcpu) \ { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ - .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ + .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \ } +#endif #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index 75470159a194..57ebe1267f7f 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -115,8 +115,9 @@ struct nvme_tcp_icresp_pdu { struct nvme_tcp_term_pdu { struct nvme_tcp_hdr hdr; __le16 fes; - __le32 fei; - __u8 rsvd[8]; + __le16 feil; + __le16 feiu; + __u8 rsvd[10]; }; /** diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4fad4aa245fb..779507ac750b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -812,6 +812,7 @@ enum nvme_opcode { nvme_opcode_name(nvme_cmd_compare), \ nvme_opcode_name(nvme_cmd_write_zeroes), \ nvme_opcode_name(nvme_cmd_dsm), \ + nvme_opcode_name(nvme_cmd_verify), \ nvme_opcode_name(nvme_cmd_resv_register), \ nvme_opcode_name(nvme_cmd_resv_report), \ nvme_opcode_name(nvme_cmd_resv_acquire), \ @@ -1144,10 +1145,14 @@ enum nvme_admin_opcode { nvme_admin_opcode_name(nvme_admin_ns_mgmt), \ nvme_admin_opcode_name(nvme_admin_activate_fw), \ nvme_admin_opcode_name(nvme_admin_download_fw), \ + nvme_admin_opcode_name(nvme_admin_dev_self_test), \ nvme_admin_opcode_name(nvme_admin_ns_attach), \ nvme_admin_opcode_name(nvme_admin_keep_alive), \ nvme_admin_opcode_name(nvme_admin_directive_send), \ nvme_admin_opcode_name(nvme_admin_directive_recv), \ + nvme_admin_opcode_name(nvme_admin_virtual_mgmt), \ + nvme_admin_opcode_name(nvme_admin_nvme_mi_send), \ + nvme_admin_opcode_name(nvme_admin_nvme_mi_recv), \ nvme_admin_opcode_name(nvme_admin_dbbuf), \ nvme_admin_opcode_name(nvme_admin_format_nvm), \ nvme_admin_opcode_name(nvme_admin_security_send), \ diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 1f62f7ba71ca..fa030d93b768 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -239,6 +239,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id); struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *name); +struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem); #else static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) @@ -251,6 +252,12 @@ static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np, { return ERR_PTR(-EOPNOTSUPP); } + +static inline struct device_node * +of_nvmem_layout_get_container(struct nvmem_device *nvmem) +{ + return ERR_PTR(-EOPNOTSUPP); +} #endif /* CONFIG_NVMEM && CONFIG_OF */ #endif /* ifndef _LINUX_NVMEM_CONSUMER_H */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 0262b86194eb..dae26295e6be 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -9,6 +9,7 @@ #ifndef _LINUX_NVMEM_PROVIDER_H #define _LINUX_NVMEM_PROVIDER_H +#include <linux/device/driver.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/gpio/consumer.h> @@ -20,7 +21,8 @@ typedef int (*nvmem_reg_write_t)(void *priv, unsigned int offset, void *val, size_t bytes); /* used for vendor specific post processing of cell data */ typedef int (*nvmem_cell_post_process_t)(void *priv, const char *id, int index, - unsigned int offset, void *buf, size_t bytes); + unsigned int offset, void *buf, + size_t bytes); enum nvmem_type { NVMEM_TYPE_UNKNOWN = 0, @@ -50,18 +52,25 @@ struct nvmem_keepout { * struct nvmem_cell_info - NVMEM cell description * @name: Name. * @offset: Offset within the NVMEM device. + * @raw_len: Length of raw data (without post processing). * @bytes: Length of the cell. * @bit_offset: Bit offset if cell is smaller than a byte. * @nbits: Number of bits. * @np: Optional device_node pointer. + * @read_post_process: Callback for optional post processing of cell data + * on reads. + * @priv: Opaque data passed to the read_post_process hook. */ struct nvmem_cell_info { const char *name; unsigned int offset; + size_t raw_len; unsigned int bytes; unsigned int bit_offset; unsigned int nbits; struct device_node *np; + nvmem_cell_post_process_t read_post_process; + void *priv; }; /** @@ -82,12 +91,12 @@ struct nvmem_cell_info { * @no_of_node: Device should not use the parent's of_node even if it's !NULL. * @reg_read: Callback to read data. * @reg_write: Callback to write data. - * @cell_post_process: Callback for vendor specific post processing of cell data * @size: Device size. * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. * @ignore_wp: Write Protect pin is managed by the provider. + * @layout: Fixed layout associated with this nvmem device. * * Note: A default "nvmem<id>" name will be assigned to the device if * no name is specified in its configuration. In such case "<id>" is @@ -109,11 +118,11 @@ struct nvmem_config { bool read_only; bool root_only; bool ignore_wp; + struct nvmem_layout *layout; struct device_node *of_node; bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; - nvmem_cell_post_process_t cell_post_process; int size; int word_size; int stride; @@ -142,6 +151,38 @@ struct nvmem_cell_table { struct list_head node; }; +/** + * struct nvmem_layout - NVMEM layout definitions + * + * @name: Layout name. + * @of_match_table: Open firmware match table. + * @add_cells: Will be called if a nvmem device is found which + * has this layout. The function will add layout + * specific cells with nvmem_add_one_cell(). + * @fixup_cell_info: Will be called before a cell is added. Can be + * used to modify the nvmem_cell_info. + * @owner: Pointer to struct module. + * @node: List node. + * + * A nvmem device can hold a well defined structure which can just be + * evaluated during runtime. For example a TLV list, or a list of "name=val" + * pairs. A nvmem layout can parse the nvmem device and add appropriate + * cells. + */ +struct nvmem_layout { + const char *name; + const struct of_device_id *of_match_table; + int (*add_cells)(struct device *dev, struct nvmem_device *nvmem, + struct nvmem_layout *layout); + void (*fixup_cell_info)(struct nvmem_device *nvmem, + struct nvmem_layout *layout, + struct nvmem_cell_info *cell); + + /* private */ + struct module *owner; + struct list_head node; +}; + #if IS_ENABLED(CONFIG_NVMEM) struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); @@ -156,6 +197,14 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table); int nvmem_add_one_cell(struct nvmem_device *nvmem, const struct nvmem_cell_info *info); +int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner); +#define nvmem_layout_register(layout) \ + __nvmem_layout_register(layout, THIS_MODULE) +void nvmem_layout_unregister(struct nvmem_layout *layout); + +const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem, + struct nvmem_layout *layout); + #else static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) @@ -179,5 +228,24 @@ static inline int nvmem_add_one_cell(struct nvmem_device *nvmem, return -EOPNOTSUPP; } +static inline int nvmem_layout_register(struct nvmem_layout *layout) +{ + return -EOPNOTSUPP; +} + +static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {} + +static inline const void * +nvmem_layout_get_match_data(struct nvmem_device *nvmem, + struct nvmem_layout *layout) +{ + return NULL; +} + #endif /* CONFIG_NVMEM */ + +#define module_nvmem_layout_driver(__layout_driver) \ + module_driver(__layout_driver, nvmem_layout_register, \ + nvmem_layout_unregister) + #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 9ac3df3fccf0..03f82c2c2ebf 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -2,47 +2,7 @@ #ifndef _LINUX_OBJTOOL_H #define _LINUX_OBJTOOL_H -#ifndef __ASSEMBLY__ - -#include <linux/types.h> - -/* - * This struct is used by asm and inline asm code to manually annotate the - * location of registers on the stack. - */ -struct unwind_hint { - u32 ip; - s16 sp_offset; - u8 sp_reg; - u8 type; - u8 signal; - u8 end; -}; -#endif - -/* - * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP - * (the caller's SP right before it made the call). Used for all callable - * functions, i.e. all C code and all callable asm functions. - * - * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset - * points to a fully populated pt_regs from a syscall, interrupt, or exception. - * - * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that - * sp_reg+sp_offset points to the iret return frame. - * - * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. - * Useful for code which doesn't have an ELF function annotation. - * - * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. - */ -#define UNWIND_HINT_TYPE_CALL 0 -#define UNWIND_HINT_TYPE_REGS 1 -#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 -#define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_ENTRY 4 -#define UNWIND_HINT_TYPE_SAVE 5 -#define UNWIND_HINT_TYPE_RESTORE 6 +#include <linux/objtool_types.h> #ifdef CONFIG_OBJTOOL @@ -50,7 +10,7 @@ struct unwind_hint { #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ +#define UNWIND_HINT(type, sp_reg, sp_offset, signal) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ @@ -59,7 +19,6 @@ struct unwind_hint { ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ ".byte " __stringify(signal) "\n\t" \ - ".byte " __stringify(end) "\n\t" \ ".balign 4 \n\t" \ ".popsection\n\t" @@ -89,7 +48,7 @@ struct unwind_hint { #define ANNOTATE_NOENDBR \ "986: \n\t" \ ".pushsection .discard.noendbr\n\t" \ - _ASM_PTR " 986b\n\t" \ + ".long 986b - .\n\t" \ ".popsection\n\t" #define ASM_REACHABLE \ @@ -107,7 +66,7 @@ struct unwind_hint { #define ANNOTATE_INTRA_FUNCTION_CALL \ 999: \ .pushsection .discard.intra_function_calls; \ - .long 999b; \ + .long 999b - .; \ .popsection; /* @@ -131,23 +90,22 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 -.Lunwind_hint_ip_\@: +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 +.Lhere_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ - .long .Lunwind_hint_ip_\@ - . + .long .Lhere_\@ - . .short \sp_offset .byte \sp_reg .byte \type .byte \signal - .byte \end .balign 4 .popsection .endm .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - _ASM_PTR \func + .long \func - . .popsection .endm @@ -160,8 +118,24 @@ struct unwind_hint { .macro ANNOTATE_NOENDBR .Lhere_\@: .pushsection .discard.noendbr - .quad .Lhere_\@ + .long .Lhere_\@ - . + .popsection +.endm + +/* + * Use objtool to validate the entry requirement that all code paths do + * VALIDATE_UNRET_END before RET. + * + * NOTE: The macro must be used at the beginning of a global symbol, otherwise + * it will be ignored. + */ +.macro VALIDATE_UNRET_BEGIN +#if defined(CONFIG_NOINSTR_VALIDATION) && defined(CONFIG_CPU_UNRET_ENTRY) +.Lhere_\@: + .pushsection .discard.validate_unret + .long .Lhere_\@ - . .popsection +#endif .endm .macro REACHABLE @@ -177,15 +151,14 @@ struct unwind_hint { #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ - "\n\t" +#define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) #define ANNOTATE_NOENDBR #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h new file mode 100644 index 000000000000..453a4f4ef39d --- /dev/null +++ b/include/linux/objtool_types.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_OBJTOOL_TYPES_H +#define _LINUX_OBJTOOL_TYPES_H + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> + +/* + * This struct is used by asm and inline asm code to manually annotate the + * location of registers on the stack. + */ +struct unwind_hint { + u32 ip; + s16 sp_offset; + u8 sp_reg; + u8 type; + u8 signal; +}; + +#endif /* __ASSEMBLY__ */ + +/* + * UNWIND_HINT_TYPE_UNDEFINED: A blind spot in ORC coverage which can result in + * a truncated and unreliable stack unwind. + * + * UNWIND_HINT_TYPE_END_OF_STACK: The end of the kernel stack unwind before + * hitting user entry, boot code, or fork entry (when there are no pt_regs + * available). + * + * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP + * (the caller's SP right before it made the call). Used for all callable + * functions, i.e. all C code and all callable asm functions. + * + * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset + * points to a fully populated pt_regs from a syscall, interrupt, or exception. + * + * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that + * sp_reg+sp_offset points to the iret return frame. + * + * UNWIND_HINT_TYPE_FUNC: Generate the unwind metadata of a callable function. + * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_TYPE_{SAVE,RESTORE}: Save the unwind metadata at a certain + * location so that it can be restored later. + */ +#define UNWIND_HINT_TYPE_UNDEFINED 0 +#define UNWIND_HINT_TYPE_END_OF_STACK 1 +#define UNWIND_HINT_TYPE_CALL 2 +#define UNWIND_HINT_TYPE_REGS 3 +#define UNWIND_HINT_TYPE_REGS_PARTIAL 4 +/* The below hint types don't have corresponding ORC types */ +#define UNWIND_HINT_TYPE_FUNC 5 +#define UNWIND_HINT_TYPE_SAVE 6 +#define UNWIND_HINT_TYPE_RESTORE 7 + +#endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/include/linux/of.h b/include/linux/of.h index 0af611307db2..6ecde0515677 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -16,14 +16,10 @@ #include <linux/errno.h> #include <linux/kobject.h> #include <linux/mod_devicetable.h> -#include <linux/spinlock.h> -#include <linux/topology.h> -#include <linux/notifier.h> #include <linux/property.h> #include <linux/list.h> #include <asm/byteorder.h> -#include <asm/errno.h> typedef u32 phandle; typedef u32 ihandle; @@ -145,7 +141,6 @@ extern struct device_node *of_root; extern struct device_node *of_chosen; extern struct device_node *of_aliases; extern struct device_node *of_stdout; -extern raw_spinlock_t devtree_lock; /* * struct device_node flag descriptions @@ -361,6 +356,8 @@ extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); +extern struct device_node *of_cpu_device_node_get(int cpu); +extern int of_cpu_node_to_id(struct device_node *np); extern struct device_node *of_get_next_cpu_node(struct device_node *prev); extern struct device_node *of_get_cpu_state_node(struct device_node *cpu_node, int index); @@ -373,7 +370,9 @@ extern int of_n_addr_cells(struct device_node *np); extern int of_n_size_cells(struct device_node *np); extern const struct of_device_id *of_match_node( const struct of_device_id *matches, const struct device_node *node); -extern int of_modalias_node(struct device_node *node, char *modalias, int len); +extern const void *of_device_get_match_data(const struct device *dev); +extern int of_alias_from_compatible(const struct device_node *node, char *alias, + int len); extern void of_print_phandle_args(const char *msg, const struct of_phandle_args *args); extern int __of_parse_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name, int cell_count, @@ -384,6 +383,10 @@ extern int of_parse_phandle_with_args_map(const struct device_node *np, extern int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name); +/* module functions */ +extern ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len); +extern int of_request_module(const struct device_node *np); + /* phandle iterator functions */ extern int of_phandle_iterator_init(struct of_phandle_iterator *it, const struct device_node *np, @@ -439,8 +442,6 @@ const char *of_prop_next_string(struct property *prop, const char *cur); bool of_console_check(struct device_node *dn, char *name, int index); -extern int of_cpu_node_to_id(struct device_node *np); - int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out); @@ -635,6 +636,16 @@ static inline struct device_node *of_get_cpu_node(int cpu, return NULL; } +static inline struct device_node *of_cpu_device_node_get(int cpu) +{ + return NULL; +} + +static inline int of_cpu_node_to_id(struct device_node *np) +{ + return -ENODEV; +} + static inline struct device_node *of_get_next_cpu_node(struct device_node *prev) { return NULL; @@ -741,6 +752,17 @@ static inline int of_count_phandle_with_args(const struct device_node *np, return -ENOSYS; } +static inline ssize_t of_modalias(const struct device_node *np, char *str, + ssize_t len) +{ + return -ENODEV; +} + +static inline int of_request_module(const struct device_node *np) +{ + return -ENODEV; +} + static inline int of_phandle_iterator_init(struct of_phandle_iterator *it, const struct device_node *np, const char *list_name, @@ -837,11 +859,6 @@ static inline void of_property_clear_flag(struct property *p, unsigned long flag { } -static inline int of_cpu_node_to_id(struct device_node *np) -{ - return -ENODEV; -} - static inline int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out) @@ -854,6 +871,11 @@ static inline phys_addr_t of_dma_get_max_cpu_address(struct device_node *np) return PHYS_ADDR_MAX; } +static inline const void *of_device_get_match_data(const struct device *dev) +{ + return NULL; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL #endif /* CONFIG_OF */ @@ -1512,6 +1534,8 @@ enum of_reconfig_change { OF_RECONFIG_CHANGE_REMOVE, }; +struct notifier_block; + #ifdef CONFIG_OF_DYNAMIC extern int of_reconfig_notifier_register(struct notifier_block *); extern int of_reconfig_notifier_unregister(struct notifier_block *); diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 376671594746..26a19daf0d09 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -35,6 +35,22 @@ struct of_pci_range { for (; of_pci_range_parser_one(parser, range);) #define for_each_of_range for_each_of_pci_range +/* + * of_range_count - Get the number of "ranges" or "dma-ranges" entries + * @parser: Parser state initialized by of_range_parser_init() + * + * Returns the number of entries or 0 if none. + * + * Note that calling this within or after the for_each_of_range() iterator will + * be inaccurate giving the number of entries remaining. + */ +static inline int of_range_count(const struct of_range_parser *parser) +{ + if (!parser || !parser->node || !parser->range || parser->range == parser->end) + return 0; + return (parser->end - parser->range) / (parser->na + parser->pna + parser->ns); +} + /* Translate a DMA address from device space to CPU space */ extern u64 of_translate_dma_address(struct device_node *dev, const __be32 *in_addr); @@ -56,6 +72,8 @@ void __iomem *of_io_request_and_map(struct device_node *device, extern const __be32 *__of_get_address(struct device_node *dev, int index, int bar_no, u64 *size, unsigned int *flags); +int of_property_read_reg(struct device_node *np, int idx, u64 *addr, u64 *size); + extern int of_pci_range_parser_init(struct of_pci_range_parser *parser, struct device_node *node); extern int of_pci_dma_range_parser_init(struct of_pci_range_parser *parser, @@ -68,6 +86,8 @@ extern int of_pci_address_to_resource(struct device_node *dev, int bar, extern int of_pci_range_to_resource(struct of_pci_range *range, struct device_node *np, struct resource *res); +extern int of_range_to_resource(struct device_node *np, int index, + struct resource *res); extern bool of_dma_is_coherent(struct device_node *np); #else /* CONFIG_OF_ADDRESS */ static inline void __iomem *of_io_request_and_map(struct device_node *device, @@ -88,6 +108,11 @@ static inline const __be32 *__of_get_address(struct device_node *dev, int index, return NULL; } +static inline int of_property_read_reg(struct device_node *np, int idx, u64 *addr, u64 *size) +{ + return -ENOSYS; +} + static inline int of_pci_range_parser_init(struct of_pci_range_parser *parser, struct device_node *node) { @@ -120,6 +145,12 @@ static inline int of_pci_range_to_resource(struct of_pci_range *range, return -ENOSYS; } +static inline int of_range_to_resource(struct device_node *np, int index, + struct resource *res) +{ + return -ENOSYS; +} + static inline bool of_dma_is_coherent(struct device_node *np) { return false; diff --git a/include/linux/of_device.h b/include/linux/of_device.h index f4b57614979d..2c7a3d4bc775 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -2,14 +2,14 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H -#include <linux/cpu.h> #include <linux/platform_device.h> #include <linux/of_platform.h> /* temporary until merge */ #include <linux/of.h> -#include <linux/mod_devicetable.h> struct device; +struct of_device_id; +struct kobj_uevent_env; #ifdef CONFIG_OF extern const struct of_device_id *of_match_device( @@ -26,27 +26,11 @@ static inline int of_driver_match_device(struct device *dev, return of_match_device(drv->of_match_table, dev) != NULL; } -extern int of_device_add(struct platform_device *pdev); -extern int of_device_register(struct platform_device *ofdev); -extern void of_device_unregister(struct platform_device *ofdev); - -extern const void *of_device_get_match_data(const struct device *dev); - extern ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len); -extern int of_device_request_module(struct device *dev); extern void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env); extern int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env); -static inline struct device_node *of_cpu_device_node_get(int cpu) -{ - struct device *cpu_dev; - cpu_dev = get_cpu_device(cpu); - if (!cpu_dev) - return of_get_cpu_node(cpu, NULL); - return of_node_get(cpu_dev->of_node); -} - int of_dma_configure_id(struct device *dev, struct device_node *np, bool force_dma, const u32 *id); @@ -67,22 +51,12 @@ static inline int of_driver_match_device(struct device *dev, static inline void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { } -static inline const void *of_device_get_match_data(const struct device *dev) -{ - return NULL; -} - static inline int of_device_modalias(struct device *dev, char *str, ssize_t len) { return -ENODEV; } -static inline int of_device_request_module(struct device *dev) -{ - return -ENODEV; -} - static inline int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { @@ -95,11 +69,6 @@ static inline const struct of_device_id *of_match_device( return NULL; } -static inline struct device_node *of_cpu_device_node_get(int cpu) -{ - return NULL; -} - static inline int of_dma_configure_id(struct device *dev, struct device_node *np, bool force_dma, diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index 5d58b3b0a97e..d0f66a5e1b2a 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -19,30 +19,9 @@ struct device_node; #ifdef CONFIG_OF_GPIO -#include <linux/container_of.h> - -/* - * OF GPIO chip for memory mapped banks - */ -struct of_mm_gpio_chip { - struct gpio_chip gc; - void (*save_regs)(struct of_mm_gpio_chip *mm_gc); - void __iomem *regs; -}; - -static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc) -{ - return container_of(gc, struct of_mm_gpio_chip, gc); -} - extern int of_get_named_gpio(const struct device_node *np, const char *list_name, int index); -extern int of_mm_gpiochip_add_data(struct device_node *np, - struct of_mm_gpio_chip *mm_gc, - void *data); -extern void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc); - #else /* CONFIG_OF_GPIO */ #include <linux/errno.h> diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index da633d34ab86..8a52ef2e6fa6 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -14,9 +14,25 @@ #if IS_ENABLED(CONFIG_OF_MDIO) bool of_mdiobus_child_is_phy(struct device_node *child); -int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); -int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, - struct device_node *np); +int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, + struct module *owner); + +static inline int of_mdiobus_register(struct mii_bus *mdio, + struct device_node *np) +{ + return __of_mdiobus_register(mdio, np, THIS_MODULE); +} + +int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np, struct module *owner); + +static inline int devm_of_mdiobus_register(struct device *dev, + struct mii_bus *mdio, + struct device_node *np) +{ + return __devm_of_mdiobus_register(dev, mdio, np, THIS_MODULE); +} + struct mdio_device *of_mdio_find_device(struct device_node *np); struct phy_device *of_phy_find_device(struct device_node *phy_np); struct phy_device * diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index d15b6cd5e1c3..d8045bcfc35e 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -6,12 +6,13 @@ * <benh@kernel.crashing.org> */ -#include <linux/device.h> #include <linux/mod_devicetable.h> -#include <linux/pm.h> #include <linux/of_device.h> #include <linux/platform_device.h> +struct device; +struct of_device_id; + /** * struct of_dev_auxdata - lookup table entry for device names & platform_data * @compatible: compatible value of node to match against node @@ -52,6 +53,11 @@ extern const struct of_device_id of_default_bus_match_table[]; extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, struct device *parent); + +extern int of_device_add(struct platform_device *pdev); +extern int of_device_register(struct platform_device *ofdev); +extern void of_device_unregister(struct platform_device *ofdev); + #ifdef CONFIG_OF extern struct platform_device *of_find_device_by_node(struct device_node *np); #else diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a7e3a3405520..92a2063a0a23 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -136,9 +136,6 @@ enum pageflags { PG_arch_2, PG_arch_3, #endif -#ifdef CONFIG_KASAN_HW_TAGS - PG_skip_kasan_poison, -#endif __NR_PAGEFLAGS, PG_readahead = PG_reclaim, @@ -174,9 +171,6 @@ enum pageflags { /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, - /* SLOB */ - PG_slob_free = PG_private, - #ifdef CONFIG_MEMORY_FAILURE /* * Compound pages. Stored in first tail page's flags. @@ -483,7 +477,6 @@ PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) -__PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ @@ -594,12 +587,6 @@ TESTCLEARFLAG(Young, young, PF_ANY) PAGEFLAG(Idle, idle, PF_ANY) #endif -#ifdef CONFIG_KASAN_HW_TAGS -PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD) -#else -PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) -#endif - /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set @@ -630,6 +617,12 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" * refers to user virtual address space into which the page is mapped. + * + * For slab pages, since slab reuses the bits in struct page to store its + * internal states, the page->mapping does not exist as such, nor do these + * flags below. So in order to avoid testing non-existent bits, please + * make sure that PageSlab(page) actually evaluates to false before calling + * the following functions (e.g., PageAnon). See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 @@ -766,11 +759,6 @@ bool set_page_writeback(struct page *page); #define folio_start_writeback_keepwrite(folio) \ __folio_start_writeback(folio, true) -static inline void set_page_writeback_keepwrite(struct page *page) -{ - folio_start_writeback_keepwrite(page_folio(page)); -} - static inline bool test_set_page_writeback(struct page *page) { return set_page_writeback(page); @@ -824,14 +812,9 @@ static inline void ClearPageCompound(struct page *page) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); -int PageHeadHuge(struct page *page); -static inline bool folio_test_hugetlb(struct folio *folio) -{ - return PageHeadHuge(&folio->page); -} +bool folio_test_hugetlb(struct folio *folio); #else TESTPAGEFLAG_FALSE(Huge, hugetlb) -TESTPAGEFLAG_FALSE(HeadHuge, headhuge) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -926,9 +909,14 @@ static inline bool is_page_hwpoison(struct page *page) #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) +static inline int page_type_has_type(unsigned int page_type) +{ + return (int)page_type < PAGE_MAPCOUNT_RESERVE; +} + static inline int page_has_type(struct page *page) { - return (int)page->page_type < PAGE_MAPCOUNT_RESERVE; + return page_type_has_type(page->page_type); } #define PAGE_TYPE_OPS(uname, lname) \ diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index bc2e39090a1f..67314f648aeb 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -29,8 +29,6 @@ struct page_ext_operations { bool need_shared_flags; }; -extern bool deferred_struct_pages; - #ifdef CONFIG_PAGE_EXTENSION /* diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 5f1ae07d724b..e83c4c095041 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -41,14 +41,14 @@ extern unsigned int pageblock_order; * Huge pages are a constant size, but don't exceed the maximum allocation * granularity. */ -#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER - 1) +#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ #else /* CONFIG_HUGETLB_PAGE */ /* If huge pages are not used, group by MAX_ORDER_NR_PAGES */ -#define pageblock_order (MAX_ORDER-1) +#define pageblock_order MAX_ORDER #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0acb8e1fb7af..a56308a9d1a4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -504,9 +504,11 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_NOFS 0x00000010 #define FGP_NOWAIT 0x00000020 #define FGP_FOR_MMAP 0x00000040 -#define FGP_ENTRY 0x00000080 -#define FGP_STABLE 0x00000100 +#define FGP_STABLE 0x00000080 +#define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) + +void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, @@ -520,7 +522,8 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned with an increased refcount. * - * Otherwise, %NULL is returned. + * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for + * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_get_folio(struct address_space *mapping, pgoff_t index) @@ -537,8 +540,8 @@ static inline struct folio *filemap_get_folio(struct address_space *mapping, * present, it is returned locked with an increased refcount. * * Context: May sleep. - * Return: A folio or %NULL if there is no folio in the cache for this - * index. Will not return a shadow, swap or DAX entry. + * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for + * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_lock_folio(struct address_space *mapping, pgoff_t index) @@ -555,8 +558,8 @@ static inline struct folio *filemap_lock_folio(struct address_space *mapping, * a new folio is created. The folio is locked, marked as accessed, and * returned. * - * Return: A found or created folio. NULL if no folio is found and failed to - * create a folio. + * Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found + * and failed to create a folio. */ static inline struct folio *filemap_grab_folio(struct address_space *mapping, pgoff_t index) @@ -1066,12 +1069,6 @@ static inline void folio_cancel_dirty(struct folio *folio) bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); -int __must_check folio_write_one(struct folio *folio); -static inline int __must_check write_one_page(struct page *page) -{ - return folio_write_one(page_folio(page)); -} - int __set_page_dirty_nobuffers(struct page *page); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h deleted file mode 100644 index 58781846f282..000000000000 --- a/include/linux/pata_parport.h +++ /dev/null @@ -1,111 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * pata_parport.h (c) 1997-8 Grant R. Guenther <grant@torque.net> - * Under the terms of the GPL. - * - * This file defines the interface for parallel port IDE adapter chip drivers. - */ - -#ifndef LINUX_PATA_PARPORT_H -#define LINUX_PATA_PARPORT_H - -#include <linux/libata.h> - -#define PI_PCD 1 /* dummy for paride protocol modules */ - -struct pi_adapter { - struct device dev; - struct pi_protocol *proto; /* adapter protocol */ - int port; /* base address of parallel port */ - int mode; /* transfer mode in use */ - int delay; /* adapter delay setting */ - int devtype; /* dummy for paride protocol modules */ - char *device; /* dummy for paride protocol modules */ - int unit; /* unit number for chained adapters */ - int saved_r0; /* saved port state */ - int saved_r2; /* saved port state */ - unsigned long private; /* for protocol module */ - struct pardevice *pardev; /* pointer to pardevice */ -}; - -typedef struct pi_adapter PIA; /* for paride protocol modules */ - -/* registers are addressed as (cont,regr) - * cont: 0 for command register file, 1 for control register(s) - * regr: 0-7 for register number. - */ - -/* macros and functions exported to the protocol modules */ -#define delay_p (pi->delay ? udelay(pi->delay) : (void)0) -#define out_p(offs, byte) do { outb(byte, pi->port + offs); delay_p; } while (0) -#define in_p(offs) (delay_p, inb(pi->port + offs)) - -#define w0(byte) out_p(0, byte) -#define r0() in_p(0) -#define w1(byte) out_p(1, byte) -#define r1() in_p(1) -#define w2(byte) out_p(2, byte) -#define r2() in_p(2) -#define w3(byte) out_p(3, byte) -#define w4(byte) out_p(4, byte) -#define r4() in_p(4) -#define w4w(data) do { outw(data, pi->port + 4); delay_p; } while (0) -#define w4l(data) do { outl(data, pi->port + 4); delay_p; } while (0) -#define r4w() (delay_p, inw(pi->port + 4)) -#define r4l() (delay_p, inl(pi->port + 4)) - -static inline u16 pi_swab16(char *b, int k) -{ - union { u16 u; char t[2]; } r; - - r.t[0] = b[2 * k + 1]; r.t[1] = b[2 * k]; - return r.u; -} - -static inline u32 pi_swab32(char *b, int k) -{ - union { u32 u; char f[4]; } r; - - r.f[0] = b[4 * k + 1]; r.f[1] = b[4 * k]; - r.f[2] = b[4 * k + 3]; r.f[3] = b[4 * k + 2]; - return r.u; -} - -struct pi_protocol { - char name[8]; - - int max_mode; - int epp_first; /* modes >= this use 8 ports */ - - int default_delay; - int max_units; /* max chained units probed for */ - - void (*write_regr)(struct pi_adapter *pi, int cont, int regr, int val); - int (*read_regr)(struct pi_adapter *pi, int cont, int regr); - void (*write_block)(struct pi_adapter *pi, char *buf, int count); - void (*read_block)(struct pi_adapter *pi, char *buf, int count); - - void (*connect)(struct pi_adapter *pi); - void (*disconnect)(struct pi_adapter *pi); - - int (*test_port)(struct pi_adapter *pi); - int (*probe_unit)(struct pi_adapter *pi); - int (*test_proto)(struct pi_adapter *pi, char *scratch, int verbose); - void (*log_adapter)(struct pi_adapter *pi, char *scratch, int verbose); - - int (*init_proto)(struct pi_adapter *pi); - void (*release_proto)(struct pi_adapter *pi); - struct module *owner; - struct device_driver driver; - struct scsi_host_template sht; -}; - -#define PATA_PARPORT_SHT ATA_PIO_SHT - -int pata_parport_register_driver(struct pi_protocol *pr); -void pata_parport_unregister_driver(struct pi_protocol *pr); -/* defines for old paride protocol modules */ -#define paride_register pata_parport_register_driver -#define paride_unregister pata_parport_unregister_driver - -#endif /* LINUX_PATA_PARPORT_H */ diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index ed9b4df792b8..1f14aed4354b 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -13,65 +13,13 @@ #ifndef LINUX_PCI_DOE_H #define LINUX_PCI_DOE_H -struct pci_doe_protocol { - u16 vid; - u8 type; -}; - struct pci_doe_mb; -/** - * struct pci_doe_task - represents a single query/response - * - * @prot: DOE Protocol - * @request_pl: The request payload - * @request_pl_sz: Size of the request payload (bytes) - * @response_pl: The response payload - * @response_pl_sz: Size of the response payload (bytes) - * @rv: Return value. Length of received response or error (bytes) - * @complete: Called when task is complete - * @private: Private data for the consumer - * @work: Used internally by the mailbox - * @doe_mb: Used internally by the mailbox - * - * The payload sizes and rv are specified in bytes with the following - * restrictions concerning the protocol. - * - * 1) The request_pl_sz must be a multiple of double words (4 bytes) - * 2) The response_pl_sz must be >= a single double word (4 bytes) - * 3) rv is returned as bytes but it will be a multiple of double words - * - * NOTE there is no need for the caller to initialize work or doe_mb. - */ -struct pci_doe_task { - struct pci_doe_protocol prot; - u32 *request_pl; - size_t request_pl_sz; - u32 *response_pl; - size_t response_pl_sz; - int rv; - void (*complete)(struct pci_doe_task *task); - void *private; - - /* No need for the user to initialize these fields */ - struct work_struct work; - struct pci_doe_mb *doe_mb; -}; - -/** - * pci_doe_for_each_off - Iterate each DOE capability - * @pdev: struct pci_dev to iterate - * @off: u16 of config space offset of each mailbox capability found - */ -#define pci_doe_for_each_off(pdev, off) \ - for (off = pci_find_next_ext_capability(pdev, off, \ - PCI_EXT_CAP_ID_DOE); \ - off > 0; \ - off = pci_find_next_ext_capability(pdev, off, \ - PCI_EXT_CAP_ID_DOE)) +struct pci_doe_mb *pci_find_doe_mailbox(struct pci_dev *pdev, u16 vendor, + u8 type); -struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); -bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); -int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task); +int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, + const void *request, size_t request_sz, + void *response, size_t response_sz); #endif diff --git a/include/linux/pci.h b/include/linux/pci.h index fafd8020c6d7..60b8772b5bd4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -512,6 +512,9 @@ struct pci_dev { #ifdef CONFIG_PCI_P2PDMA struct pci_p2pdma __rcu *p2pdma; #endif +#ifdef CONFIG_PCI_DOE + struct xarray doe_mbs; /* Data Object Exchange mailboxes */ +#endif u16 acs_cap; /* ACS Capability offset */ phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ @@ -1438,16 +1441,51 @@ void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, unsigned int flags); struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n); void pci_bus_remove_resources(struct pci_bus *bus); +void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); /* Temporary until new and working PCI SBR API in place */ int pci_bridge_secondary_bus_reset(struct pci_dev *dev); -#define pci_bus_for_each_resource(bus, res, i) \ - for (i = 0; \ - (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ - i++) +#define __pci_bus_for_each_res0(bus, res, ...) \ + for (unsigned int __b = 0; \ + (res = pci_bus_resource_n(bus, __b)) || __b < PCI_BRIDGE_RESOURCE_NUM; \ + __b++) + +#define __pci_bus_for_each_res1(bus, res, __b) \ + for (__b = 0; \ + (res = pci_bus_resource_n(bus, __b)) || __b < PCI_BRIDGE_RESOURCE_NUM; \ + __b++) + +/** + * pci_bus_for_each_resource - iterate over PCI bus resources + * @bus: the PCI bus + * @res: pointer to the current resource + * @...: optional index of the current resource + * + * Iterate over PCI bus resources. The first part is to go over PCI bus + * resource array, which has at most the %PCI_BRIDGE_RESOURCE_NUM entries. + * After that continue with the separate list of the additional resources, + * if not empty. That's why the Logical OR is being used. + * + * Possible usage: + * + * struct pci_bus *bus = ...; + * struct resource *res; + * unsigned int i; + * + * // With optional index + * pci_bus_for_each_resource(bus, res, i) + * pr_info("PCI bus resource[%u]: %pR\n", i, res); + * + * // Without index + * pci_bus_for_each_resource(bus, res) + * _do_something_(res); + */ +#define pci_bus_for_each_resource(bus, res, ...) \ + CONCATENATE(__pci_bus_for_each_res, COUNT_ARGS(__VA_ARGS__)) \ + (bus, res, __VA_ARGS__) int __must_check pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res, resource_size_t size, @@ -1623,6 +1661,8 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, flags, NULL); } +static inline bool pci_msix_can_alloc_dyn(struct pci_dev *dev) +{ return false; } static inline struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, const struct irq_affinity_desc *affdesc) { @@ -1994,14 +2034,27 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma); * These helpers provide future and backwards compatibility * for accessing popular PCI BAR info */ -#define pci_resource_start(dev, bar) ((dev)->resource[(bar)].start) -#define pci_resource_end(dev, bar) ((dev)->resource[(bar)].end) -#define pci_resource_flags(dev, bar) ((dev)->resource[(bar)].flags) -#define pci_resource_len(dev,bar) \ - ((pci_resource_end((dev), (bar)) == 0) ? 0 : \ - \ - (pci_resource_end((dev), (bar)) - \ - pci_resource_start((dev), (bar)) + 1)) +#define pci_resource_n(dev, bar) (&(dev)->resource[(bar)]) +#define pci_resource_start(dev, bar) (pci_resource_n(dev, bar)->start) +#define pci_resource_end(dev, bar) (pci_resource_n(dev, bar)->end) +#define pci_resource_flags(dev, bar) (pci_resource_n(dev, bar)->flags) +#define pci_resource_len(dev,bar) \ + (pci_resource_end((dev), (bar)) ? \ + resource_size(pci_resource_n((dev), (bar))) : 0) + +#define __pci_dev_for_each_res0(dev, res, ...) \ + for (unsigned int __b = 0; \ + res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES; \ + __b++) + +#define __pci_dev_for_each_res1(dev, res, __b) \ + for (__b = 0; \ + res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES; \ + __b++) + +#define pci_dev_for_each_resource(dev, res, ...) \ + CONCATENATE(__pci_dev_for_each_res, COUNT_ARGS(__VA_ARGS__)) \ + (dev, res, __VA_ARGS__) /* * Similar to the helpers above, these manipulate per-pci_dev diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 45c3d62e616d..95f33dadb2be 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -567,6 +567,7 @@ #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F3 0x166d #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F3 0x14e3 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F3 0x14f3 +#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F3 0x12fb #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 diff --git a/include/linux/pcs/pcs-mtk-lynxi.h b/include/linux/pcs/pcs-mtk-lynxi.h new file mode 100644 index 000000000000..be3b4ab32f4a --- /dev/null +++ b/include/linux/pcs/pcs-mtk-lynxi.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_PCS_MTK_LYNXI_H +#define __LINUX_PCS_MTK_LYNXI_H + +#include <linux/phylink.h> +#include <linux/regmap.h> + +#define MTK_SGMII_FLAG_PN_SWAP BIT(0) +struct phylink_pcs *mtk_pcs_lynxi_create(struct device *dev, + struct regmap *regmap, + u32 ana_rgc3, u32 flags); +void mtk_pcs_lynxi_destroy(struct phylink_pcs *pcs); +#endif diff --git a/include/linux/pds/pds_adminq.h b/include/linux/pds/pds_adminq.h new file mode 100644 index 000000000000..98a60ce87b92 --- /dev/null +++ b/include/linux/pds/pds_adminq.h @@ -0,0 +1,647 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2023 Advanced Micro Devices, Inc */ + +#ifndef _PDS_CORE_ADMINQ_H_ +#define _PDS_CORE_ADMINQ_H_ + +#define PDSC_ADMINQ_MAX_POLL_INTERVAL 256 + +enum pds_core_adminq_flags { + PDS_AQ_FLAG_FASTPOLL = BIT(1), /* completion poll at 1ms */ +}; + +/* + * enum pds_core_adminq_opcode - AdminQ command opcodes + * These commands are only processed on AdminQ, not available in devcmd + */ +enum pds_core_adminq_opcode { + PDS_AQ_CMD_NOP = 0, + + /* Client control */ + PDS_AQ_CMD_CLIENT_REG = 6, + PDS_AQ_CMD_CLIENT_UNREG = 7, + PDS_AQ_CMD_CLIENT_CMD = 8, + + /* LIF commands */ + PDS_AQ_CMD_LIF_IDENTIFY = 20, + PDS_AQ_CMD_LIF_INIT = 21, + PDS_AQ_CMD_LIF_RESET = 22, + PDS_AQ_CMD_LIF_GETATTR = 23, + PDS_AQ_CMD_LIF_SETATTR = 24, + PDS_AQ_CMD_LIF_SETPHC = 25, + + PDS_AQ_CMD_RX_MODE_SET = 30, + PDS_AQ_CMD_RX_FILTER_ADD = 31, + PDS_AQ_CMD_RX_FILTER_DEL = 32, + + /* Queue commands */ + PDS_AQ_CMD_Q_IDENTIFY = 39, + PDS_AQ_CMD_Q_INIT = 40, + PDS_AQ_CMD_Q_CONTROL = 41, + + /* SR/IOV commands */ + PDS_AQ_CMD_VF_GETATTR = 60, + PDS_AQ_CMD_VF_SETATTR = 61, +}; + +/* + * enum pds_core_notifyq_opcode - NotifyQ event codes + */ +enum pds_core_notifyq_opcode { + PDS_EVENT_LINK_CHANGE = 1, + PDS_EVENT_RESET = 2, + PDS_EVENT_XCVR = 5, + PDS_EVENT_CLIENT = 6, +}; + +#define PDS_COMP_COLOR_MASK 0x80 + +/** + * struct pds_core_notifyq_event - Generic event reporting structure + * @eid: event number + * @ecode: event code + * + * This is the generic event report struct from which the other + * actual events will be formed. + */ +struct pds_core_notifyq_event { + __le64 eid; + __le16 ecode; +}; + +/** + * struct pds_core_link_change_event - Link change event notification + * @eid: event number + * @ecode: event code = PDS_EVENT_LINK_CHANGE + * @link_status: link up/down, with error bits + * @link_speed: speed of the network link + * + * Sent when the network link state changes between UP and DOWN + */ +struct pds_core_link_change_event { + __le64 eid; + __le16 ecode; + __le16 link_status; + __le32 link_speed; /* units of 1Mbps: e.g. 10000 = 10Gbps */ +}; + +/** + * struct pds_core_reset_event - Reset event notification + * @eid: event number + * @ecode: event code = PDS_EVENT_RESET + * @reset_code: reset type + * @state: 0=pending, 1=complete, 2=error + * + * Sent when the NIC or some subsystem is going to be or + * has been reset. + */ +struct pds_core_reset_event { + __le64 eid; + __le16 ecode; + u8 reset_code; + u8 state; +}; + +/** + * struct pds_core_client_event - Client event notification + * @eid: event number + * @ecode: event code = PDS_EVENT_CLIENT + * @client_id: client to sent event to + * @client_event: wrapped event struct for the client + * + * Sent when an event needs to be passed on to a client + */ +struct pds_core_client_event { + __le64 eid; + __le16 ecode; + __le16 client_id; + u8 client_event[54]; +}; + +/** + * struct pds_core_notifyq_cmd - Placeholder for building qcq + * @data: anonymous field for building the qcq + */ +struct pds_core_notifyq_cmd { + __le32 data; /* Not used but needed for qcq structure */ +}; + +/* + * union pds_core_notifyq_comp - Overlay of notifyq event structures + */ +union pds_core_notifyq_comp { + struct { + __le64 eid; + __le16 ecode; + }; + struct pds_core_notifyq_event event; + struct pds_core_link_change_event link_change; + struct pds_core_reset_event reset; + u8 data[64]; +}; + +#define PDS_DEVNAME_LEN 32 +/** + * struct pds_core_client_reg_cmd - Register a new client with DSC + * @opcode: opcode PDS_AQ_CMD_CLIENT_REG + * @rsvd: word boundary padding + * @devname: text name of client device + * @vif_type: what type of device (enum pds_core_vif_types) + * + * Tell the DSC of the new client, and receive a client_id from DSC. + */ +struct pds_core_client_reg_cmd { + u8 opcode; + u8 rsvd[3]; + char devname[PDS_DEVNAME_LEN]; + u8 vif_type; +}; + +/** + * struct pds_core_client_reg_comp - Client registration completion + * @status: Status of the command (enum pdc_core_status_code) + * @rsvd: Word boundary padding + * @comp_index: Index in the descriptor ring for which this is the completion + * @client_id: New id assigned by DSC + * @rsvd1: Word boundary padding + * @color: Color bit + */ +struct pds_core_client_reg_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + __le16 client_id; + u8 rsvd1[9]; + u8 color; +}; + +/** + * struct pds_core_client_unreg_cmd - Unregister a client from DSC + * @opcode: opcode PDS_AQ_CMD_CLIENT_UNREG + * @rsvd: word boundary padding + * @client_id: id of client being removed + * + * Tell the DSC this client is going away and remove its context + * This uses the generic completion. + */ +struct pds_core_client_unreg_cmd { + u8 opcode; + u8 rsvd; + __le16 client_id; +}; + +/** + * struct pds_core_client_request_cmd - Pass along a wrapped client AdminQ cmd + * @opcode: opcode PDS_AQ_CMD_CLIENT_CMD + * @rsvd: word boundary padding + * @client_id: id of client being removed + * @client_cmd: the wrapped client command + * + * Proxy post an adminq command for the client. + * This uses the generic completion. + */ +struct pds_core_client_request_cmd { + u8 opcode; + u8 rsvd; + __le16 client_id; + u8 client_cmd[60]; +}; + +#define PDS_CORE_MAX_FRAGS 16 + +#define PDS_CORE_QCQ_F_INITED BIT(0) +#define PDS_CORE_QCQ_F_SG BIT(1) +#define PDS_CORE_QCQ_F_INTR BIT(2) +#define PDS_CORE_QCQ_F_TX_STATS BIT(3) +#define PDS_CORE_QCQ_F_RX_STATS BIT(4) +#define PDS_CORE_QCQ_F_NOTIFYQ BIT(5) +#define PDS_CORE_QCQ_F_CMB_RINGS BIT(6) +#define PDS_CORE_QCQ_F_CORE BIT(7) + +enum pds_core_lif_type { + PDS_CORE_LIF_TYPE_DEFAULT = 0, +}; + +/** + * union pds_core_lif_config - LIF configuration + * @state: LIF state (enum pds_core_lif_state) + * @rsvd: Word boundary padding + * @name: LIF name + * @rsvd2: Word boundary padding + * @features: LIF features active (enum pds_core_hw_features) + * @queue_count: Queue counts per queue-type + * @words: Full union buffer size + */ +union pds_core_lif_config { + struct { + u8 state; + u8 rsvd[3]; + char name[PDS_CORE_IFNAMSIZ]; + u8 rsvd2[12]; + __le64 features; + __le32 queue_count[PDS_CORE_QTYPE_MAX]; + } __packed; + __le32 words[64]; +}; + +/** + * struct pds_core_lif_status - LIF status register + * @eid: most recent NotifyQ event id + * @rsvd: full struct size + */ +struct pds_core_lif_status { + __le64 eid; + u8 rsvd[56]; +}; + +/** + * struct pds_core_lif_info - LIF info structure + * @config: LIF configuration structure + * @status: LIF status structure + */ +struct pds_core_lif_info { + union pds_core_lif_config config; + struct pds_core_lif_status status; +}; + +/** + * struct pds_core_lif_identity - LIF identity information (type-specific) + * @features: LIF features (see enum pds_core_hw_features) + * @version: Identify structure version + * @hw_index: LIF hardware index + * @rsvd: Word boundary padding + * @max_nb_sessions: Maximum number of sessions supported + * @rsvd2: buffer padding + * @config: LIF config struct with features, q counts + */ +struct pds_core_lif_identity { + __le64 features; + u8 version; + u8 hw_index; + u8 rsvd[2]; + __le32 max_nb_sessions; + u8 rsvd2[120]; + union pds_core_lif_config config; +}; + +/** + * struct pds_core_lif_identify_cmd - Get LIF identity info command + * @opcode: Opcode PDS_AQ_CMD_LIF_IDENTIFY + * @type: LIF type (enum pds_core_lif_type) + * @client_id: Client identifier + * @ver: Version of identify returned by device + * @rsvd: Word boundary padding + * @ident_pa: DMA address to receive identity info + * + * Firmware will copy LIF identity data (struct pds_core_lif_identity) + * into the buffer address given. + */ +struct pds_core_lif_identify_cmd { + u8 opcode; + u8 type; + __le16 client_id; + u8 ver; + u8 rsvd[3]; + __le64 ident_pa; +}; + +/** + * struct pds_core_lif_identify_comp - LIF identify command completion + * @status: Status of the command (enum pds_core_status_code) + * @ver: Version of identify returned by device + * @bytes: Bytes copied into the buffer + * @rsvd: Word boundary padding + * @color: Color bit + */ +struct pds_core_lif_identify_comp { + u8 status; + u8 ver; + __le16 bytes; + u8 rsvd[11]; + u8 color; +}; + +/** + * struct pds_core_lif_init_cmd - LIF init command + * @opcode: Opcode PDS_AQ_CMD_LIF_INIT + * @type: LIF type (enum pds_core_lif_type) + * @client_id: Client identifier + * @rsvd: Word boundary padding + * @info_pa: Destination address for LIF info (struct pds_core_lif_info) + */ +struct pds_core_lif_init_cmd { + u8 opcode; + u8 type; + __le16 client_id; + __le32 rsvd; + __le64 info_pa; +}; + +/** + * struct pds_core_lif_init_comp - LIF init command completion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word boundary padding + * @hw_index: Hardware index of the initialized LIF + * @rsvd1: Word boundary padding + * @color: Color bit + */ +struct pds_core_lif_init_comp { + u8 status; + u8 rsvd; + __le16 hw_index; + u8 rsvd1[11]; + u8 color; +}; + +/** + * struct pds_core_lif_reset_cmd - LIF reset command + * Will reset only the specified LIF. + * @opcode: Opcode PDS_AQ_CMD_LIF_RESET + * @rsvd: Word boundary padding + * @client_id: Client identifier + */ +struct pds_core_lif_reset_cmd { + u8 opcode; + u8 rsvd; + __le16 client_id; +}; + +/** + * enum pds_core_lif_attr - List of LIF attributes + * @PDS_CORE_LIF_ATTR_STATE: LIF state attribute + * @PDS_CORE_LIF_ATTR_NAME: LIF name attribute + * @PDS_CORE_LIF_ATTR_FEATURES: LIF features attribute + * @PDS_CORE_LIF_ATTR_STATS_CTRL: LIF statistics control attribute + */ +enum pds_core_lif_attr { + PDS_CORE_LIF_ATTR_STATE = 0, + PDS_CORE_LIF_ATTR_NAME = 1, + PDS_CORE_LIF_ATTR_FEATURES = 4, + PDS_CORE_LIF_ATTR_STATS_CTRL = 6, +}; + +/** + * struct pds_core_lif_setattr_cmd - Set LIF attributes on the NIC + * @opcode: Opcode PDS_AQ_CMD_LIF_SETATTR + * @attr: Attribute type (enum pds_core_lif_attr) + * @client_id: Client identifier + * @state: LIF state (enum pds_core_lif_state) + * @name: The name string, 0 terminated + * @features: Features (enum pds_core_hw_features) + * @stats_ctl: Stats control commands (enum pds_core_stats_ctl_cmd) + * @rsvd: Command Buffer padding + */ +struct pds_core_lif_setattr_cmd { + u8 opcode; + u8 attr; + __le16 client_id; + union { + u8 state; + char name[PDS_CORE_IFNAMSIZ]; + __le64 features; + u8 stats_ctl; + u8 rsvd[60]; + } __packed; +}; + +/** + * struct pds_core_lif_setattr_comp - LIF set attr command completion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word boundary padding + * @comp_index: Index in the descriptor ring for which this is the completion + * @features: Features (enum pds_core_hw_features) + * @rsvd2: Word boundary padding + * @color: Color bit + */ +struct pds_core_lif_setattr_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + union { + __le64 features; + u8 rsvd2[11]; + } __packed; + u8 color; +}; + +/** + * struct pds_core_lif_getattr_cmd - Get LIF attributes from the NIC + * @opcode: Opcode PDS_AQ_CMD_LIF_GETATTR + * @attr: Attribute type (enum pds_core_lif_attr) + * @client_id: Client identifier + */ +struct pds_core_lif_getattr_cmd { + u8 opcode; + u8 attr; + __le16 client_id; +}; + +/** + * struct pds_core_lif_getattr_comp - LIF get attr command completion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word boundary padding + * @comp_index: Index in the descriptor ring for which this is the completion + * @state: LIF state (enum pds_core_lif_state) + * @name: LIF name string, 0 terminated + * @features: Features (enum pds_core_hw_features) + * @rsvd2: Word boundary padding + * @color: Color bit + */ +struct pds_core_lif_getattr_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + union { + u8 state; + __le64 features; + u8 rsvd2[11]; + } __packed; + u8 color; +}; + +/** + * union pds_core_q_identity - Queue identity information + * @version: Queue type version that can be used with FW + * @supported: Bitfield of queue versions, first bit = ver 0 + * @rsvd: Word boundary padding + * @features: Queue features + * @desc_sz: Descriptor size + * @comp_sz: Completion descriptor size + * @rsvd2: Word boundary padding + */ +struct pds_core_q_identity { + u8 version; + u8 supported; + u8 rsvd[6]; +#define PDS_CORE_QIDENT_F_CQ 0x01 /* queue has completion ring */ + __le64 features; + __le16 desc_sz; + __le16 comp_sz; + u8 rsvd2[6]; +}; + +/** + * struct pds_core_q_identify_cmd - queue identify command + * @opcode: Opcode PDS_AQ_CMD_Q_IDENTIFY + * @type: Logical queue type (enum pds_core_logical_qtype) + * @client_id: Client identifier + * @ver: Highest queue type version that the driver supports + * @rsvd: Word boundary padding + * @ident_pa: DMA address to receive the data (struct pds_core_q_identity) + */ +struct pds_core_q_identify_cmd { + u8 opcode; + u8 type; + __le16 client_id; + u8 ver; + u8 rsvd[3]; + __le64 ident_pa; +}; + +/** + * struct pds_core_q_identify_comp - queue identify command completion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word boundary padding + * @comp_index: Index in the descriptor ring for which this is the completion + * @ver: Queue type version that can be used with FW + * @rsvd1: Word boundary padding + * @color: Color bit + */ +struct pds_core_q_identify_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + u8 ver; + u8 rsvd1[10]; + u8 color; +}; + +/** + * struct pds_core_q_init_cmd - Queue init command + * @opcode: Opcode PDS_AQ_CMD_Q_INIT + * @type: Logical queue type + * @client_id: Client identifier + * @ver: Queue type version + * @rsvd: Word boundary padding + * @index: (LIF, qtype) relative admin queue index + * @intr_index: Interrupt control register index, or Event queue index + * @pid: Process ID + * @flags: + * IRQ: Interrupt requested on completion + * ENA: Enable the queue. If ENA=0 the queue is initialized + * but remains disabled, to be later enabled with the + * Queue Enable command. If ENA=1, then queue is + * initialized and then enabled. + * @cos: Class of service for this queue + * @ring_size: Queue ring size, encoded as a log2(size), in + * number of descriptors. The actual ring size is + * (1 << ring_size). For example, to select a ring size + * of 64 descriptors write ring_size = 6. The minimum + * ring_size value is 2 for a ring of 4 descriptors. + * The maximum ring_size value is 12 for a ring of 4k + * descriptors. Values of ring_size <2 and >12 are + * reserved. + * @ring_base: Queue ring base address + * @cq_ring_base: Completion queue ring base address + */ +struct pds_core_q_init_cmd { + u8 opcode; + u8 type; + __le16 client_id; + u8 ver; + u8 rsvd[3]; + __le32 index; + __le16 pid; + __le16 intr_index; + __le16 flags; +#define PDS_CORE_QINIT_F_IRQ 0x01 /* Request interrupt on completion */ +#define PDS_CORE_QINIT_F_ENA 0x02 /* Enable the queue */ + u8 cos; +#define PDS_CORE_QSIZE_MIN_LG2 2 +#define PDS_CORE_QSIZE_MAX_LG2 12 + u8 ring_size; + __le64 ring_base; + __le64 cq_ring_base; +} __packed; + +/** + * struct pds_core_q_init_comp - Queue init command completion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word boundary padding + * @comp_index: Index in the descriptor ring for which this is the completion + * @hw_index: Hardware Queue ID + * @hw_type: Hardware Queue type + * @rsvd2: Word boundary padding + * @color: Color + */ +struct pds_core_q_init_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + __le32 hw_index; + u8 hw_type; + u8 rsvd2[6]; + u8 color; +}; + +union pds_core_adminq_cmd { + u8 opcode; + u8 bytes[64]; + + struct pds_core_client_reg_cmd client_reg; + struct pds_core_client_unreg_cmd client_unreg; + struct pds_core_client_request_cmd client_request; + + struct pds_core_lif_identify_cmd lif_ident; + struct pds_core_lif_init_cmd lif_init; + struct pds_core_lif_reset_cmd lif_reset; + struct pds_core_lif_setattr_cmd lif_setattr; + struct pds_core_lif_getattr_cmd lif_getattr; + + struct pds_core_q_identify_cmd q_ident; + struct pds_core_q_init_cmd q_init; +}; + +union pds_core_adminq_comp { + struct { + u8 status; + u8 rsvd; + __le16 comp_index; + u8 rsvd2[11]; + u8 color; + }; + u32 words[4]; + + struct pds_core_client_reg_comp client_reg; + + struct pds_core_lif_identify_comp lif_ident; + struct pds_core_lif_init_comp lif_init; + struct pds_core_lif_setattr_comp lif_setattr; + struct pds_core_lif_getattr_comp lif_getattr; + + struct pds_core_q_identify_comp q_ident; + struct pds_core_q_init_comp q_init; +}; + +#ifndef __CHECKER__ +static_assert(sizeof(union pds_core_adminq_cmd) == 64); +static_assert(sizeof(union pds_core_adminq_comp) == 16); +static_assert(sizeof(union pds_core_notifyq_comp) == 64); +#endif /* __CHECKER__ */ + +/* The color bit is a 'done' bit for the completion descriptors + * where the meaning alternates between '1' and '0' for alternating + * passes through the completion descriptor ring. + */ +static inline bool pdsc_color_match(u8 color, bool done_color) +{ + return (!!(color & PDS_COMP_COLOR_MASK)) == done_color; +} + +struct pdsc; +int pdsc_adminq_post(struct pdsc *pdsc, + union pds_core_adminq_cmd *cmd, + union pds_core_adminq_comp *comp, + bool fast_poll); + +#endif /* _PDS_CORE_ADMINQ_H_ */ diff --git a/include/linux/pds/pds_auxbus.h b/include/linux/pds/pds_auxbus.h new file mode 100644 index 000000000000..214ef12302d0 --- /dev/null +++ b/include/linux/pds/pds_auxbus.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2023 Advanced Micro Devices, Inc */ + +#ifndef _PDSC_AUXBUS_H_ +#define _PDSC_AUXBUS_H_ + +#include <linux/auxiliary_bus.h> + +struct pds_auxiliary_dev { + struct auxiliary_device aux_dev; + struct pci_dev *vf_pdev; + u16 client_id; +}; + +int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev, + union pds_core_adminq_cmd *req, + size_t req_len, + union pds_core_adminq_comp *resp, + u64 flags); +#endif /* _PDSC_AUXBUS_H_ */ diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h new file mode 100644 index 000000000000..060331486d50 --- /dev/null +++ b/include/linux/pds/pds_common.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) OR BSD-2-Clause */ +/* Copyright(c) 2023 Advanced Micro Devices, Inc. */ + +#ifndef _PDS_COMMON_H_ +#define _PDS_COMMON_H_ + +#define PDS_CORE_DRV_NAME "pds_core" + +/* the device's internal addressing uses up to 52 bits */ +#define PDS_CORE_ADDR_LEN 52 +#define PDS_CORE_ADDR_MASK (BIT_ULL(PDS_ADDR_LEN) - 1) +#define PDS_PAGE_SIZE 4096 + +enum pds_core_driver_type { + PDS_DRIVER_LINUX = 1, + PDS_DRIVER_WIN = 2, + PDS_DRIVER_DPDK = 3, + PDS_DRIVER_FREEBSD = 4, + PDS_DRIVER_IPXE = 5, + PDS_DRIVER_ESXI = 6, +}; + +enum pds_core_vif_types { + PDS_DEV_TYPE_CORE = 0, + PDS_DEV_TYPE_VDPA = 1, + PDS_DEV_TYPE_VFIO = 2, + PDS_DEV_TYPE_ETH = 3, + PDS_DEV_TYPE_RDMA = 4, + PDS_DEV_TYPE_LM = 5, + + /* new ones added before this line */ + PDS_DEV_TYPE_MAX = 16 /* don't change - used in struct size */ +}; + +#define PDS_DEV_TYPE_CORE_STR "Core" +#define PDS_DEV_TYPE_VDPA_STR "vDPA" +#define PDS_DEV_TYPE_VFIO_STR "VFio" +#define PDS_DEV_TYPE_ETH_STR "Eth" +#define PDS_DEV_TYPE_RDMA_STR "RDMA" +#define PDS_DEV_TYPE_LM_STR "LM" + +#define PDS_CORE_IFNAMSIZ 16 + +/** + * enum pds_core_logical_qtype - Logical Queue Types + * @PDS_CORE_QTYPE_ADMINQ: Administrative Queue + * @PDS_CORE_QTYPE_NOTIFYQ: Notify Queue + * @PDS_CORE_QTYPE_RXQ: Receive Queue + * @PDS_CORE_QTYPE_TXQ: Transmit Queue + * @PDS_CORE_QTYPE_EQ: Event Queue + * @PDS_CORE_QTYPE_MAX: Max queue type supported + */ +enum pds_core_logical_qtype { + PDS_CORE_QTYPE_ADMINQ = 0, + PDS_CORE_QTYPE_NOTIFYQ = 1, + PDS_CORE_QTYPE_RXQ = 2, + PDS_CORE_QTYPE_TXQ = 3, + PDS_CORE_QTYPE_EQ = 4, + + PDS_CORE_QTYPE_MAX = 16 /* don't change - used in struct size */ +}; + +int pdsc_register_notify(struct notifier_block *nb); +void pdsc_unregister_notify(struct notifier_block *nb); +void *pdsc_get_pf_struct(struct pci_dev *vf_pdev); +int pds_client_register(struct pci_dev *pf_pdev, char *devname); +int pds_client_unregister(struct pci_dev *pf_pdev, u16 client_id); +#endif /* _PDS_COMMON_H_ */ diff --git a/include/linux/pds/pds_core_if.h b/include/linux/pds/pds_core_if.h new file mode 100644 index 000000000000..e838a2b90440 --- /dev/null +++ b/include/linux/pds/pds_core_if.h @@ -0,0 +1,571 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) OR BSD-2-Clause */ +/* Copyright(c) 2023 Advanced Micro Devices, Inc. */ + +#ifndef _PDS_CORE_IF_H_ +#define _PDS_CORE_IF_H_ + +#define PCI_VENDOR_ID_PENSANDO 0x1dd8 +#define PCI_DEVICE_ID_PENSANDO_CORE_PF 0x100c +#define PCI_DEVICE_ID_VIRTIO_NET_TRANS 0x1000 +#define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF 0x1003 +#define PCI_DEVICE_ID_PENSANDO_VDPA_VF 0x100b +#define PDS_CORE_BARS_MAX 4 +#define PDS_CORE_PCI_BAR_DBELL 1 + +/* Bar0 */ +#define PDS_CORE_DEV_INFO_SIGNATURE 0x44455649 /* 'DEVI' */ +#define PDS_CORE_BAR0_SIZE 0x8000 +#define PDS_CORE_BAR0_DEV_INFO_REGS_OFFSET 0x0000 +#define PDS_CORE_BAR0_DEV_CMD_REGS_OFFSET 0x0800 +#define PDS_CORE_BAR0_DEV_CMD_DATA_REGS_OFFSET 0x0c00 +#define PDS_CORE_BAR0_INTR_STATUS_OFFSET 0x1000 +#define PDS_CORE_BAR0_INTR_CTRL_OFFSET 0x2000 +#define PDS_CORE_DEV_CMD_DONE 0x00000001 + +#define PDS_CORE_DEVCMD_TIMEOUT 5 + +#define PDS_CORE_CLIENT_ID 0 +#define PDS_CORE_ASIC_TYPE_CAPRI 0 + +/* + * enum pds_core_cmd_opcode - Device commands + */ +enum pds_core_cmd_opcode { + /* Core init */ + PDS_CORE_CMD_NOP = 0, + PDS_CORE_CMD_IDENTIFY = 1, + PDS_CORE_CMD_RESET = 2, + PDS_CORE_CMD_INIT = 3, + + PDS_CORE_CMD_FW_DOWNLOAD = 4, + PDS_CORE_CMD_FW_CONTROL = 5, + + /* SR/IOV commands */ + PDS_CORE_CMD_VF_GETATTR = 60, + PDS_CORE_CMD_VF_SETATTR = 61, + PDS_CORE_CMD_VF_CTRL = 62, + + /* Add commands before this line */ + PDS_CORE_CMD_MAX, + PDS_CORE_CMD_COUNT +}; + +/* + * enum pds_core_status_code - Device command return codes + */ +enum pds_core_status_code { + PDS_RC_SUCCESS = 0, /* Success */ + PDS_RC_EVERSION = 1, /* Incorrect version for request */ + PDS_RC_EOPCODE = 2, /* Invalid cmd opcode */ + PDS_RC_EIO = 3, /* I/O error */ + PDS_RC_EPERM = 4, /* Permission denied */ + PDS_RC_EQID = 5, /* Bad qid */ + PDS_RC_EQTYPE = 6, /* Bad qtype */ + PDS_RC_ENOENT = 7, /* No such element */ + PDS_RC_EINTR = 8, /* operation interrupted */ + PDS_RC_EAGAIN = 9, /* Try again */ + PDS_RC_ENOMEM = 10, /* Out of memory */ + PDS_RC_EFAULT = 11, /* Bad address */ + PDS_RC_EBUSY = 12, /* Device or resource busy */ + PDS_RC_EEXIST = 13, /* object already exists */ + PDS_RC_EINVAL = 14, /* Invalid argument */ + PDS_RC_ENOSPC = 15, /* No space left or alloc failure */ + PDS_RC_ERANGE = 16, /* Parameter out of range */ + PDS_RC_BAD_ADDR = 17, /* Descriptor contains a bad ptr */ + PDS_RC_DEV_CMD = 18, /* Device cmd attempted on AdminQ */ + PDS_RC_ENOSUPP = 19, /* Operation not supported */ + PDS_RC_ERROR = 29, /* Generic error */ + PDS_RC_ERDMA = 30, /* Generic RDMA error */ + PDS_RC_EVFID = 31, /* VF ID does not exist */ + PDS_RC_BAD_FW = 32, /* FW file is invalid or corrupted */ + PDS_RC_ECLIENT = 33, /* No such client id */ +}; + +/** + * struct pds_core_drv_identity - Driver identity information + * @drv_type: Driver type (enum pds_core_driver_type) + * @os_dist: OS distribution, numeric format + * @os_dist_str: OS distribution, string format + * @kernel_ver: Kernel version, numeric format + * @kernel_ver_str: Kernel version, string format + * @driver_ver_str: Driver version, string format + */ +struct pds_core_drv_identity { + __le32 drv_type; + __le32 os_dist; + char os_dist_str[128]; + __le32 kernel_ver; + char kernel_ver_str[32]; + char driver_ver_str[32]; +}; + +#define PDS_DEV_TYPE_MAX 16 +/** + * struct pds_core_dev_identity - Device identity information + * @version: Version of device identify + * @type: Identify type (0 for now) + * @state: Device state + * @rsvd: Word boundary padding + * @nlifs: Number of LIFs provisioned + * @nintrs: Number of interrupts provisioned + * @ndbpgs_per_lif: Number of doorbell pages per LIF + * @intr_coal_mult: Interrupt coalescing multiplication factor + * Scale user-supplied interrupt coalescing + * value in usecs to device units using: + * device units = usecs * mult / div + * @intr_coal_div: Interrupt coalescing division factor + * Scale user-supplied interrupt coalescing + * value in usecs to device units using: + * device units = usecs * mult / div + * @vif_types: How many of each VIF device type is supported + */ +struct pds_core_dev_identity { + u8 version; + u8 type; + u8 state; + u8 rsvd; + __le32 nlifs; + __le32 nintrs; + __le32 ndbpgs_per_lif; + __le32 intr_coal_mult; + __le32 intr_coal_div; + __le16 vif_types[PDS_DEV_TYPE_MAX]; +}; + +#define PDS_CORE_IDENTITY_VERSION_1 1 + +/** + * struct pds_core_dev_identify_cmd - Driver/device identify command + * @opcode: Opcode PDS_CORE_CMD_IDENTIFY + * @ver: Highest version of identify supported by driver + * + * Expects to find driver identification info (struct pds_core_drv_identity) + * in cmd_regs->data. Driver should keep the devcmd interface locked + * while preparing the driver info. + */ +struct pds_core_dev_identify_cmd { + u8 opcode; + u8 ver; +}; + +/** + * struct pds_core_dev_identify_comp - Device identify command completion + * @status: Status of the command (enum pds_core_status_code) + * @ver: Version of identify returned by device + * + * Device identification info (struct pds_core_dev_identity) can be found + * in cmd_regs->data. Driver should keep the devcmd interface locked + * while reading the results. + */ +struct pds_core_dev_identify_comp { + u8 status; + u8 ver; +}; + +/** + * struct pds_core_dev_reset_cmd - Device reset command + * @opcode: Opcode PDS_CORE_CMD_RESET + * + * Resets and clears all LIFs, VDevs, and VIFs on the device. + */ +struct pds_core_dev_reset_cmd { + u8 opcode; +}; + +/** + * struct pds_core_dev_reset_comp - Reset command completion + * @status: Status of the command (enum pds_core_status_code) + */ +struct pds_core_dev_reset_comp { + u8 status; +}; + +/* + * struct pds_core_dev_init_data - Pointers and info needed for the Core + * initialization PDS_CORE_CMD_INIT command. The in and out structs are + * overlays on the pds_core_dev_cmd_regs.data space for passing data down + * to the firmware on init, and then returning initialization results. + */ +struct pds_core_dev_init_data_in { + __le64 adminq_q_base; + __le64 adminq_cq_base; + __le64 notifyq_cq_base; + __le32 flags; + __le16 intr_index; + u8 adminq_ring_size; + u8 notifyq_ring_size; +}; + +struct pds_core_dev_init_data_out { + __le32 core_hw_index; + __le32 adminq_hw_index; + __le32 notifyq_hw_index; + u8 adminq_hw_type; + u8 notifyq_hw_type; +}; + +/** + * struct pds_core_dev_init_cmd - Core device initialize + * @opcode: opcode PDS_CORE_CMD_INIT + * + * Initializes the core device and sets up the AdminQ and NotifyQ. + * Expects to find initialization data (struct pds_core_dev_init_data_in) + * in cmd_regs->data. Driver should keep the devcmd interface locked + * while preparing the driver info. + */ +struct pds_core_dev_init_cmd { + u8 opcode; +}; + +/** + * struct pds_core_dev_init_comp - Core init completion + * @status: Status of the command (enum pds_core_status_code) + * + * Initialization result data (struct pds_core_dev_init_data_in) + * is found in cmd_regs->data. + */ +struct pds_core_dev_init_comp { + u8 status; +}; + +/** + * struct pds_core_fw_download_cmd - Firmware download command + * @opcode: opcode + * @rsvd: Word boundary padding + * @addr: DMA address of the firmware buffer + * @offset: offset of the firmware buffer within the full image + * @length: number of valid bytes in the firmware buffer + */ +struct pds_core_fw_download_cmd { + u8 opcode; + u8 rsvd[3]; + __le32 offset; + __le64 addr; + __le32 length; +}; + +/** + * struct pds_core_fw_download_comp - Firmware download completion + * @status: Status of the command (enum pds_core_status_code) + */ +struct pds_core_fw_download_comp { + u8 status; +}; + +/** + * enum pds_core_fw_control_oper - FW control operations + * @PDS_CORE_FW_INSTALL_ASYNC: Install firmware asynchronously + * @PDS_CORE_FW_INSTALL_STATUS: Firmware installation status + * @PDS_CORE_FW_ACTIVATE_ASYNC: Activate firmware asynchronously + * @PDS_CORE_FW_ACTIVATE_STATUS: Firmware activate status + * @PDS_CORE_FW_UPDATE_CLEANUP: Cleanup any firmware update leftovers + * @PDS_CORE_FW_GET_BOOT: Return current active firmware slot + * @PDS_CORE_FW_SET_BOOT: Set active firmware slot for next boot + * @PDS_CORE_FW_GET_LIST: Return list of installed firmware images + */ +enum pds_core_fw_control_oper { + PDS_CORE_FW_INSTALL_ASYNC = 0, + PDS_CORE_FW_INSTALL_STATUS = 1, + PDS_CORE_FW_ACTIVATE_ASYNC = 2, + PDS_CORE_FW_ACTIVATE_STATUS = 3, + PDS_CORE_FW_UPDATE_CLEANUP = 4, + PDS_CORE_FW_GET_BOOT = 5, + PDS_CORE_FW_SET_BOOT = 6, + PDS_CORE_FW_GET_LIST = 7, +}; + +enum pds_core_fw_slot { + PDS_CORE_FW_SLOT_INVALID = 0, + PDS_CORE_FW_SLOT_A = 1, + PDS_CORE_FW_SLOT_B = 2, + PDS_CORE_FW_SLOT_GOLD = 3, +}; + +/** + * struct pds_core_fw_control_cmd - Firmware control command + * @opcode: opcode + * @rsvd: Word boundary padding + * @oper: firmware control operation (enum pds_core_fw_control_oper) + * @slot: slot to operate on (enum pds_core_fw_slot) + */ +struct pds_core_fw_control_cmd { + u8 opcode; + u8 rsvd[3]; + u8 oper; + u8 slot; +}; + +/** + * struct pds_core_fw_control_comp - Firmware control copletion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word alignment space + * @slot: Slot number (enum pds_core_fw_slot) + * @rsvd1: Struct padding + * @color: Color bit + */ +struct pds_core_fw_control_comp { + u8 status; + u8 rsvd[3]; + u8 slot; + u8 rsvd1[10]; + u8 color; +}; + +struct pds_core_fw_name_info { +#define PDS_CORE_FWSLOT_BUFLEN 8 +#define PDS_CORE_FWVERS_BUFLEN 32 + char slotname[PDS_CORE_FWSLOT_BUFLEN]; + char fw_version[PDS_CORE_FWVERS_BUFLEN]; +}; + +struct pds_core_fw_list_info { +#define PDS_CORE_FWVERS_LIST_LEN 16 + u8 num_fw_slots; + struct pds_core_fw_name_info fw_names[PDS_CORE_FWVERS_LIST_LEN]; +} __packed; + +enum pds_core_vf_attr { + PDS_CORE_VF_ATTR_SPOOFCHK = 1, + PDS_CORE_VF_ATTR_TRUST = 2, + PDS_CORE_VF_ATTR_MAC = 3, + PDS_CORE_VF_ATTR_LINKSTATE = 4, + PDS_CORE_VF_ATTR_VLAN = 5, + PDS_CORE_VF_ATTR_RATE = 6, + PDS_CORE_VF_ATTR_STATSADDR = 7, +}; + +/** + * enum pds_core_vf_link_status - Virtual Function link status + * @PDS_CORE_VF_LINK_STATUS_AUTO: Use link state of the uplink + * @PDS_CORE_VF_LINK_STATUS_UP: Link always up + * @PDS_CORE_VF_LINK_STATUS_DOWN: Link always down + */ +enum pds_core_vf_link_status { + PDS_CORE_VF_LINK_STATUS_AUTO = 0, + PDS_CORE_VF_LINK_STATUS_UP = 1, + PDS_CORE_VF_LINK_STATUS_DOWN = 2, +}; + +/** + * struct pds_core_vf_setattr_cmd - Set VF attributes on the NIC + * @opcode: Opcode + * @attr: Attribute type (enum pds_core_vf_attr) + * @vf_index: VF index + * @macaddr: mac address + * @vlanid: vlan ID + * @maxrate: max Tx rate in Mbps + * @spoofchk: enable address spoof checking + * @trust: enable VF trust + * @linkstate: set link up or down + * @stats: stats addr struct + * @stats.pa: set DMA address for VF stats + * @stats.len: length of VF stats space + * @pad: force union to specific size + */ +struct pds_core_vf_setattr_cmd { + u8 opcode; + u8 attr; + __le16 vf_index; + union { + u8 macaddr[6]; + __le16 vlanid; + __le32 maxrate; + u8 spoofchk; + u8 trust; + u8 linkstate; + struct { + __le64 pa; + __le32 len; + } stats; + u8 pad[60]; + } __packed; +}; + +struct pds_core_vf_setattr_comp { + u8 status; + u8 attr; + __le16 vf_index; + __le16 comp_index; + u8 rsvd[9]; + u8 color; +}; + +/** + * struct pds_core_vf_getattr_cmd - Get VF attributes from the NIC + * @opcode: Opcode + * @attr: Attribute type (enum pds_core_vf_attr) + * @vf_index: VF index + */ +struct pds_core_vf_getattr_cmd { + u8 opcode; + u8 attr; + __le16 vf_index; +}; + +struct pds_core_vf_getattr_comp { + u8 status; + u8 attr; + __le16 vf_index; + union { + u8 macaddr[6]; + __le16 vlanid; + __le32 maxrate; + u8 spoofchk; + u8 trust; + u8 linkstate; + __le64 stats_pa; + u8 pad[11]; + } __packed; + u8 color; +}; + +enum pds_core_vf_ctrl_opcode { + PDS_CORE_VF_CTRL_START_ALL = 0, + PDS_CORE_VF_CTRL_START = 1, +}; + +/** + * struct pds_core_vf_ctrl_cmd - VF control command + * @opcode: Opcode for the command + * @ctrl_opcode: VF control operation type + * @vf_index: VF Index. It is unused if op START_ALL is used. + */ + +struct pds_core_vf_ctrl_cmd { + u8 opcode; + u8 ctrl_opcode; + __le16 vf_index; +}; + +/** + * struct pds_core_vf_ctrl_comp - VF_CTRL command completion. + * @status: Status of the command (enum pds_core_status_code) + */ +struct pds_core_vf_ctrl_comp { + u8 status; +}; + +/* + * union pds_core_dev_cmd - Overlay of core device command structures + */ +union pds_core_dev_cmd { + u8 opcode; + u32 words[16]; + + struct pds_core_dev_identify_cmd identify; + struct pds_core_dev_init_cmd init; + struct pds_core_dev_reset_cmd reset; + struct pds_core_fw_download_cmd fw_download; + struct pds_core_fw_control_cmd fw_control; + + struct pds_core_vf_setattr_cmd vf_setattr; + struct pds_core_vf_getattr_cmd vf_getattr; + struct pds_core_vf_ctrl_cmd vf_ctrl; +}; + +/* + * union pds_core_dev_comp - Overlay of core device completion structures + */ +union pds_core_dev_comp { + u8 status; + u8 bytes[16]; + + struct pds_core_dev_identify_comp identify; + struct pds_core_dev_reset_comp reset; + struct pds_core_dev_init_comp init; + struct pds_core_fw_download_comp fw_download; + struct pds_core_fw_control_comp fw_control; + + struct pds_core_vf_setattr_comp vf_setattr; + struct pds_core_vf_getattr_comp vf_getattr; + struct pds_core_vf_ctrl_comp vf_ctrl; +}; + +/** + * struct pds_core_dev_hwstamp_regs - Hardware current timestamp registers + * @tick_low: Low 32 bits of hardware timestamp + * @tick_high: High 32 bits of hardware timestamp + */ +struct pds_core_dev_hwstamp_regs { + u32 tick_low; + u32 tick_high; +}; + +/** + * struct pds_core_dev_info_regs - Device info register format (read-only) + * @signature: Signature value of 0x44455649 ('DEVI') + * @version: Current version of info + * @asic_type: Asic type + * @asic_rev: Asic revision + * @fw_status: Firmware status + * bit 0 - 1 = fw running + * bit 4-7 - 4 bit generation number, changes on fw restart + * @fw_heartbeat: Firmware heartbeat counter + * @serial_num: Serial number + * @fw_version: Firmware version + * @oprom_regs: oprom_regs to store oprom debug enable/disable and bmp + * @rsvd_pad1024: Struct padding + * @hwstamp: Hardware current timestamp registers + * @rsvd_pad2048: Struct padding + */ +struct pds_core_dev_info_regs { +#define PDS_CORE_DEVINFO_FWVERS_BUFLEN 32 +#define PDS_CORE_DEVINFO_SERIAL_BUFLEN 32 + u32 signature; + u8 version; + u8 asic_type; + u8 asic_rev; +#define PDS_CORE_FW_STS_F_STOPPED 0x00 +#define PDS_CORE_FW_STS_F_RUNNING 0x01 +#define PDS_CORE_FW_STS_F_GENERATION 0xF0 + u8 fw_status; + __le32 fw_heartbeat; + char fw_version[PDS_CORE_DEVINFO_FWVERS_BUFLEN]; + char serial_num[PDS_CORE_DEVINFO_SERIAL_BUFLEN]; + u8 oprom_regs[32]; /* reserved */ + u8 rsvd_pad1024[916]; + struct pds_core_dev_hwstamp_regs hwstamp; /* on 1k boundary */ + u8 rsvd_pad2048[1016]; +} __packed; + +/** + * struct pds_core_dev_cmd_regs - Device command register format (read-write) + * @doorbell: Device Cmd Doorbell, write-only + * Write a 1 to signal device to process cmd + * @done: Command completed indicator, poll for completion + * bit 0 == 1 when command is complete + * @cmd: Opcode-specific command bytes + * @comp: Opcode-specific response bytes + * @rsvd: Struct padding + * @data: Opcode-specific side-data + */ +struct pds_core_dev_cmd_regs { + u32 doorbell; + u32 done; + union pds_core_dev_cmd cmd; + union pds_core_dev_comp comp; + u8 rsvd[48]; + u32 data[478]; +} __packed; + +/** + * struct pds_core_dev_regs - Device register format for bar 0 page 0 + * @info: Device info registers + * @devcmd: Device command registers + */ +struct pds_core_dev_regs { + struct pds_core_dev_info_regs info; + struct pds_core_dev_cmd_regs devcmd; +} __packed; + +#ifndef __CHECKER__ +static_assert(sizeof(struct pds_core_drv_identity) <= 1912); +static_assert(sizeof(struct pds_core_dev_identity) <= 1912); +static_assert(sizeof(union pds_core_dev_cmd) == 64); +static_assert(sizeof(union pds_core_dev_comp) == 16); +static_assert(sizeof(struct pds_core_dev_info_regs) == 2048); +static_assert(sizeof(struct pds_core_dev_cmd_regs) == 2048); +static_assert(sizeof(struct pds_core_dev_regs) == 4096); +#endif /* __CHECKER__ */ + +#endif /* _PDS_CORE_IF_H_ */ diff --git a/include/linux/pds/pds_intr.h b/include/linux/pds/pds_intr.h new file mode 100644 index 000000000000..56277c37248c --- /dev/null +++ b/include/linux/pds/pds_intr.h @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) OR BSD-2-Clause */ +/* Copyright(c) 2023 Advanced Micro Devices, Inc. */ + +#ifndef _PDS_INTR_H_ +#define _PDS_INTR_H_ + +/* + * Interrupt control register + * @coal_init: Coalescing timer initial value, in + * device units. Use @identity->intr_coal_mult + * and @identity->intr_coal_div to convert from + * usecs to device units: + * + * coal_init = coal_usecs * coal_mutl / coal_div + * + * When an interrupt is sent the interrupt + * coalescing timer current value + * (@coalescing_curr) is initialized with this + * value and begins counting down. No more + * interrupts are sent until the coalescing + * timer reaches 0. When @coalescing_init=0 + * interrupt coalescing is effectively disabled + * and every interrupt assert results in an + * interrupt. Reset value: 0 + * @mask: Interrupt mask. When @mask=1 the interrupt + * resource will not send an interrupt. When + * @mask=0 the interrupt resource will send an + * interrupt if an interrupt event is pending + * or on the next interrupt assertion event. + * Reset value: 1 + * @credits: Interrupt credits. This register indicates + * how many interrupt events the hardware has + * sent. When written by software this + * register atomically decrements @int_credits + * by the value written. When @int_credits + * becomes 0 then the "pending interrupt" bit + * in the Interrupt Status register is cleared + * by the hardware and any pending but unsent + * interrupts are cleared. + * !!!IMPORTANT!!! This is a signed register. + * @flags: Interrupt control flags + * @unmask -- When this bit is written with a 1 + * the interrupt resource will set mask=0. + * @coal_timer_reset -- When this + * bit is written with a 1 the + * @coalescing_curr will be reloaded with + * @coalescing_init to reset the coalescing + * timer. + * @mask_on_assert: Automatically mask on assertion. When + * @mask_on_assert=1 the interrupt resource + * will set @mask=1 whenever an interrupt is + * sent. When using interrupts in Legacy + * Interrupt mode the driver must select + * @mask_on_assert=0 for proper interrupt + * operation. + * @coalescing_curr: Coalescing timer current value, in + * microseconds. When this value reaches 0 + * the interrupt resource is again eligible to + * send an interrupt. If an interrupt event + * is already pending when @coalescing_curr + * reaches 0 the pending interrupt will be + * sent, otherwise an interrupt will be sent + * on the next interrupt assertion event. + */ +struct pds_core_intr { + u32 coal_init; + u32 mask; + u16 credits; + u16 flags; +#define PDS_CORE_INTR_F_UNMASK 0x0001 +#define PDS_CORE_INTR_F_TIMER_RESET 0x0002 + u32 mask_on_assert; + u32 coalescing_curr; + u32 rsvd6[3]; +}; + +#ifndef __CHECKER__ +static_assert(sizeof(struct pds_core_intr) == 32); +#endif /* __CHECKER__ */ + +#define PDS_CORE_INTR_CTRL_REGS_MAX 2048 +#define PDS_CORE_INTR_CTRL_COAL_MAX 0x3F +#define PDS_CORE_INTR_INDEX_NOT_ASSIGNED -1 + +struct pds_core_intr_status { + u32 status[2]; +}; + +/** + * enum pds_core_intr_mask_vals - valid values for mask and mask_assert. + * @PDS_CORE_INTR_MASK_CLEAR: unmask interrupt. + * @PDS_CORE_INTR_MASK_SET: mask interrupt. + */ +enum pds_core_intr_mask_vals { + PDS_CORE_INTR_MASK_CLEAR = 0, + PDS_CORE_INTR_MASK_SET = 1, +}; + +/** + * enum pds_core_intr_credits_bits - Bitwise composition of credits values. + * @PDS_CORE_INTR_CRED_COUNT: bit mask of credit count, no shift needed. + * @PDS_CORE_INTR_CRED_COUNT_SIGNED: bit mask of credit count, including sign bit. + * @PDS_CORE_INTR_CRED_UNMASK: unmask the interrupt. + * @PDS_CORE_INTR_CRED_RESET_COALESCE: reset the coalesce timer. + * @PDS_CORE_INTR_CRED_REARM: unmask the and reset the timer. + */ +enum pds_core_intr_credits_bits { + PDS_CORE_INTR_CRED_COUNT = 0x7fffu, + PDS_CORE_INTR_CRED_COUNT_SIGNED = 0xffffu, + PDS_CORE_INTR_CRED_UNMASK = 0x10000u, + PDS_CORE_INTR_CRED_RESET_COALESCE = 0x20000u, + PDS_CORE_INTR_CRED_REARM = (PDS_CORE_INTR_CRED_UNMASK | + PDS_CORE_INTR_CRED_RESET_COALESCE), +}; + +static inline void +pds_core_intr_coal_init(struct pds_core_intr __iomem *intr_ctrl, u32 coal) +{ + iowrite32(coal, &intr_ctrl->coal_init); +} + +static inline void +pds_core_intr_mask(struct pds_core_intr __iomem *intr_ctrl, u32 mask) +{ + iowrite32(mask, &intr_ctrl->mask); +} + +static inline void +pds_core_intr_credits(struct pds_core_intr __iomem *intr_ctrl, + u32 cred, u32 flags) +{ + if (WARN_ON_ONCE(cred > PDS_CORE_INTR_CRED_COUNT)) { + cred = ioread32(&intr_ctrl->credits); + cred &= PDS_CORE_INTR_CRED_COUNT_SIGNED; + } + + iowrite32(cred | flags, &intr_ctrl->credits); +} + +static inline void +pds_core_intr_clean_flags(struct pds_core_intr __iomem *intr_ctrl, u32 flags) +{ + u32 cred; + + cred = ioread32(&intr_ctrl->credits); + cred &= PDS_CORE_INTR_CRED_COUNT_SIGNED; + cred |= flags; + iowrite32(cred, &intr_ctrl->credits); +} + +static inline void +pds_core_intr_clean(struct pds_core_intr __iomem *intr_ctrl) +{ + pds_core_intr_clean_flags(intr_ctrl, PDS_CORE_INTR_CRED_RESET_COALESCE); +} + +static inline void +pds_core_intr_mask_assert(struct pds_core_intr __iomem *intr_ctrl, u32 mask) +{ + iowrite32(mask, &intr_ctrl->mask_on_assert); +} + +#endif /* _PDS_INTR_H_ */ diff --git a/include/linux/pe.h b/include/linux/pe.h index 6ffabf1e6d03..fdf9c95709ba 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -11,25 +11,26 @@ #include <linux/types.h> /* - * Linux EFI stub v1.0 adds the following functionality: - * - Loading initrd from the LINUX_EFI_INITRD_MEDIA_GUID device path, - * - Loading/starting the kernel from firmware that targets a different - * machine type, via the entrypoint exposed in the .compat PE/COFF section. + * Starting from version v3.0, the major version field should be interpreted as + * a bit mask of features supported by the kernel's EFI stub: + * - 0x1: initrd loading from the LINUX_EFI_INITRD_MEDIA_GUID device path, + * - 0x2: initrd loading using the initrd= command line option, where the file + * may be specified using device path notation, and is not required to + * reside on the same volume as the loaded kernel image. * * The recommended way of loading and starting v1.0 or later kernels is to use * the LoadImage() and StartImage() EFI boot services, and expose the initrd * via the LINUX_EFI_INITRD_MEDIA_GUID device path. * - * Versions older than v1.0 support initrd loading via the image load options - * (using initrd=, limited to the volume from which the kernel itself was - * loaded), or via arch specific means (bootparams, DT, etc). + * Versions older than v1.0 may support initrd loading via the image load + * options (using initrd=, limited to the volume from which the kernel itself + * was loaded), or only via arch specific means (bootparams, DT, etc). * - * On x86, LoadImage() and StartImage() can be omitted if the EFI handover - * protocol is implemented, which can be inferred from the version, - * handover_offset and xloadflags fields in the bootparams structure. + * The minor version field must remain 0x0. + * (https://lore.kernel.org/all/efd6f2d4-547c-1378-1faa-53c044dbd297@gmail.com/) */ -#define LINUX_EFISTUB_MAJOR_VERSION 0x1 -#define LINUX_EFISTUB_MINOR_VERSION 0x1 +#define LINUX_EFISTUB_MAJOR_VERSION 0x3 +#define LINUX_EFISTUB_MINOR_VERSION 0x0 /* * LINUX_PE_MAGIC appears at offset 0x38 into the MS-DOS header of EFI bootable @@ -118,6 +119,9 @@ #define IMAGE_DLLCHARACTERISTICS_WDM_DRIVER 0x2000 #define IMAGE_DLLCHARACTERISTICS_TERMINAL_SERVER_AWARE 0x8000 +#define IMAGE_DLLCHARACTERISTICS_EX_CET_COMPAT 0x0001 +#define IMAGE_DLLCHARACTERISTICS_EX_FORWARD_CFI_COMPAT 0x0040 + /* they actually defined 0x00000000 as well, but I think we'll skip that one. */ #define IMAGE_SCN_RESERVED_0 0x00000001 #define IMAGE_SCN_RESERVED_1 0x00000002 @@ -165,6 +169,7 @@ #define IMAGE_SCN_MEM_WRITE 0x80000000 /* writeable */ #define IMAGE_DEBUG_TYPE_CODEVIEW 2 +#define IMAGE_DEBUG_TYPE_EX_DLLCHARACTERISTICS 20 #ifndef __ASSEMBLY__ diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 521a733e21a9..75b73c83bc9d 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -45,7 +45,6 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); -s64 percpu_counter_sum_all(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); @@ -196,11 +195,6 @@ static inline s64 percpu_counter_sum(struct percpu_counter *fbc) return percpu_counter_read(fbc); } -static inline s64 percpu_counter_sum_all(struct percpu_counter *fbc) -{ - return percpu_counter_read(fbc); -} - static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return true; diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h new file mode 100644 index 000000000000..e3899bd77f5c --- /dev/null +++ b/include/linux/perf/arm_pmuv3.h @@ -0,0 +1,303 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2012 ARM Ltd. + */ + +#ifndef __PERF_ARM_PMUV3_H +#define __PERF_ARM_PMUV3_H + +#define ARMV8_PMU_MAX_COUNTERS 32 +#define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1) + +/* + * Common architectural and microarchitectural event numbers. + */ +#define ARMV8_PMUV3_PERFCTR_SW_INCR 0x0000 +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL 0x0001 +#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL 0x0002 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL 0x0003 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE 0x0004 +#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL 0x0005 +#define ARMV8_PMUV3_PERFCTR_LD_RETIRED 0x0006 +#define ARMV8_PMUV3_PERFCTR_ST_RETIRED 0x0007 +#define ARMV8_PMUV3_PERFCTR_INST_RETIRED 0x0008 +#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN 0x0009 +#define ARMV8_PMUV3_PERFCTR_EXC_RETURN 0x000A +#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED 0x000B +#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED 0x000C +#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED 0x000D +#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED 0x000E +#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED 0x000F +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED 0x0010 +#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES 0x0011 +#define ARMV8_PMUV3_PERFCTR_BR_PRED 0x0012 +#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS 0x0013 +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE 0x0014 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB 0x0015 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE 0x0016 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL 0x0017 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB 0x0018 +#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS 0x0019 +#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR 0x001A +#define ARMV8_PMUV3_PERFCTR_INST_SPEC 0x001B +#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED 0x001C +#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES 0x001D +#define ARMV8_PMUV3_PERFCTR_CHAIN 0x001E +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE 0x001F +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE 0x0020 +#define ARMV8_PMUV3_PERFCTR_BR_RETIRED 0x0021 +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED 0x0022 +#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND 0x0023 +#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND 0x0024 +#define ARMV8_PMUV3_PERFCTR_L1D_TLB 0x0025 +#define ARMV8_PMUV3_PERFCTR_L1I_TLB 0x0026 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE 0x0027 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL 0x0028 +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE 0x0029 +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL 0x002A +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE 0x002B +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB 0x002C +#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL 0x002D +#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL 0x002E +#define ARMV8_PMUV3_PERFCTR_L2D_TLB 0x002F +#define ARMV8_PMUV3_PERFCTR_L2I_TLB 0x0030 +#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS 0x0031 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE 0x0032 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS 0x0033 +#define ARMV8_PMUV3_PERFCTR_DTLB_WALK 0x0034 +#define ARMV8_PMUV3_PERFCTR_ITLB_WALK 0x0035 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD 0x0036 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD 0x0037 +#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD 0x0038 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD 0x0039 +#define ARMV8_PMUV3_PERFCTR_OP_RETIRED 0x003A +#define ARMV8_PMUV3_PERFCTR_OP_SPEC 0x003B +#define ARMV8_PMUV3_PERFCTR_STALL 0x003C +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND 0x003D +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND 0x003E +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT 0x003F + +/* Statistical profiling extension microarchitectural events */ +#define ARMV8_SPE_PERFCTR_SAMPLE_POP 0x4000 +#define ARMV8_SPE_PERFCTR_SAMPLE_FEED 0x4001 +#define ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE 0x4002 +#define ARMV8_SPE_PERFCTR_SAMPLE_COLLISION 0x4003 + +/* AMUv1 architecture events */ +#define ARMV8_AMU_PERFCTR_CNT_CYCLES 0x4004 +#define ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM 0x4005 + +/* long-latency read miss events */ +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS 0x4006 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD 0x4009 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS 0x400A +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD 0x400B + +/* Trace buffer events */ +#define ARMV8_PMUV3_PERFCTR_TRB_WRAP 0x400C +#define ARMV8_PMUV3_PERFCTR_TRB_TRIG 0x400E + +/* Trace unit events */ +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT0 0x4010 +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT1 0x4011 +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT2 0x4012 +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT3 0x4013 +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT4 0x4018 +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT5 0x4019 +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT6 0x401A +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT7 0x401B + +/* additional latency from alignment events */ +#define ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT 0x4020 +#define ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT 0x4021 +#define ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT 0x4022 + +/* Armv8.5 Memory Tagging Extension events */ +#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED 0x4024 +#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD 0x4025 +#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR 0x4026 + +/* ARMv8 recommended implementation defined event types */ +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD 0x0040 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR 0x0041 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD 0x0042 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR 0x0043 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER 0x0044 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER 0x0045 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM 0x0046 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN 0x0047 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL 0x0048 + +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD 0x004C +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR 0x004D +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD 0x004E +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR 0x004F +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD 0x0050 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR 0x0051 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD 0x0052 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR 0x0053 + +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM 0x0056 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN 0x0057 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL 0x0058 + +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD 0x005C +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR 0x005D +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD 0x005E +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR 0x005F +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD 0x0060 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR 0x0061 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED 0x0062 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED 0x0063 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL 0x0064 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH 0x0065 +#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD 0x0066 +#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR 0x0067 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC 0x0068 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC 0x0069 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC 0x006A + +#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC 0x006C +#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC 0x006D +#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC 0x006E +#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC 0x006F +#define ARMV8_IMPDEF_PERFCTR_LD_SPEC 0x0070 +#define ARMV8_IMPDEF_PERFCTR_ST_SPEC 0x0071 +#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC 0x0072 +#define ARMV8_IMPDEF_PERFCTR_DP_SPEC 0x0073 +#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC 0x0074 +#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC 0x0075 +#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC 0x0076 +#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC 0x0077 +#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC 0x0078 +#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC 0x0079 +#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC 0x007A + +#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC 0x007C +#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC 0x007D +#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC 0x007E + +#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF 0x0081 +#define ARMV8_IMPDEF_PERFCTR_EXC_SVC 0x0082 +#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT 0x0083 +#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT 0x0084 + +#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ 0x0086 +#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ 0x0087 +#define ARMV8_IMPDEF_PERFCTR_EXC_SMC 0x0088 + +#define ARMV8_IMPDEF_PERFCTR_EXC_HVC 0x008A +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT 0x008B +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT 0x008C +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER 0x008D +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ 0x008E +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ 0x008F +#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC 0x0090 +#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC 0x0091 + +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD 0x00A0 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR 0x00A1 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD 0x00A2 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR 0x00A3 + +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM 0x00A6 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN 0x00A7 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL 0x00A8 + +/* + * Per-CPU PMCR: config reg + */ +#define ARMV8_PMU_PMCR_E (1 << 0) /* Enable all counters */ +#define ARMV8_PMU_PMCR_P (1 << 1) /* Reset all counters */ +#define ARMV8_PMU_PMCR_C (1 << 2) /* Cycle counter reset */ +#define ARMV8_PMU_PMCR_D (1 << 3) /* CCNT counts every 64th cpu cycle */ +#define ARMV8_PMU_PMCR_X (1 << 4) /* Export to ETM */ +#define ARMV8_PMU_PMCR_DP (1 << 5) /* Disable CCNT if non-invasive debug*/ +#define ARMV8_PMU_PMCR_LC (1 << 6) /* Overflow on 64 bit cycle counter */ +#define ARMV8_PMU_PMCR_LP (1 << 7) /* Long event counter enable */ +#define ARMV8_PMU_PMCR_N_SHIFT 11 /* Number of counters supported */ +#define ARMV8_PMU_PMCR_N_MASK 0x1f +#define ARMV8_PMU_PMCR_MASK 0xff /* Mask for writable bits */ + +/* + * PMOVSR: counters overflow flag status reg + */ +#define ARMV8_PMU_OVSR_MASK 0xffffffff /* Mask for writable bits */ +#define ARMV8_PMU_OVERFLOWED_MASK ARMV8_PMU_OVSR_MASK + +/* + * PMXEVTYPER: Event selection reg + */ +#define ARMV8_PMU_EVTYPE_MASK 0xc800ffff /* Mask for writable bits */ +#define ARMV8_PMU_EVTYPE_EVENT 0xffff /* Mask for EVENT bits */ + +/* + * Event filters for PMUv3 + */ +#define ARMV8_PMU_EXCLUDE_EL1 (1U << 31) +#define ARMV8_PMU_EXCLUDE_EL0 (1U << 30) +#define ARMV8_PMU_INCLUDE_EL2 (1U << 27) + +/* + * PMUSERENR: user enable reg + */ +#define ARMV8_PMU_USERENR_MASK 0xf /* Mask for writable bits */ +#define ARMV8_PMU_USERENR_EN (1 << 0) /* PMU regs can be accessed at EL0 */ +#define ARMV8_PMU_USERENR_SW (1 << 1) /* PMSWINC can be written at EL0 */ +#define ARMV8_PMU_USERENR_CR (1 << 2) /* Cycle counter can be read at EL0 */ +#define ARMV8_PMU_USERENR_ER (1 << 3) /* Event counter can be read at EL0 */ + +/* PMMIR_EL1.SLOTS mask */ +#define ARMV8_PMU_SLOTS_MASK 0xff + +#define ARMV8_PMU_BUS_SLOTS_SHIFT 8 +#define ARMV8_PMU_BUS_SLOTS_MASK 0xff +#define ARMV8_PMU_BUS_WIDTH_SHIFT 16 +#define ARMV8_PMU_BUS_WIDTH_MASK 0xf + +/* + * This code is really good + */ + +#define PMEVN_CASE(n, case_macro) \ + case n: case_macro(n); break + +#define PMEVN_SWITCH(x, case_macro) \ + do { \ + switch (x) { \ + PMEVN_CASE(0, case_macro); \ + PMEVN_CASE(1, case_macro); \ + PMEVN_CASE(2, case_macro); \ + PMEVN_CASE(3, case_macro); \ + PMEVN_CASE(4, case_macro); \ + PMEVN_CASE(5, case_macro); \ + PMEVN_CASE(6, case_macro); \ + PMEVN_CASE(7, case_macro); \ + PMEVN_CASE(8, case_macro); \ + PMEVN_CASE(9, case_macro); \ + PMEVN_CASE(10, case_macro); \ + PMEVN_CASE(11, case_macro); \ + PMEVN_CASE(12, case_macro); \ + PMEVN_CASE(13, case_macro); \ + PMEVN_CASE(14, case_macro); \ + PMEVN_CASE(15, case_macro); \ + PMEVN_CASE(16, case_macro); \ + PMEVN_CASE(17, case_macro); \ + PMEVN_CASE(18, case_macro); \ + PMEVN_CASE(19, case_macro); \ + PMEVN_CASE(20, case_macro); \ + PMEVN_CASE(21, case_macro); \ + PMEVN_CASE(22, case_macro); \ + PMEVN_CASE(23, case_macro); \ + PMEVN_CASE(24, case_macro); \ + PMEVN_CASE(25, case_macro); \ + PMEVN_CASE(26, case_macro); \ + PMEVN_CASE(27, case_macro); \ + PMEVN_CASE(28, case_macro); \ + PMEVN_CASE(29, case_macro); \ + PMEVN_CASE(30, case_macro); \ + default: WARN(1, "Invalid PMEV* index\n"); \ + } \ + } while (0) + +#endif diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d5628a7b5eaa..c8dcfdbda1f4 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1845,9 +1845,9 @@ int perf_event_exit_cpu(unsigned int cpu); #define perf_event_exit_cpu NULL #endif -extern void __weak arch_perf_update_userpage(struct perf_event *event, - struct perf_event_mmap_page *userpg, - u64 now); +extern void arch_perf_update_userpage(struct perf_event *event, + struct perf_event_mmap_page *userpg, + u64 now); #ifdef CONFIG_MMU extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index c63cd44777ec..c5a51481bbb9 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -817,7 +817,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) #endif #ifndef flush_tlb_fix_spurious_fault -#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) +#define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address) #endif /* @@ -1191,9 +1191,10 @@ static inline void untrack_pfn(struct vm_area_struct *vma, } /* - * untrack_pfn_moved is called while mremapping a pfnmap for a new region. + * untrack_pfn_clear is called while mremapping a pfnmap for a new region + * or fails to copy pgtable during duplicate vm area. */ -static inline void untrack_pfn_moved(struct vm_area_struct *vma) +static inline void untrack_pfn_clear(struct vm_area_struct *vma) { } #else @@ -1205,7 +1206,7 @@ extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked); -extern void untrack_pfn_moved(struct vm_area_struct *vma); +extern void untrack_pfn_clear(struct vm_area_struct *vma); #endif #ifdef CONFIG_MMU diff --git a/include/linux/phy.h b/include/linux/phy.h index 36bf0bbc8efa..6478838405a0 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -14,6 +14,7 @@ #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/ethtool.h> +#include <linux/leds.h> #include <linux/linkmode.h> #include <linux/netlink.h> #include <linux/mdio.h> @@ -600,6 +601,7 @@ struct macsec_ops; * @phy_num_led_triggers: Number of triggers in @phy_led_triggers * @led_link_trigger: LED trigger for link up/down * @last_triggered: last LED trigger for link speed + * @leds: list of PHY LED structures * @master_slave_set: User requested master/slave configuration * @master_slave_get: Current master/slave advertisement * @master_slave_state: Current master/slave configuration @@ -699,6 +701,7 @@ struct phy_device { struct phy_led_trigger *led_link_trigger; #endif + struct list_head leds; /* * Interrupt number for this PHY @@ -835,6 +838,23 @@ struct phy_plca_status { }; /** + * struct phy_led: An LED driven by the PHY + * + * @list: List of LEDs + * @phydev: PHY this LED is attached to + * @led_cdev: Standard LED class structure + * @index: Number of the LED + */ +struct phy_led { + struct list_head list; + struct phy_device *phydev; + struct led_classdev led_cdev; + u8 index; +}; + +#define to_phy_led(d) container_of(d, struct phy_led, led_cdev) + +/** * struct phy_driver - Driver structure for a particular PHY type * * @mdiodrv: Data common to all MDIO devices @@ -1056,6 +1076,27 @@ struct phy_driver { /** @get_plca_status: Return the current PLCA status info */ int (*get_plca_status)(struct phy_device *dev, struct phy_plca_status *plca_st); + + /** + * @led_brightness_set: Set a PHY LED brightness. Index + * indicates which of the PHYs led should be set. Value + * follows the standard LED class meaning, e.g. LED_OFF, + * LED_HALF, LED_FULL. + */ + int (*led_brightness_set)(struct phy_device *dev, + u8 index, enum led_brightness value); + + /** + * @led_blink_set: Set a PHY LED brightness. Index indicates + * which of the PHYs led should be configured to blink. Delays + * are in milliseconds and if both are zero then a sensible + * default should be chosen. The call should adjust the + * timings in that case and if it can't match the values + * specified exactly. + */ + int (*led_blink_set)(struct phy_device *dev, u8 index, + unsigned long *delay_on, + unsigned long *delay_off); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) @@ -1130,16 +1171,15 @@ static inline int phy_read(struct phy_device *phydev, u32 regnum) #define phy_read_poll_timeout(phydev, regnum, val, cond, sleep_us, \ timeout_us, sleep_before_read) \ ({ \ - int __ret = read_poll_timeout(phy_read, val, (cond) || val < 0, \ + int __ret = read_poll_timeout(phy_read, val, val < 0 || (cond), \ sleep_us, timeout_us, sleep_before_read, phydev, regnum); \ - if (val < 0) \ + if (val < 0) \ __ret = val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ }) - /** * __phy_read - convenience function for reading a given PHY register * @phydev: the phy_device struct @@ -1547,7 +1587,7 @@ int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct phy_device *device_phy_find_device(struct device *dev); -struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); @@ -1860,10 +1900,8 @@ void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, int addr, size_t priv_size); -#if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); -#endif int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index c492c26202b5..71755c66c162 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -93,7 +93,6 @@ static inline bool phylink_autoneg_inband(unsigned int mode) * the medium link mode (@speed and @duplex) and the speed/duplex of the phy * interface mode (@interface) are different. * @link: true if the link is up. - * @an_enabled: true if autonegotiation is enabled/desired. * @an_complete: true if autonegotiation has completed. */ struct phylink_link_state { @@ -105,7 +104,6 @@ struct phylink_link_state { int pause; int rate_matching; unsigned int link:1; - unsigned int an_enabled:1; unsigned int an_complete:1; }; @@ -574,6 +572,7 @@ struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); void phylink_destroy(struct phylink *); +bool phylink_expects_phy(struct phylink *pl); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); diff --git a/include/linux/pid.h b/include/linux/pid.h index 343abf22092e..b75de288a8c2 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -80,6 +80,7 @@ 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); +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); static inline struct pid *get_pid(struct pid *pid) { diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 7e9c76aedd2d..ab721cf13a98 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -2701,7 +2701,7 @@ struct ec_response_motion_sense { * Sensor data is truncated if response_max is too small * for holding all the data. */ - struct ec_response_motion_sensor_data sensor[0]; + DECLARE_FLEX_ARRAY(struct ec_response_motion_sensor_data, sensor); } dump; /* Used for MOTIONSENSE_CMD_INFO. */ diff --git a/include/linux/platform_data/nfcmrvl.h b/include/linux/platform_data/nfcmrvl.h deleted file mode 100644 index 9e75ac8d19be..000000000000 --- a/include/linux/platform_data/nfcmrvl.h +++ /dev/null @@ -1,48 +0,0 @@ -/* - * Copyright (C) 2015, Marvell International Ltd. - * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. - */ - -#ifndef _NFCMRVL_PTF_H_ -#define _NFCMRVL_PTF_H_ - -struct nfcmrvl_platform_data { - /* - * Generic - */ - - /* GPIO that is wired to RESET_N signal */ - int reset_n_io; - /* Tell if transport is muxed in HCI one */ - unsigned int hci_muxed; - - /* - * UART specific - */ - - /* Tell if UART needs flow control at init */ - unsigned int flow_control; - /* Tell if firmware supports break control for power management */ - unsigned int break_control; - - - /* - * I2C specific - */ - - unsigned int irq; - unsigned int irq_polarity; -}; - -#endif /* _NFCMRVL_PTF_H_ */ diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index 5df1ace6d2c9..3101152ce449 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -29,6 +29,7 @@ struct s3c64xx_spi_csinfo { * struct s3c64xx_spi_info - SPI Controller defining structure * @src_clk_nr: Clock source index for the CLK_CFG[SPI_CLKSEL] field. * @num_cs: Number of CS this controller emulates. + * @no_cs: Used when CS line is not connected. * @cfg_gpio: Configure pins for this SPI controller. */ struct s3c64xx_spi_info { diff --git a/include/linux/platform_data/usb3503.h b/include/linux/platform_data/usb3503.h index d01ef97ddf36..f3c942f396f8 100644 --- a/include/linux/platform_data/usb3503.h +++ b/include/linux/platform_data/usb3503.h @@ -12,6 +12,7 @@ enum usb3503_mode { USB3503_MODE_UNKNOWN, USB3503_MODE_HUB, USB3503_MODE_STANDBY, + USB3503_MODE_BYPASS, }; struct usb3503_platform_data { diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 2c6e99ca48af..d607f51404fc 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -4,6 +4,7 @@ #include <linux/spinlock.h> #include <linux/list.h> +#include <linux/mutex.h> #include <linux/alarmtimer.h> #include <linux/timerqueue.h> @@ -62,16 +63,18 @@ static inline int clockid_to_fd(const clockid_t clk) * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig * @head: timerqueue head on which this timer is queued - * @task: Pointer to target task + * @pid: Pointer to target task PID * @elist: List head for the expiry list * @firing: Timer is currently firing + * @handling: Pointer to the task which handles expiry */ struct cpu_timer { - struct timerqueue_node node; - struct timerqueue_head *head; - struct pid *pid; - struct list_head elist; - int firing; + struct timerqueue_node node; + struct timerqueue_head *head; + struct pid *pid; + struct list_head elist; + int firing; + struct task_struct __rcu *handling; }; static inline bool cpu_timer_enqueue(struct timerqueue_head *head, @@ -135,10 +138,12 @@ struct posix_cputimers { /** * posix_cputimers_work - Container for task work based posix CPU timer expiry * @work: The task work to be scheduled + * @mutex: Mutex held around expiry in context of this task work * @scheduled: @work has been scheduled already, no further processing */ struct posix_cputimers_work { struct callback_head work; + struct mutex mutex; unsigned int scheduled; }; diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 21cc29b8a9e8..0e65b3d634d9 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -106,6 +106,8 @@ struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); +int posix_acl_listxattr(struct inode *inode, char **buffer, + ssize_t *remaining_size); #else static inline int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) @@ -153,6 +155,11 @@ static inline int vfs_remove_acl(struct mnt_idmap *idmap, { return -EOPNOTSUPP; } +static inline int posix_acl_listxattr(struct inode *inode, char **buffer, + ssize_t *remaining_size) +{ + return 0; +} #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_inode_acl(struct inode *inode, int type); diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 54cd7a14330d..e86f3b731da2 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -68,7 +68,8 @@ static inline int posix_acl_type(const char *name) return -1; } -extern const struct xattr_handler posix_acl_access_xattr_handler; -extern const struct xattr_handler posix_acl_default_xattr_handler; +/* These are legacy handlers. Don't use them for new code. */ +extern const struct xattr_handler nop_posix_acl_access; +extern const struct xattr_handler nop_posix_acl_default; #endif /* _POSIX_ACL_XATTR_H */ diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index a1aa68141d0b..7c8d65414a70 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -2,6 +2,8 @@ #ifndef __LINUX_BQ27X00_BATTERY_H__ #define __LINUX_BQ27X00_BATTERY_H__ +#include <linux/power_supply.h> + enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ @@ -68,7 +70,9 @@ struct bq27xxx_device_info { struct bq27xxx_access_methods bus; struct bq27xxx_reg_cache cache; int charge_design_full; + bool removed; unsigned long last_update; + union power_supply_propval last_status; struct delayed_work work; struct power_supply *bat; struct list_head list; diff --git a/include/linux/power/generic-adc-battery.h b/include/linux/power/generic-adc-battery.h deleted file mode 100644 index c68cbf34cd34..000000000000 --- a/include/linux/power/generic-adc-battery.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012, Anish Kumar <anish198519851985@gmail.com> - */ - -#ifndef GENERIC_ADC_BATTERY_H -#define GENERIC_ADC_BATTERY_H - -/** - * struct gab_platform_data - platform_data for generic adc iio battery driver. - * @battery_info: recommended structure to specify static power supply - * parameters - * @cal_charge: calculate charge level. - * @jitter_delay: delay required after the interrupt to check battery - * status.Default set is 10ms. - */ -struct gab_platform_data { - struct power_supply_info battery_info; - int (*cal_charge)(long value); - int jitter_delay; -}; - -#endif /* GENERIC_ADC_BATTERY_H */ diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index aa2c4a7c4826..a427f13c757f 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -301,6 +301,7 @@ struct power_supply { bool initialized; bool removing; atomic_t use_cnt; + struct power_supply_battery_info *battery_info; #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd; struct thermal_cooling_device *tcd; @@ -791,10 +792,17 @@ devm_power_supply_get_by_phandle(struct device *dev, const char *property) { return NULL; } #endif /* CONFIG_OF */ +extern const enum power_supply_property power_supply_battery_info_properties[]; +extern const size_t power_supply_battery_info_properties_size; extern int power_supply_get_battery_info(struct power_supply *psy, struct power_supply_battery_info **info_out); extern void power_supply_put_battery_info(struct power_supply *psy, struct power_supply_battery_info *info); +extern bool power_supply_battery_info_has_prop(struct power_supply_battery_info *info, + enum power_supply_property psp); +extern int power_supply_battery_info_get_prop(struct power_supply_battery_info *info, + enum power_supply_property psp, + union power_supply_propval *val); extern int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table, int table_len, int ocv); extern struct power_supply_battery_ocv_table * diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 75807ecef880..49539bc416ce 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -72,7 +72,6 @@ static inline int ns_alloc_inum(struct ns_common *ns) #define ns_free_inum(ns) proc_free_inum((ns)->inum) -extern struct file *proc_ns_fget(int fd); #define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private) extern int ns_get_path(struct path *path, struct task_struct *task, const struct proc_ns_operations *ns_ops); diff --git a/include/linux/property.h b/include/linux/property.h index 0a29db15ff34..66df1a15d518 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -16,7 +16,6 @@ #include <linux/types.h> struct device; -struct net_device; enum dev_prop_type { DEV_PROP_U8, @@ -40,20 +39,20 @@ struct fwnode_handle *__dev_fwnode(struct device *dev); const struct device *: __dev_fwnode_const, \ struct device *: __dev_fwnode)(dev) -bool device_property_present(struct device *dev, const char *propname); -int device_property_read_u8_array(struct device *dev, const char *propname, +bool device_property_present(const struct device *dev, const char *propname); +int device_property_read_u8_array(const struct device *dev, const char *propname, u8 *val, size_t nval); -int device_property_read_u16_array(struct device *dev, const char *propname, +int device_property_read_u16_array(const struct device *dev, const char *propname, u16 *val, size_t nval); -int device_property_read_u32_array(struct device *dev, const char *propname, +int device_property_read_u32_array(const struct device *dev, const char *propname, u32 *val, size_t nval); -int device_property_read_u64_array(struct device *dev, const char *propname, +int device_property_read_u64_array(const struct device *dev, const char *propname, u64 *val, size_t nval); -int device_property_read_string_array(struct device *dev, const char *propname, +int device_property_read_string_array(const struct device *dev, const char *propname, const char **val, size_t nval); -int device_property_read_string(struct device *dev, const char *propname, +int device_property_read_string(const struct device *dev, const char *propname, const char **val); -int device_property_match_string(struct device *dev, +int device_property_match_string(const struct device *dev, const char *propname, const char *string); bool fwnode_property_present(const struct fwnode_handle *fwnode, @@ -105,11 +104,11 @@ struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); for (parent = fwnode_get_parent(fwnode); parent; \ parent = fwnode_get_next_parent(parent)) -struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode); +struct device *fwnode_get_next_parent_dev(const struct fwnode_handle *fwnode); unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, unsigned int depth); -bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child); +bool fwnode_is_ancestor_of(const struct fwnode_handle *ancestor, const struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_available_child_node( @@ -143,57 +142,57 @@ int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); unsigned int device_get_child_node_count(const struct device *dev); -static inline bool device_property_read_bool(struct device *dev, +static inline bool device_property_read_bool(const struct device *dev, const char *propname) { return device_property_present(dev, propname); } -static inline int device_property_read_u8(struct device *dev, +static inline int device_property_read_u8(const struct device *dev, const char *propname, u8 *val) { return device_property_read_u8_array(dev, propname, val, 1); } -static inline int device_property_read_u16(struct device *dev, +static inline int device_property_read_u16(const struct device *dev, const char *propname, u16 *val) { return device_property_read_u16_array(dev, propname, val, 1); } -static inline int device_property_read_u32(struct device *dev, +static inline int device_property_read_u32(const struct device *dev, const char *propname, u32 *val) { return device_property_read_u32_array(dev, propname, val, 1); } -static inline int device_property_read_u64(struct device *dev, +static inline int device_property_read_u64(const struct device *dev, const char *propname, u64 *val) { return device_property_read_u64_array(dev, propname, val, 1); } -static inline int device_property_count_u8(struct device *dev, const char *propname) +static inline int device_property_count_u8(const struct device *dev, const char *propname) { return device_property_read_u8_array(dev, propname, NULL, 0); } -static inline int device_property_count_u16(struct device *dev, const char *propname) +static inline int device_property_count_u16(const struct device *dev, const char *propname) { return device_property_read_u16_array(dev, propname, NULL, 0); } -static inline int device_property_count_u32(struct device *dev, const char *propname) +static inline int device_property_count_u32(const struct device *dev, const char *propname) { return device_property_read_u32_array(dev, propname, NULL, 0); } -static inline int device_property_count_u64(struct device *dev, const char *propname) +static inline int device_property_count_u64(const struct device *dev, const char *propname) { return device_property_read_u64_array(dev, propname, NULL, 0); } -static inline int device_property_string_array_count(struct device *dev, +static inline int device_property_string_array_count(const struct device *dev, const char *propname) { return device_property_read_string_array(dev, propname, NULL, 0); @@ -396,7 +395,7 @@ enum dev_dma_attr device_get_dma_attr(const struct device *dev); const void *device_get_match_data(const struct device *dev); int device_get_phy_mode(struct device *dev); -int fwnode_get_phy_mode(struct fwnode_handle *fwnode); +int fwnode_get_phy_mode(const struct fwnode_handle *fwnode); void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); @@ -433,7 +432,7 @@ static inline bool fwnode_graph_is_endpoint(const struct fwnode_handle *fwnode) struct fwnode_handle * fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, u32 port, u32 endpoint, unsigned long flags); -unsigned int fwnode_graph_get_endpoint_count(struct fwnode_handle *fwnode, +unsigned int fwnode_graph_get_endpoint_count(const struct fwnode_handle *fwnode, unsigned long flags); #define fwnode_graph_for_each_endpoint(fwnode, child) \ diff --git a/include/linux/psi.h b/include/linux/psi.h index b029a847def1..ab26200c2803 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -24,7 +24,7 @@ void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, enum psi_res res); + char *buf, enum psi_res res, struct file *file); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 1e0a0d7ace3a..040c089581c6 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -151,6 +151,9 @@ struct psi_trigger { /* Deferred event(s) from previous ratelimit window */ bool pending_event; + + /* Trigger type - PSI_AVGS for unprivileged, PSI_POLL for RT */ + enum psi_aggregators aggregator; }; struct psi_group { @@ -171,30 +174,34 @@ struct psi_group { /* Aggregator work control */ struct delayed_work avgs_work; + /* Unprivileged triggers against N*PSI_FREQ windows */ + struct list_head avg_triggers; + u32 avg_nr_triggers[NR_PSI_STATES - 1]; + /* Total stall times and sampled pressure averages */ u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1]; unsigned long avg[NR_PSI_STATES - 1][3]; - /* Monitor work control */ - struct task_struct __rcu *poll_task; - struct timer_list poll_timer; - wait_queue_head_t poll_wait; - atomic_t poll_wakeup; - atomic_t poll_scheduled; + /* Monitor RT polling work control */ + struct task_struct __rcu *rtpoll_task; + struct timer_list rtpoll_timer; + wait_queue_head_t rtpoll_wait; + atomic_t rtpoll_wakeup; + atomic_t rtpoll_scheduled; /* Protects data used by the monitor */ - struct mutex trigger_lock; - - /* Configured polling triggers */ - struct list_head triggers; - u32 nr_triggers[NR_PSI_STATES - 1]; - u32 poll_states; - u64 poll_min_period; - - /* Total stall times at the start of monitor activation */ - u64 polling_total[NR_PSI_STATES - 1]; - u64 polling_next_update; - u64 polling_until; + struct mutex rtpoll_trigger_lock; + + /* Configured RT polling triggers */ + struct list_head rtpoll_triggers; + u32 rtpoll_nr_triggers[NR_PSI_STATES - 1]; + u32 rtpoll_states; + u64 rtpoll_min_period; + + /* Total stall times at the start of RT polling monitor activation */ + u64 rtpoll_total[NR_PSI_STATES - 1]; + u64 rtpoll_next_update; + u64 rtpoll_until; }; #else /* CONFIG_PSI */ diff --git a/include/linux/psp-platform-access.h b/include/linux/psp-platform-access.h new file mode 100644 index 000000000000..75da8f5f7ad8 --- /dev/null +++ b/include/linux/psp-platform-access.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __PSP_PLATFORM_ACCESS_H +#define __PSP_PLATFORM_ACCESS_H + +#include <linux/psp.h> + +enum psp_platform_access_msg { + PSP_CMD_NONE = 0x0, + PSP_I2C_REQ_BUS_CMD = 0x64, +}; + +struct psp_req_buffer_hdr { + u32 payload_size; + u32 status; +} __packed; + +struct psp_request { + struct psp_req_buffer_hdr header; + void *buf; +} __packed; + +/** + * psp_send_platform_access_msg() - Send a message to control platform features + * + * This function is intended to be used by drivers outside of ccp to communicate + * with the platform. + * + * Returns: + * 0: success + * -%EBUSY: mailbox in recovery or in use + * -%ENODEV: driver not bound with PSP device + * -%ETIMEDOUT: request timed out + * -%EIO: unknown error (see kernel log) + */ +int psp_send_platform_access_msg(enum psp_platform_access_msg, struct psp_request *req); + +/** + * psp_ring_platform_doorbell() - Ring platform doorbell + * + * This function is intended to be used by drivers outside of ccp to ring the + * platform doorbell with a message. + * + * Returns: + * 0: success + * -%EBUSY: mailbox in recovery or in use + * -%ENODEV: driver not bound with PSP device + * -%ETIMEDOUT: request timed out + * -%EIO: error will be stored in result argument + */ +int psp_ring_platform_doorbell(int msg, u32 *result); + +/** + * psp_check_platform_access_status() - Checks whether platform features is ready + * + * This function is intended to be used by drivers outside of ccp to determine + * if platform features has initialized. + * + * Returns: + * 0 platform features is ready + * -%ENODEV platform features is not ready or present + */ +int psp_check_platform_access_status(void); + +#endif /* __PSP_PLATFORM_ACCESS_H */ diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 1595088c428b..7fd17e82bab4 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -14,14 +14,6 @@ #include <uapi/linux/psp-sev.h> -#ifdef CONFIG_X86 -#include <linux/mem_encrypt.h> - -#define __psp_pa(x) __sme_pa(x) -#else -#define __psp_pa(x) __pa(x) -#endif - #define SEV_FW_BLOB_MAX_SIZE 0x4000 /* 16KB */ /** diff --git a/include/linux/psp.h b/include/linux/psp.h new file mode 100644 index 000000000000..92e60aeef21e --- /dev/null +++ b/include/linux/psp.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __PSP_H +#define __PSP_H + +#ifdef CONFIG_X86 +#include <linux/mem_encrypt.h> + +#define __psp_pa(x) __sme_pa(x) +#else +#define __psp_pa(x) __pa(x) +#endif + +/* + * Fields and bits used by most PSP mailboxes + * + * Note: Some mailboxes (such as SEV) have extra bits or different meanings + * and should include an appropriate local definition in their source file. + */ +#define PSP_CMDRESP_STS GENMASK(15, 0) +#define PSP_CMDRESP_CMD GENMASK(23, 16) +#define PSP_CMDRESP_RESERVED GENMASK(29, 24) +#define PSP_CMDRESP_RECOVERY BIT(30) +#define PSP_CMDRESP_RESP BIT(31) + +#define PSP_DRBL_MSG PSP_CMDRESP_CMD +#define PSP_DRBL_RING BIT(0) + +#endif /* __PSP_H */ diff --git a/include/linux/ptp_kvm.h b/include/linux/ptp_kvm.h index c2e28deef33a..746fd67c3480 100644 --- a/include/linux/ptp_kvm.h +++ b/include/linux/ptp_kvm.h @@ -14,6 +14,7 @@ struct timespec64; struct clocksource; int kvm_arch_ptp_init(void); +void kvm_arch_ptp_exit(void); int kvm_arch_ptp_get_clock(struct timespec64 *ts); int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec, struct clocksource **cs); diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 7b7b93b6fb81..04ae1d9073a7 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -309,8 +309,6 @@ struct pwm_chip { #if IS_ENABLED(CONFIG_PWM) /* PWM user APIs */ -struct pwm_device *pwm_request(int pwm_id, const char *label); -void pwm_free(struct pwm_device *pwm); int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state); int pwm_adjust_config(struct pwm_device *pwm); @@ -410,17 +408,6 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, const char *con_id); #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, const struct pwm_state *state) { diff --git a/include/linux/raid_class.h b/include/linux/raid_class.h index 5cdfcb873a8f..6a9b177d5c41 100644 --- a/include/linux/raid_class.h +++ b/include/linux/raid_class.h @@ -11,7 +11,7 @@ struct raid_template { }; struct raid_function_template { - void *cookie; + const void *cookie; int (*is_raid)(struct device *); void (*get_resync)(struct device *); void (*get_state)(struct device *); diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index d1c53e9d8c75..7ee7ed5de722 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -156,13 +156,13 @@ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { - rb->__rb_parent_color = rb_color(rb) | (unsigned long)p; + rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { - rb->__rb_parent_color = (unsigned long)p | color; + rb->__rb_parent_color = (unsigned long)p + color; } static inline void diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 094321c17e48..dcd2cf1e8326 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -976,8 +976,10 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * - * Note that the allowable offset might decrease in the future, for example, - * to allow something like kmem_cache_free_rcu(). + * The object to be freed can be allocated either by kmalloc() or + * kmem_cache_alloc(). + * + * Note that the allowable offset might decrease in the future. * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. diff --git a/include/linux/rcuref.h b/include/linux/rcuref.h new file mode 100644 index 000000000000..2c8bfd0f1b6b --- /dev/null +++ b/include/linux/rcuref.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LINUX_RCUREF_H +#define _LINUX_RCUREF_H + +#include <linux/atomic.h> +#include <linux/bug.h> +#include <linux/limits.h> +#include <linux/lockdep.h> +#include <linux/preempt.h> +#include <linux/rcupdate.h> + +#define RCUREF_ONEREF 0x00000000U +#define RCUREF_MAXREF 0x7FFFFFFFU +#define RCUREF_SATURATED 0xA0000000U +#define RCUREF_RELEASED 0xC0000000U +#define RCUREF_DEAD 0xE0000000U +#define RCUREF_NOREF 0xFFFFFFFFU + +/** + * rcuref_init - Initialize a rcuref reference count with the given reference count + * @ref: Pointer to the reference count + * @cnt: The initial reference count typically '1' + */ +static inline void rcuref_init(rcuref_t *ref, unsigned int cnt) +{ + atomic_set(&ref->refcnt, cnt - 1); +} + +/** + * rcuref_read - Read the number of held reference counts of a rcuref + * @ref: Pointer to the reference count + * + * Return: The number of held references (0 ... N) + */ +static inline unsigned int rcuref_read(rcuref_t *ref) +{ + unsigned int c = atomic_read(&ref->refcnt); + + /* Return 0 if within the DEAD zone. */ + return c >= RCUREF_RELEASED ? 0 : c + 1; +} + +extern __must_check bool rcuref_get_slowpath(rcuref_t *ref); + +/** + * rcuref_get - Acquire one reference on a rcuref reference count + * @ref: Pointer to the reference count + * + * Similar to atomic_inc_not_zero() but saturates at RCUREF_MAXREF. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See documentation in lib/rcuref.c + * + * Return: + * False if the attempt to acquire a reference failed. This happens + * when the last reference has been put already + * + * True if a reference was successfully acquired + */ +static inline __must_check bool rcuref_get(rcuref_t *ref) +{ + /* + * Unconditionally increase the reference count. The saturation and + * dead zones provide enough tolerance for this. + */ + if (likely(!atomic_add_negative_relaxed(1, &ref->refcnt))) + return true; + + /* Handle the cases inside the saturation and dead zones */ + return rcuref_get_slowpath(ref); +} + +extern __must_check bool rcuref_put_slowpath(rcuref_t *ref); + +/* + * Internal helper. Do not invoke directly. + */ +static __always_inline __must_check bool __rcuref_put(rcuref_t *ref) +{ + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(), + "suspicious rcuref_put_rcusafe() usage"); + /* + * Unconditionally decrease the reference count. The saturation and + * dead zones provide enough tolerance for this. + */ + if (likely(!atomic_add_negative_release(-1, &ref->refcnt))) + return false; + + /* + * Handle the last reference drop and cases inside the saturation + * and dead zones. + */ + return rcuref_put_slowpath(ref); +} + +/** + * rcuref_put_rcusafe -- Release one reference for a rcuref reference count RCU safe + * @ref: Pointer to the reference count + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides an acquire ordering on success such that free() + * must come after. + * + * Can be invoked from contexts, which guarantee that no grace period can + * happen which would free the object concurrently if the decrement drops + * the last reference and the slowpath races against a concurrent get() and + * put() pair. rcu_read_lock()'ed and atomic contexts qualify. + * + * Return: + * True if this was the last reference with no future references + * possible. This signals the caller that it can safely release the + * object which is protected by the reference counter. + * + * False if there are still active references or the put() raced + * with a concurrent get()/put() pair. Caller is not allowed to + * release the protected object. + */ +static inline __must_check bool rcuref_put_rcusafe(rcuref_t *ref) +{ + return __rcuref_put(ref); +} + +/** + * rcuref_put -- Release one reference for a rcuref reference count + * @ref: Pointer to the reference count + * + * Can be invoked from any context. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides an acquire ordering on success such that free() + * must come after. + * + * Return: + * + * True if this was the last reference with no future references + * possible. This signals the caller that it can safely schedule the + * object, which is protected by the reference counter, for + * deconstruction. + * + * False if there are still active references or the put() raced + * with a concurrent get()/put() pair. Caller is not allowed to + * deconstruct the protected object. + */ +static inline __must_check bool rcuref_put(rcuref_t *ref) +{ + bool released; + + preempt_disable(); + released = __rcuref_put(ref); + preempt_enable(); + return released; +} + +#endif diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4d10790adeb0..c2b9cc5db824 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -46,12 +46,20 @@ struct sdw_slave; #define REGMAP_MDIO_C45_DEVAD_MASK GENMASK(20, 16) #define REGMAP_MDIO_C45_REGNUM_MASK GENMASK(15, 0) +/* + * regmap.reg_shift indicates by how much we must shift registers prior to + * performing any operation. It's a signed value, positive numbers means + * downshifting the register's address, while negative numbers means upshifting. + */ +#define REGMAP_UPSHIFT(s) (-(s)) +#define REGMAP_DOWNSHIFT(s) (s) + /* An enum of all the supported cache types */ enum regcache_type { REGCACHE_NONE, REGCACHE_RBTREE, - REGCACHE_COMPRESSED, REGCACHE_FLAT, + REGCACHE_MAPLE, }; /** @@ -246,8 +254,9 @@ typedef void (*regmap_unlock)(void *); * @reg_stride: The register address stride. Valid register addresses are a * multiple of this value. If set to 0, a value of 1 will be * used. - * @reg_downshift: The number of bits to downshift the register before - * performing any operations. + * @reg_shift: The number of bits to shift the register before performing any + * operations. Any positive number will be downshifted, and negative + * values will be upshifted * @reg_base: Value to be added to every register address before performing any * operation. * @pad_bits: Number of bits of padding between register and value. @@ -381,7 +390,7 @@ struct regmap_config { int reg_bits; int reg_stride; - int reg_downshift; + int reg_shift; unsigned int reg_base; int pad_bits; int val_bits; @@ -1551,6 +1560,7 @@ struct regmap_irq_chip_data; * @use_ack: Use @ack register even if it is zero. * @ack_invert: Inverted ack register: cleared bits for ack. * @clear_ack: Use this to set 1 and 0 or vice-versa to clear interrupts. + * @status_invert: Inverted status register: cleared bits are active interrupts. * @wake_invert: Inverted wake register: cleared bits are wake enabled. * @type_in_mask: Use the mask registers for controlling irq type. Use this if * the hardware provides separate bits for rising/falling edge @@ -1560,18 +1570,20 @@ struct regmap_irq_chip_data; * @clear_on_unmask: For chips with interrupts cleared on read: read the status * registers before unmasking interrupts to clear any bits * set when they were masked. + * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * @not_fixed_stride: Used when chip peripherals are not laid out with fixed * stride. Must be used with sub_reg_offsets containing the * offsets to each peripheral. Deprecated; the same thing * can be accomplished with a @get_irq_reg callback, without * the need for a @sub_reg_offsets table. - * @status_invert: Inverted status register: cleared bits are active interrupts. - * @runtime_pm: Hold a runtime PM lock on the device when accessing it. + * @no_status: No status register: all interrupts assumed generated by device. * * @num_regs: Number of registers in each control bank. + * * @irqs: Descriptors for individual IRQs. Interrupt numbers are * assigned based on the index in the array of the interrupt. * @num_irqs: Number of descriptors. + * * @num_type_reg: Number of type registers. Deprecated, use config registers * instead. * @num_virt_regs: Number of non-standard irq configuration registers. @@ -1579,6 +1591,7 @@ struct regmap_irq_chip_data; * instead. * @num_config_bases: Number of config base registers. * @num_config_regs: Number of config registers for each config base register. + * * @handle_pre_irq: Driver specific callback to handle interrupt from device * before regmap_irq_handler process the interrupts. * @handle_post_irq: Driver specific callback to handle interrupt from device @@ -1625,12 +1638,13 @@ struct regmap_irq_chip { unsigned int use_ack:1; unsigned int ack_invert:1; unsigned int clear_ack:1; + unsigned int status_invert:1; unsigned int wake_invert:1; - unsigned int runtime_pm:1; unsigned int type_in_mask:1; unsigned int clear_on_unmask:1; + unsigned int runtime_pm:1; unsigned int not_fixed_stride:1; - unsigned int status_invert:1; + unsigned int no_status:1; int num_regs; @@ -1650,7 +1664,8 @@ struct regmap_irq_chip { int (*set_type_virt)(unsigned int **buf, unsigned int type, unsigned long hwirq, int reg); int (*set_type_config)(unsigned int **buf, unsigned int type, - const struct regmap_irq *irq_data, int idx); + const struct regmap_irq *irq_data, int idx, + void *irq_drv_data); unsigned int (*get_irq_reg)(struct regmap_irq_chip_data *data, unsigned int base, int index); void *irq_drv_data; @@ -1659,7 +1674,8 @@ struct regmap_irq_chip { unsigned int regmap_irq_get_irq_reg_linear(struct regmap_irq_chip_data *data, unsigned int base, int index); int regmap_irq_set_type_config_simple(unsigned int **buf, unsigned int type, - const struct regmap_irq *irq_data, int idx); + const struct regmap_irq *irq_data, + int idx, void *irq_drv_data); int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 3c01c2bf84f5..505c908dbb81 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -196,11 +196,11 @@ enum { /* PCA9450_REG_LDO3_VOLT bits */ #define LDO3_EN_MASK 0xC0 -#define LDO3OUT_MASK 0x0F +#define LDO3OUT_MASK 0x1F /* PCA9450_REG_LDO4_VOLT bits */ #define LDO4_EN_MASK 0xC0 -#define LDO4OUT_MASK 0x0F +#define LDO4OUT_MASK 0x1F /* PCA9450_REG_LDO5_VOLT bits */ #define LDO5L_EN_MASK 0xC0 diff --git a/include/linux/rpmsg/qcom_smd.h b/include/linux/rpmsg/qcom_smd.h index 2e92d7407a85..3379bf4e1cb1 100644 --- a/include/linux/rpmsg/qcom_smd.h +++ b/include/linux/rpmsg/qcom_smd.h @@ -11,7 +11,7 @@ struct qcom_smd_edge; struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent, struct device_node *node); -int qcom_smd_unregister_edge(struct qcom_smd_edge *edge); +void qcom_smd_unregister_edge(struct qcom_smd_edge *edge); #else @@ -22,9 +22,8 @@ qcom_smd_register_edge(struct device *parent, return NULL; } -static inline int qcom_smd_unregister_edge(struct qcom_smd_edge *edge) +static inline void qcom_smd_unregister_edge(struct qcom_smd_edge *edge) { - return 0; } #endif diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 92ad75549e9c..3d6cf306cd55 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -25,7 +25,8 @@ void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq); + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags, u32 portid, const struct nlmsghdr *nlh); @@ -62,16 +63,6 @@ static inline bool lockdep_rtnl_is_held(void) rcu_dereference_check(p, lockdep_rtnl_is_held()) /** - * rcu_dereference_bh_rtnl - rcu_dereference_bh with debug checking - * @p: The pointer to read, prior to dereference - * - * Do an rcu_dereference_bh(p), but check caller either holds rcu_read_lock_bh() - * or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference_bh() - */ -#define rcu_dereference_bh_rtnl(p) \ - rcu_dereference_bh_check(p, lockdep_rtnl_is_held()) - -/** * rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL * @p: The pointer to read, prior to dereferencing * diff --git a/include/linux/sched.h b/include/linux/sched.h index 63d242164b1a..eed5d65b8d1f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -36,6 +36,7 @@ #include <linux/seqlock.h> #include <linux/kcsan.h> #include <linux/rv.h> +#include <linux/livepatch_sched.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ @@ -69,6 +70,7 @@ struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; +struct user_event_mm; /* * Task state bitmask. NOTE! These bits are also @@ -1313,16 +1315,14 @@ struct task_struct { #ifdef CONFIG_SCHED_MM_CID int mm_cid; /* Current cid in mm */ + int last_mm_cid; /* Most recent cid in mm */ + int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */ + struct callback_head cid_work; #endif struct tlbflush_unmap_batch tlb_ubc; - union { - refcount_t rcu_users; - struct rcu_head rcu; - }; - /* Cache last used pipe for splice(): */ struct pipe_inode_info *splice_pipe; @@ -1459,6 +1459,8 @@ struct task_struct { unsigned long saved_state_change; # endif #endif + struct rcu_head rcu; + refcount_t rcu_users; int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; @@ -1528,6 +1530,10 @@ struct task_struct { union rv_task_monitor rv[RV_PER_TASK_MONITORS]; #endif +#ifdef CONFIG_USER_EVENTS + struct user_event_mm *user_event_mm; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. @@ -1729,7 +1735,7 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ -#define PF__HOLE__00004000 0x00004000 +#define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ @@ -2070,6 +2076,9 @@ extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +void sched_dynamic_klp_enable(void); +void sched_dynamic_klp_disable(void); + DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) @@ -2078,6 +2087,7 @@ static __always_inline int _cond_resched(void) } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) + extern int dynamic_cond_resched(void); static __always_inline int _cond_resched(void) @@ -2085,20 +2095,25 @@ static __always_inline int _cond_resched(void) return dynamic_cond_resched(); } -#else +#else /* !CONFIG_PREEMPTION */ static inline int _cond_resched(void) { + klp_sched_try_switch(); return __cond_resched(); } -#endif /* CONFIG_PREEMPT_DYNAMIC */ +#endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ -#else +#else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */ -static inline int _cond_resched(void) { return 0; } +static inline int _cond_resched(void) +{ + klp_sched_try_switch(); + return 0; +} -#endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */ +#endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */ #define cond_resched() ({ \ __might_resched(__FILE__, __LINE__, 0); \ diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 0e17ae7fbfd3..0ee96ea7a0e9 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -90,4 +90,5 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK) +#define MMF_VM_MERGE_ANY 29 #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 8c15abd67aed..fe1a46f30d24 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -46,6 +46,12 @@ static inline bool housekeeping_enabled(enum hk_type type) static inline void housekeeping_affine(struct task_struct *t, enum hk_type type) { } + +static inline bool housekeeping_test_cpu(int cpu, enum hk_type type) +{ + return true; +} + static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ @@ -58,4 +64,10 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type) return true; } +static inline bool cpu_is_isolated(int cpu) +{ + return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) || + !housekeeping_test_cpu(cpu, HK_TYPE_TICK); +} + #endif /* _LINUX_SCHED_ISOLATION_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2a243616f222..8d89c8c4fac1 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,7 +8,6 @@ #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> -#include <linux/ioasid.h> /* * Routines for handling mm_structs @@ -37,6 +36,11 @@ static inline void mmgrab(struct mm_struct *mm) atomic_inc(&mm->mm_count); } +static inline void smp_mb__after_mmgrab(void) +{ + smp_mb__after_atomic(); +} + extern void __mmdrop(struct mm_struct *mm); static inline void mmdrop(struct mm_struct *mm) @@ -79,6 +83,34 @@ static inline void mmdrop_sched(struct mm_struct *mm) } #endif +/* Helpers for lazy TLB mm refcounting */ +static inline void mmgrab_lazy_tlb(struct mm_struct *mm) +{ + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) + mmgrab(mm); +} + +static inline void mmdrop_lazy_tlb(struct mm_struct *mm) +{ + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) { + mmdrop(mm); + } else { + /* + * mmdrop_lazy_tlb must provide a full memory barrier, see the + * membarrier comment finish_task_switch which relies on this. + */ + smp_mb(); + } +} + +static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) +{ + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) + mmdrop_sched(mm); + else + smp_mb(); /* see mmdrop_lazy_tlb() above */ +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. @@ -451,29 +483,4 @@ static inline void membarrier_update_current_mm(struct mm_struct *next_mm) } #endif -#ifdef CONFIG_IOMMU_SVA -static inline void mm_pasid_init(struct mm_struct *mm) -{ - mm->pasid = INVALID_IOASID; -} - -/* Associate a PASID with an mm_struct: */ -static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) -{ - mm->pasid = pasid; -} - -static inline void mm_pasid_drop(struct mm_struct *mm) -{ - if (pasid_valid(mm->pasid)) { - ioasid_free(mm->pasid); - mm->pasid = INVALID_IOASID; - } -} -#else -static inline void mm_pasid_init(struct mm_struct *mm) {} -static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} -static inline void mm_pasid_drop(struct mm_struct *mm) {} -#endif - #endif /* _LINUX_SCHED_MM_H */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 357e0068497c..e0f5ac90a228 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -23,7 +23,12 @@ struct kernel_clone_args { int __user *pidfd; int __user *child_tid; int __user *parent_tid; + const char *name; int exit_signal; + u32 kthread:1; + u32 io_thread:1; + u32 user_worker:1; + u32 no_files:1; unsigned long stack; unsigned long stack_size; unsigned long tls; @@ -31,8 +36,6 @@ struct kernel_clone_args { /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; - int io_thread; - int kthread; int idle; int (*fn)(void *); void *fn_arg; @@ -89,9 +92,12 @@ extern void exit_files(struct task_struct *); extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); +struct task_struct *copy_process(struct pid *pid, int trace, int node, + struct kernel_clone_args *args); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); -extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); +extern pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, + unsigned long flags); extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 5e799a47431e..f158b025c175 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -23,7 +23,7 @@ static __always_inline void *task_stack_page(const struct task_struct *task) #define setup_thread_stack(new,old) do { } while(0) -static inline unsigned long *end_of_stack(const struct task_struct *task) +static __always_inline unsigned long *end_of_stack(const struct task_struct *task) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1; diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h new file mode 100644 index 000000000000..837a23624a66 --- /dev/null +++ b/include/linux/sched/vhost_task.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VHOST_TASK_H +#define _LINUX_VHOST_TASK_H + + +struct vhost_task; + +struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, + const char *name); +void vhost_task_start(struct vhost_task *vtsk); +void vhost_task_stop(struct vhost_task *vtsk); +void vhost_task_wake(struct vhost_task *vtsk); + +#endif diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 358dc08e0831..836a7e200f39 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -222,7 +222,7 @@ struct sctp_datahdr { __be16 stream; __be16 ssn; __u32 ppid; - __u8 payload[]; + /* __u8 payload[]; */ }; struct sctp_data_chunk { @@ -270,7 +270,7 @@ struct sctp_inithdr { __be16 num_outbound_streams; __be16 num_inbound_streams; __be32 initial_tsn; - __u8 params[]; + /* __u8 params[]; */ }; struct sctp_init_chunk { @@ -385,7 +385,7 @@ struct sctp_sackhdr { __be32 a_rwnd; __be16 num_gap_ack_blocks; __be16 num_dup_tsns; - union sctp_sack_variable variable[]; + /* union sctp_sack_variable variable[]; */ }; struct sctp_sack_chunk { @@ -443,7 +443,7 @@ struct sctp_shutdown_chunk { struct sctp_errhdr { __be16 cause; __be16 length; - __u8 variable[]; + /* __u8 variable[]; */ }; struct sctp_operr_chunk { @@ -603,7 +603,7 @@ struct sctp_fwdtsn_skip { struct sctp_fwdtsn_hdr { __be32 new_cum_tsn; - struct sctp_fwdtsn_skip skip[]; + /* struct sctp_fwdtsn_skip skip[]; */ }; struct sctp_fwdtsn_chunk { @@ -620,7 +620,7 @@ struct sctp_ifwdtsn_skip { struct sctp_ifwdtsn_hdr { __be32 new_cum_tsn; - struct sctp_ifwdtsn_skip skip[]; + /* struct sctp_ifwdtsn_skip skip[]; */ }; struct sctp_ifwdtsn_chunk { @@ -667,7 +667,7 @@ struct sctp_addip_param { struct sctp_addiphdr { __be32 serial; - __u8 params[]; + /* __u8 params[]; */ }; struct sctp_addip_chunk { @@ -727,7 +727,7 @@ struct sctp_addip_chunk { struct sctp_authhdr { __be16 shkey_id; __be16 hmac_id; - __u8 hmac[]; + /* __u8 hmac[]; */ }; struct sctp_auth_chunk { @@ -742,7 +742,7 @@ struct sctp_infox { struct sctp_reconf_chunk { struct sctp_chunkhdr chunk_hdr; - __u8 params[]; + /* __u8 params[]; */ }; struct sctp_strreset_outreq { diff --git a/include/linux/security.h b/include/linux/security.h index 5984d0d550b4..e2734e9e44d5 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -68,7 +68,7 @@ struct watch_notification; /* If capable is being called by a setid function */ #define CAP_OPT_INSETID BIT(2) -/* LSM Agnostic defines for fs_context::lsm_flags */ +/* LSM Agnostic defines for security_sb_set_mnt_opts() flags */ #define SECURITY_LSM_NATIVE_LABELS 1 struct ctl_table; @@ -336,9 +336,6 @@ int security_inode_init_security(struct inode *inode, struct inode *dir, int security_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode); -int security_old_inode_init_security(struct inode *inode, struct inode *dir, - const struct qstr *qstr, const char **name, - void **value, size_t *len); int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode); int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry); @@ -778,15 +775,6 @@ static inline int security_inode_init_security_anon(struct inode *inode, return 0; } -static inline int security_old_inode_init_security(struct inode *inode, - struct inode *dir, - const struct qstr *qstr, - const char **name, - void **value, size_t *len) -{ - return -EOPNOTSUPP; -} - static inline int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 31ac562a17d7..bbae1e52ab4f 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -45,6 +45,8 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_WRITE_SHADOW_MBR: case IOC_OPAL_GENERIC_TABLE_RW: case IOC_OPAL_GET_STATUS: + case IOC_OPAL_GET_LR_STATUS: + case IOC_OPAL_GET_GEOMETRY: return true; } return false; diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index 6694d0019a68..04655faadc2d 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -25,8 +25,14 @@ struct semaphore { .wait_list = LIST_HEAD_INIT((name).wait_list), \ } -#define DEFINE_SEMAPHORE(name) \ - struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) +/* + * Unlike mutexes, binary semaphores do not have an owner, so up() can + * be called in a different thread from the one which called down(). + * It is also safe to call down_trylock() and up() from interrupt + * context. + */ +#define DEFINE_SEMAPHORE(_name, _n) \ + struct semaphore _name = __SEMAPHORE_INITIALIZER(_name, _n) static inline void sema_init(struct semaphore *sem, int val) { diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index 5b31c5147969..515d7fcb9634 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -159,4 +159,6 @@ extern int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary); #endif +void seq_buf_do_printk(struct seq_buf *s, const char *lvl); + #endif /* _LINUX_SEQ_BUF_H */ diff --git a/include/linux/serdev.h b/include/linux/serdev.h index 5f6bfe4f6d95..f5f97fa25e8a 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -93,6 +93,7 @@ struct serdev_controller_ops { void (*wait_until_sent)(struct serdev_controller *, long); int (*get_tiocm)(struct serdev_controller *); int (*set_tiocm)(struct serdev_controller *, unsigned int, unsigned int); + int (*break_ctl)(struct serdev_controller *ctrl, unsigned int break_state); }; /** @@ -203,6 +204,7 @@ int serdev_device_write_buf(struct serdev_device *, const unsigned char *, size_ void serdev_device_wait_until_sent(struct serdev_device *, long); int serdev_device_get_tiocm(struct serdev_device *); int serdev_device_set_tiocm(struct serdev_device *, int, int); +int serdev_device_break_ctl(struct serdev_device *serdev, int break_state); void serdev_device_write_wakeup(struct serdev_device *); int serdev_device_write(struct serdev_device *, const unsigned char *, size_t, long); void serdev_device_write_flush(struct serdev_device *); @@ -250,11 +252,15 @@ static inline int serdev_device_write_buf(struct serdev_device *serdev, static inline void serdev_device_wait_until_sent(struct serdev_device *sdev, long timeout) {} static inline int serdev_device_get_tiocm(struct serdev_device *serdev) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int serdev_device_set_tiocm(struct serdev_device *serdev, int set, int clear) { - return -ENOTSUPP; + return -EOPNOTSUPP; +} +static inline int serdev_device_break_ctl(struct serdev_device *serdev, int break_state) +{ + return -EOPNOTSUPP; } static inline int serdev_device_write(struct serdev_device *sdev, const unsigned char *buf, size_t count, unsigned long timeout) diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 19376bee9667..6f78f302d272 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -18,16 +18,16 @@ struct plat_serial8250_port { unsigned long iobase; /* io base address */ void __iomem *membase; /* ioremap cookie or NULL */ resource_size_t mapbase; /* resource base */ + unsigned int uartclk; /* UART clock rate */ unsigned int irq; /* interrupt number */ unsigned long irqflags; /* request_irq flags */ - unsigned int uartclk; /* UART clock rate */ void *private_data; unsigned char regshift; /* register shift */ unsigned char iotype; /* UPIO_* */ unsigned char hub6; unsigned char has_sysrq; /* supports magic SysRq */ - upf_t flags; /* UPF_* flags */ unsigned int type; /* If UPF_FIXED_TYPE */ + upf_t flags; /* UPF_* flags */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); void (*set_termios)(struct uart_port *, @@ -151,26 +151,22 @@ void serial8250_unregister_port(int line); void serial8250_suspend_port(int line); void serial8250_resume_port(int line); -extern int early_serial_setup(struct uart_port *port); - -extern int early_serial8250_setup(struct earlycon_device *device, - const char *options); -extern void serial8250_update_uartclk(struct uart_port *port, - unsigned int uartclk); -extern void serial8250_do_set_termios(struct uart_port *port, - struct ktermios *termios, const struct ktermios *old); -extern void serial8250_do_set_ldisc(struct uart_port *port, - struct ktermios *termios); -extern unsigned int serial8250_do_get_mctrl(struct uart_port *port); -extern int serial8250_do_startup(struct uart_port *port); -extern void serial8250_do_shutdown(struct uart_port *port); -extern void serial8250_do_pm(struct uart_port *port, unsigned int state, - unsigned int oldstate); -extern void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); -extern void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, - unsigned int quot, - unsigned int quot_frac); -extern int fsl8250_handle_irq(struct uart_port *port); +int early_serial_setup(struct uart_port *port); +int early_serial8250_setup(struct earlycon_device *device, const char *options); + +void serial8250_update_uartclk(struct uart_port *port, unsigned int uartclk); +void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, + const struct ktermios *old); +void serial8250_do_set_ldisc(struct uart_port *port, struct ktermios *termios); +unsigned int serial8250_do_get_mctrl(struct uart_port *port); +int serial8250_do_startup(struct uart_port *port); +void serial8250_do_shutdown(struct uart_port *port); +void serial8250_do_pm(struct uart_port *port, unsigned int state, + unsigned int oldstate); +void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); +void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, + unsigned int quot, unsigned int quot_frac); +int fsl8250_handle_irq(struct uart_port *port); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr); void serial8250_read_char(struct uart_8250_port *up, u16 lsr); @@ -183,9 +179,8 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, int serial8250_console_setup(struct uart_port *port, char *options, bool probe); int serial8250_console_exit(struct uart_port *port); -extern void serial8250_set_isa_configurator(void (*v) - (int port, struct uart_port *up, - u32 *capabilities)); +void serial8250_set_isa_configurator(void (*v)(int port, struct uart_port *up, + u32 *capabilities)); #ifdef CONFIG_SERIAL_8250_RT288X unsigned int au_serial_in(struct uart_port *p, int offset); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 9e3e5e0d11b2..66ecec15a1bf 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -553,7 +553,7 @@ struct uart_port { #define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) #define UPSTAT_SYNC_FIFO ((__force upstat_t) (1 << 5)) - int hw_stopped; /* sw-assisted CTS flow state */ + bool hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ @@ -812,9 +812,8 @@ extern const struct earlycon_id __earlycon_table_end[]; #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) -extern int of_setup_earlycon(const struct earlycon_id *match, - unsigned long node, - const char *options); +int of_setup_earlycon(const struct earlycon_id *match, unsigned long node, + const char *options); #ifdef CONFIG_SERIAL_EARLYCON extern bool earlycon_acpi_spcr_enable __initdata; @@ -897,11 +896,11 @@ static inline bool uart_softcts_mode(struct uart_port *uport) * The following are helper functions for the low level drivers. */ -extern void uart_handle_dcd_change(struct uart_port *uport, bool active); -extern void uart_handle_cts_change(struct uart_port *uport, bool active); +void uart_handle_dcd_change(struct uart_port *uport, bool active); +void uart_handle_cts_change(struct uart_port *uport, bool active); -extern void uart_insert_char(struct uart_port *port, unsigned int status, - unsigned int overrun, unsigned int ch, unsigned int flag); +void uart_insert_char(struct uart_port *port, unsigned int status, + unsigned int overrun, unsigned int ch, unsigned int flag); void uart_xchar_out(struct uart_port *uport, int offset); diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 52b98f9666a2..ef06a195b3c2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -557,7 +557,7 @@ int sfp_get_module_eeprom_by_page(struct sfp_bus *bus, void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); void sfp_bus_put(struct sfp_bus *bus); -struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode); +struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops); void sfp_bus_del_upstream(struct sfp_bus *bus); @@ -619,7 +619,8 @@ static inline void sfp_bus_put(struct sfp_bus *bus) { } -static inline struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) +static inline struct sfp_bus * +sfp_bus_find_fwnode(const struct fwnode_handle *fwnode) { return NULL; } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 103d1000a5a2..9029abd29b1c 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -9,6 +9,7 @@ #include <linux/percpu_counter.h> #include <linux/xattr.h> #include <linux/fs_parser.h> +#include <linux/userfaultfd_k.h> /* inode in-kernel data */ @@ -45,6 +46,7 @@ struct shmem_sb_info { kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ bool full_inums; /* If i_ino should be uint or ino_t */ + bool noswap; /* ignores VM reclaim / swap requests */ ino_t next_ino; /* The next per-sb inode number to use */ ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ @@ -94,7 +96,14 @@ int shmem_unuse(unsigned int type); extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +#ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); +#else +static inline unsigned long shmem_swap_usage(struct vm_area_struct *vma) +{ + return 0; +} +#endif extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); @@ -151,15 +160,15 @@ extern void shmem_uncharge(struct inode *inode, long pages); #ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM -extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - bool zeropage, bool wp_copy, - struct page **pagep); + uffd_flags_t flags, + struct folio **foliop); #else /* !CONFIG_SHMEM */ -#define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ - src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; }) +#define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ + src_addr, flags, foliop) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 7bde8e1c228a..224293b2dd06 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -107,7 +107,10 @@ extern void synchronize_shrinkers(void); #ifdef CONFIG_SHRINKER_DEBUG extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id); +extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id); extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ @@ -115,10 +118,16 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } -static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { + *debugfs_id = -1; return NULL; } +static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id) +{ +} static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ff7ad331fb82..0b40417457cd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,7 +37,7 @@ #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> -#include <net/dropreason.h> +#include <net/dropreason-core.h> /** * DOC: skb checksums @@ -294,6 +294,7 @@ struct nf_bridge_info { u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; + u8 sabotage_in_done:1; __u16 frag_max_size; struct net_device *physindev; @@ -345,18 +346,12 @@ struct sk_buff_head { struct sk_buff; -/* To allow 64K frame to be packed as single skb without frag_list we - * require 64K/PAGE_SIZE pages plus 1 additional page to allow for - * buffers which do not start on a page boundary. - * - * Since GRO uses frags we allocate at least 16 regardless of page - * size. - */ -#if (65536/PAGE_SIZE + 1) < 16 -#define MAX_SKB_FRAGS 16UL -#else -#define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1) +#ifndef CONFIG_MAX_SKB_FRAGS +# define CONFIG_MAX_SKB_FRAGS 17 #endif + +#define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS + extern int sysctl_max_skb_frags; /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to @@ -810,7 +805,6 @@ typedef unsigned char *sk_buff_data_t; * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) - * @scm_io_uring: SKB holds io_uring registered files * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required @@ -941,38 +935,44 @@ struct sk_buff { /* public: */ __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; - __u8 nf_trace:1; + __u8 dst_pending_confirm:1; __u8 ip_summed:2; __u8 ooo_okay:1; + /* private: */ + __u8 __mono_tc_offset[0]; + /* public: */ + __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ +#ifdef CONFIG_NET_CLS_ACT + __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ + __u8 tc_skip_classify:1; +#endif + __u8 remcsum_offload:1; + __u8 csum_complete_sw:1; + __u8 csum_level:2; + __u8 inner_protocol_type:1; + __u8 l4_hash:1; __u8 sw_hash:1; +#ifdef CONFIG_WIRELESS __u8 wifi_acked_valid:1; __u8 wifi_acked:1; +#endif __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; - - /* private: */ - __u8 __pkt_vlan_present_offset[0]; - /* public: */ - __u8 remcsum_offload:1; - __u8 csum_complete_sw:1; - __u8 csum_level:2; - __u8 dst_pending_confirm:1; - __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ -#ifdef CONFIG_NET_CLS_ACT - __u8 tc_skip_classify:1; - __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ -#endif #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif +#if IS_ENABLED(CONFIG_IP_VS) __u8 ipvs_property:1; - __u8 inner_protocol_type:1; +#endif +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) + __u8 nf_trace:1; +#endif #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; @@ -988,13 +988,16 @@ struct sk_buff { __u8 decrypted:1; #endif __u8 slow_gro:1; +#if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; - __u8 scm_io_uring:1; +#endif #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ #endif + u16 alloc_cpu; + union { __wsum csum; struct { @@ -1018,7 +1021,6 @@ struct sk_buff { unsigned int sender_cpu; }; #endif - u16 alloc_cpu; #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif @@ -1074,13 +1076,13 @@ struct sk_buff { * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD -#define TC_AT_INGRESS_MASK (1 << 0) -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 2) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 7) +#define TC_AT_INGRESS_MASK (1 << 6) #else -#define TC_AT_INGRESS_MASK (1 << 7) -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 0) +#define TC_AT_INGRESS_MASK (1 << 1) #endif -#define PKT_VLAN_PRESENT_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) +#define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) #ifdef __KERNEL__ /* @@ -1195,6 +1197,15 @@ static inline unsigned int skb_napi_id(const struct sk_buff *skb) #endif } +static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) +{ +#ifdef CONFIG_WIRELESS + return skb->wifi_acked_valid; +#else + return 0; +#endif +} + /** * skb_unref - decrement the skb's reference count * @skb: buffer @@ -1576,6 +1587,16 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) to->l4_hash = from->l4_hash; }; +static inline int skb_cmp_decrypted(const struct sk_buff *skb1, + const struct sk_buff *skb2) +{ +#ifdef CONFIG_TLS_DEVICE + return skb2->decrypted - skb1->decrypted; +#else + return 0; +#endif +} + static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { @@ -3242,7 +3263,7 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); -void __kfree_skb_defer(struct sk_buff *skb); +void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); /** * __dev_alloc_pages - allocate page for network Rx @@ -3394,6 +3415,18 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } +static inline void +napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) +{ + struct page *page = skb_frag_page(frag); + +#ifdef CONFIG_PAGE_POOL + if (recycle && page_pool_return_skb_page(page, napi_safe)) + return; +#endif + put_page(page); +} + /** * __skb_frag_unref - release a reference on a paged fragment. * @frag: the paged fragment @@ -3404,13 +3437,7 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) */ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { - struct page *page = skb_frag_page(frag); - -#ifdef CONFIG_PAGE_POOL - if (recycle && page_pool_return_skb_page(page)) - return; -#endif - put_page(page); + napi_frag_unref(frag, recycle, false); } /** @@ -4712,7 +4739,7 @@ static inline void nf_reset_ct(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -4732,7 +4759,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif @@ -5049,9 +5076,30 @@ static inline void skb_reset_redirect(struct sk_buff *skb) skb->redirected = 0; } +static inline void skb_set_redirected_noclear(struct sk_buff *skb, + bool from_ingress) +{ + skb->redirected = 1; +#ifdef CONFIG_NET_REDIRECT + skb->from_ingress = from_ingress; +#endif +} + static inline bool skb_csum_is_sctp(struct sk_buff *skb) { +#if IS_ENABLED(CONFIG_IP_SCTP) return skb->csum_not_inet; +#else + return 0; +#endif +} + +static inline void skb_reset_csum_not_inet(struct sk_buff *skb) +{ + skb->ip_summed = CHECKSUM_NONE; +#if IS_ENABLED(CONFIG_IP_SCTP) + skb->csum_not_inet = 0; +#endif } static inline void skb_set_kcov_handle(struct sk_buff *skb, @@ -5071,12 +5119,12 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) #endif } -#ifdef CONFIG_PAGE_POOL static inline void skb_mark_for_recycle(struct sk_buff *skb) { +#ifdef CONFIG_PAGE_POOL skb->pp_recycle = 1; -} #endif +} #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 84f787416a54..054d7911bfc9 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -71,7 +71,6 @@ struct sk_psock_link { }; struct sk_psock_work_state { - struct sk_buff *skb; u32 len; u32 off; }; @@ -105,7 +104,7 @@ struct sk_psock { struct proto *sk_proto; struct mutex work_mutex; struct sk_psock_work_state work_state; - struct work_struct work; + struct delayed_work work; struct rcu_work rwork; }; diff --git a/include/linux/slab.h b/include/linux/slab.h index 45af70315a94..6b3e155b70bf 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -167,7 +167,6 @@ struct mem_cgroup; /* * struct kmem_cache related prototypes */ -void __init kmem_cache_init(void); bool slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, @@ -284,7 +283,7 @@ static inline unsigned int arch_slab_minalign(void) * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif @@ -292,20 +291,7 @@ static inline unsigned int arch_slab_minalign(void) #ifdef CONFIG_SLUB #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) -#ifndef KMALLOC_SHIFT_LOW -#define KMALLOC_SHIFT_LOW 3 -#endif -#endif - -#ifdef CONFIG_SLOB -/* - * SLOB passes all requests larger than one page to the page allocator. - * No kmalloc array is necessary since objects of different sizes can - * be allocated from the same page. - */ -#define KMALLOC_SHIFT_HIGH PAGE_SHIFT -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif @@ -366,7 +352,6 @@ enum kmalloc_cache_type { NR_KMALLOC_TYPES }; -#ifndef CONFIG_SLOB extern struct kmem_cache * kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; @@ -458,7 +443,6 @@ static __always_inline unsigned int __kmalloc_index(size_t size, } static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) -#endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); @@ -487,10 +471,6 @@ void kmem_cache_free(struct kmem_cache *s, void *objp); 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 - * by kmalloc(), because the SLOB allocator cannot handle this. - */ static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); @@ -526,7 +506,7 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align * to be at least to the size. * * The @flags argument may be one of the GFP flags defined at - * include/linux/gfp.h and described at + * include/linux/gfp_types.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` * * The recommended usage of the @flags is described at @@ -567,7 +547,6 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align * Try really hard to succeed the allocation but fail * eventually. */ -#ifndef CONFIG_SLOB static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size) && size) { @@ -583,17 +562,7 @@ static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) } return __kmalloc(size, flags); } -#else -static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) -{ - if (__builtin_constant_p(size) && size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large(size, flags); - return __kmalloc(size, flags); -} -#endif - -#ifndef CONFIG_SLOB static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && size) { @@ -609,15 +578,6 @@ static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t fla } return __kmalloc_node(size, flags, node); } -#else -static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) -{ - if (__builtin_constant_p(size) && size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large_node(size, flags, node); - - return __kmalloc_node(size, flags, node); -} -#endif /** * kmalloc_array - allocate memory for an array. diff --git a/include/linux/smp.h b/include/linux/smp.h index a80ab58ae3f1..91ea4a67f8ca 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -59,8 +59,8 @@ int smp_call_function_single_async(int cpu, struct __call_single_data *csd); * Cpus stopping functions in panic. All have default weak definitions. * Architecture-dependent code may override them. */ -void panic_smp_self_stop(void); -void nmi_panic_self_stop(struct pt_regs *regs); +void __noreturn panic_smp_self_stop(void); +void __noreturn nmi_panic_self_stop(struct pt_regs *regs); void crash_smp_send_stop(void); /* @@ -125,8 +125,15 @@ extern void smp_send_stop(void); /* * sends a 'reschedule' event to another CPU: */ -extern void smp_send_reschedule(int cpu); - +extern void arch_smp_send_reschedule(int cpu); +/* + * scheduler_ipi() is inline so can't be passed as callback reason, but the + * callsite IP should be sufficient for root-causing IPIs sent from here. + */ +#define smp_send_reschedule(cpu) ({ \ + trace_ipi_send_cpu(cpu, _RET_IP_, NULL); \ + arch_smp_send_reschedule(cpu); \ +}) /* * Prepare machine for booting other CPUs. diff --git a/include/linux/smscphy.h b/include/linux/smscphy.h index 1a136271ba6a..e1c88627755a 100644 --- a/include/linux/smscphy.h +++ b/include/linux/smscphy.h @@ -28,4 +28,14 @@ #define MII_LAN83C185_MODE_POWERDOWN 0xC0 /* Power Down mode */ #define MII_LAN83C185_MODE_ALL 0xE0 /* All capable mode */ +int smsc_phy_config_intr(struct phy_device *phydev); +irqreturn_t smsc_phy_handle_interrupt(struct phy_device *phydev); +int smsc_phy_config_init(struct phy_device *phydev); +int lan87xx_read_status(struct phy_device *phydev); +int smsc_phy_get_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, void *data); +int smsc_phy_set_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, const void *data); +int smsc_phy_probe(struct phy_device *phydev); + #endif /* __LINUX_SMSCPHY_H__ */ diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 2b498f4f3946..649955d2cf5c 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -27,6 +27,8 @@ struct cmdq_client { struct mbox_chan *chan; }; +#if IS_ENABLED(CONFIG_MTK_CMDQ) + /** * cmdq_dev_get_client_reg() - parse cmdq client reg from the device * node of CMDQ client @@ -277,4 +279,116 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt); */ int cmdq_pkt_flush_async(struct cmdq_pkt *pkt); +#else /* IS_ENABLED(CONFIG_MTK_CMDQ) */ + +static inline int cmdq_dev_get_client_reg(struct device *dev, + struct cmdq_client_reg *client_reg, int idx) +{ + return -ENODEV; +} + +static inline struct cmdq_client *cmdq_mbox_create(struct device *dev, int index) +{ + return ERR_PTR(-EINVAL); +} + +static inline void cmdq_mbox_destroy(struct cmdq_client *client) { } + +static inline struct cmdq_pkt *cmdq_pkt_create(struct cmdq_client *client, size_t size) +{ + return ERR_PTR(-EINVAL); +} + +static inline void cmdq_pkt_destroy(struct cmdq_pkt *pkt) { } + +static inline int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys, + u16 offset, u32 value, u32 mask) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_read_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, + u16 addr_low, u16 reg_idx) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, + u16 addr_low, u16 src_reg_idx) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, + u16 addr_low, u16 src_reg_idx, u32 mask) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, + u16 addr_low, u32 value) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, + u16 addr_low, u32 value, u32 mask) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u16 event) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_set_event(struct cmdq_pkt *pkt, u16 event) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_poll(struct cmdq_pkt *pkt, u8 subsys, + u16 offset, u32 value) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, + u16 offset, u32 value, u32 mask) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_flush_async(struct cmdq_pkt *pkt) +{ + return -EINVAL; +} + +#endif /* IS_ENABLED(CONFIG_MTK_CMDQ) */ + #endif /* __MTK_CMDQ_H__ */ diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index dc2963a0a0f7..37544ea6286d 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -99,4 +99,10 @@ void mtk_mmsys_mixer_in_config(struct device *dev, int idx, bool alpha_sel, u16 void mtk_mmsys_mixer_in_channel_swap(struct device *dev, int idx, bool channel_swap, struct cmdq_pkt *cmdq_pkt); +void mtk_mmsys_vpp_rsz_merge_config(struct device *dev, u32 id, bool enable, + struct cmdq_pkt *cmdq_pkt); + +void mtk_mmsys_vpp_rsz_dcm_config(struct device *dev, bool enable, + struct cmdq_pkt *cmdq_pkt); + #endif /* __MTK_MMSYS_H */ diff --git a/include/linux/soc/mediatek/mtk-mutex.h b/include/linux/soc/mediatek/mtk-mutex.h index b335c2837cd8..635218e3ac68 100644 --- a/include/linux/soc/mediatek/mtk-mutex.h +++ b/include/linux/soc/mediatek/mtk-mutex.h @@ -22,6 +22,41 @@ enum mtk_mutex_mod_index { MUTEX_MOD_IDX_MDP_CCORR0, MUTEX_MOD_IDX_MDP_HDR0, MUTEX_MOD_IDX_MDP_COLOR0, + MUTEX_MOD_IDX_MDP_RDMA1, + MUTEX_MOD_IDX_MDP_RDMA2, + MUTEX_MOD_IDX_MDP_RDMA3, + MUTEX_MOD_IDX_MDP_STITCH0, + MUTEX_MOD_IDX_MDP_FG0, + MUTEX_MOD_IDX_MDP_FG1, + MUTEX_MOD_IDX_MDP_FG2, + MUTEX_MOD_IDX_MDP_FG3, + MUTEX_MOD_IDX_MDP_HDR1, + MUTEX_MOD_IDX_MDP_HDR2, + MUTEX_MOD_IDX_MDP_HDR3, + MUTEX_MOD_IDX_MDP_AAL1, + MUTEX_MOD_IDX_MDP_AAL2, + MUTEX_MOD_IDX_MDP_AAL3, + MUTEX_MOD_IDX_MDP_RSZ2, + MUTEX_MOD_IDX_MDP_RSZ3, + MUTEX_MOD_IDX_MDP_MERGE2, + MUTEX_MOD_IDX_MDP_MERGE3, + MUTEX_MOD_IDX_MDP_TDSHP1, + MUTEX_MOD_IDX_MDP_TDSHP2, + MUTEX_MOD_IDX_MDP_TDSHP3, + MUTEX_MOD_IDX_MDP_COLOR1, + MUTEX_MOD_IDX_MDP_COLOR2, + MUTEX_MOD_IDX_MDP_COLOR3, + MUTEX_MOD_IDX_MDP_OVL0, + MUTEX_MOD_IDX_MDP_OVL1, + MUTEX_MOD_IDX_MDP_PAD0, + MUTEX_MOD_IDX_MDP_PAD1, + MUTEX_MOD_IDX_MDP_PAD2, + MUTEX_MOD_IDX_MDP_PAD3, + MUTEX_MOD_IDX_MDP_TCC0, + MUTEX_MOD_IDX_MDP_TCC1, + MUTEX_MOD_IDX_MDP_WROT1, + MUTEX_MOD_IDX_MDP_WROT2, + MUTEX_MOD_IDX_MDP_WROT3, MUTEX_MOD_IDX_MAX /* ALWAYS keep at the end */ }; diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index fd0b0605cf90..b2b28180dff7 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -6,6 +6,7 @@ #include <linux/regmap.h> #include <linux/pci.h> #include <linux/skbuff.h> +#include <linux/netdevice.h> #define MTK_WED_TX_QUEUES 2 #define MTK_WED_RX_QUEUES 2 @@ -179,6 +180,8 @@ struct mtk_wed_ops { u32 (*irq_get)(struct mtk_wed_device *dev, u32 mask); void (*irq_set_mask)(struct mtk_wed_device *dev, u32 mask); + int (*setup_tc)(struct mtk_wed_device *wed, struct net_device *dev, + enum tc_setup_type type, void *type_data); }; extern const struct mtk_wed_ops __rcu *mtk_soc_wed_ops; @@ -237,6 +240,8 @@ mtk_wed_get_rx_capa(struct mtk_wed_device *dev) (_dev)->ops->msg_update(_dev, _id, _msg, _len) #define mtk_wed_device_stop(_dev) (_dev)->ops->stop(_dev) #define mtk_wed_device_dma_reset(_dev) (_dev)->ops->reset_dma(_dev) +#define mtk_wed_device_setup_tc(_dev, _netdev, _type, _type_data) \ + (_dev)->ops->setup_tc(_dev, _netdev, _type, _type_data) #else static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) { @@ -255,6 +260,7 @@ static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) #define mtk_wed_device_update_msg(_dev, _id, _msg, _len) -ENODEV #define mtk_wed_device_stop(_dev) do {} while (0) #define mtk_wed_device_dma_reset(_dev) do {} while (0) +#define mtk_wed_device_setup_tc(_dev, _netdev, _type, _type_data) -EOPNOTSUPP #endif #endif diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h index 400213daa461..c55a0bc8cb0e 100644 --- a/include/linux/soc/qcom/geni-se.h +++ b/include/linux/soc/qcom/geni-se.h @@ -245,12 +245,22 @@ struct geni_se { /* SE_HW_PARAM_0 fields */ #define TX_FIFO_WIDTH_MSK GENMASK(29, 24) #define TX_FIFO_WIDTH_SHFT 24 +/* + * For QUP HW Version >= 3.10 Tx fifo depth support is increased + * to 256bytes and corresponding bits are 16 to 23 + */ +#define TX_FIFO_DEPTH_MSK_256_BYTES GENMASK(23, 16) #define TX_FIFO_DEPTH_MSK GENMASK(21, 16) #define TX_FIFO_DEPTH_SHFT 16 /* SE_HW_PARAM_1 fields */ #define RX_FIFO_WIDTH_MSK GENMASK(29, 24) #define RX_FIFO_WIDTH_SHFT 24 +/* + * For QUP HW Version >= 3.10 Rx fifo depth support is increased + * to 256bytes and corresponding bits are 16 to 23 + */ +#define RX_FIFO_DEPTH_MSK_256_BYTES GENMASK(23, 16) #define RX_FIFO_DEPTH_MSK GENMASK(21, 16) #define RX_FIFO_DEPTH_SHFT 16 @@ -391,7 +401,8 @@ static inline void geni_se_abort_s_cmd(struct geni_se *se) /** * geni_se_get_tx_fifo_depth() - Get the TX fifo depth of the serial engine - * @se: Pointer to the concerned serial engine. + * based on QUP HW version + * @se: Pointer to the concerned serial engine. * * This function is used to get the depth i.e. number of elements in the * TX fifo of the serial engine. @@ -400,11 +411,20 @@ static inline void geni_se_abort_s_cmd(struct geni_se *se) */ static inline u32 geni_se_get_tx_fifo_depth(struct geni_se *se) { - u32 val; + u32 val, hw_version, hw_major, hw_minor, tx_fifo_depth_mask; + + hw_version = geni_se_get_qup_hw_version(se); + hw_major = GENI_SE_VERSION_MAJOR(hw_version); + hw_minor = GENI_SE_VERSION_MINOR(hw_version); + + if ((hw_major == 3 && hw_minor >= 10) || hw_major > 3) + tx_fifo_depth_mask = TX_FIFO_DEPTH_MSK_256_BYTES; + else + tx_fifo_depth_mask = TX_FIFO_DEPTH_MSK; val = readl_relaxed(se->base + SE_HW_PARAM_0); - return (val & TX_FIFO_DEPTH_MSK) >> TX_FIFO_DEPTH_SHFT; + return (val & tx_fifo_depth_mask) >> TX_FIFO_DEPTH_SHFT; } /** @@ -427,7 +447,8 @@ static inline u32 geni_se_get_tx_fifo_width(struct geni_se *se) /** * geni_se_get_rx_fifo_depth() - Get the RX fifo depth of the serial engine - * @se: Pointer to the concerned serial engine. + * based on QUP HW version + * @se: Pointer to the concerned serial engine. * * This function is used to get the depth i.e. number of elements in the * RX fifo of the serial engine. @@ -436,11 +457,20 @@ static inline u32 geni_se_get_tx_fifo_width(struct geni_se *se) */ static inline u32 geni_se_get_rx_fifo_depth(struct geni_se *se) { - u32 val; + u32 val, hw_version, hw_major, hw_minor, rx_fifo_depth_mask; + + hw_version = geni_se_get_qup_hw_version(se); + hw_major = GENI_SE_VERSION_MAJOR(hw_version); + hw_minor = GENI_SE_VERSION_MINOR(hw_version); + + if ((hw_major == 3 && hw_minor >= 10) || hw_major > 3) + rx_fifo_depth_mask = RX_FIFO_DEPTH_MSK_256_BYTES; + else + rx_fifo_depth_mask = RX_FIFO_DEPTH_MSK; val = readl_relaxed(se->base + SE_HW_PARAM_1); - return (val & RX_FIFO_DEPTH_MSK) >> RX_FIFO_DEPTH_SHFT; + return (val & rx_fifo_depth_mask) >> RX_FIFO_DEPTH_SHFT; } void geni_se_init(struct geni_se *se, u32 rx_wm, u32 rx_rfr); diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index ad1fd718169d..93417ba1ead4 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -69,9 +69,6 @@ struct llcc_slice_desc { /** * struct llcc_edac_reg_data - llcc edac registers data for each error type * @name: Name of the error - * @synd_reg: Syndrome register address - * @count_status_reg: Status register address to read the error count - * @ways_status_reg: Status register address to read the error ways * @reg_cnt: Number of registers * @count_mask: Mask value to get the error count * @ways_mask: Mask value to get the error ways @@ -80,9 +77,6 @@ struct llcc_slice_desc { */ struct llcc_edac_reg_data { char *name; - u64 synd_reg; - u64 count_status_reg; - u64 ways_status_reg; u32 reg_cnt; u32 count_mask; u32 ways_mask; @@ -120,7 +114,7 @@ struct llcc_edac_reg_offset { /** * struct llcc_drv_data - Data associated with the llcc driver - * @regmap: regmap associated with the llcc device + * @regmaps: regmaps associated with the llcc device * @bcast_regmap: regmap associated with llcc broadcast offset * @cfg: pointer to the data structure for slice configuration * @edac_reg_offset: Offset of the LLCC EDAC registers @@ -129,12 +123,11 @@ struct llcc_edac_reg_offset { * @max_slices: max slices as read from device tree * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids - * @offsets: Pointer to the bank offsets array * @ecc_irq: interrupt for llcc cache error detection and reporting * @version: Indicates the LLCC version */ struct llcc_drv_data { - struct regmap *regmap; + struct regmap **regmaps; struct regmap *bcast_regmap; const struct llcc_slice_config *cfg; const struct llcc_edac_reg_offset *edac_reg_offset; @@ -143,7 +136,6 @@ struct llcc_drv_data { u32 max_slices; u32 num_banks; unsigned long *bitmap; - u32 *offsets; int ecc_irq; u32 version; }; diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h new file mode 100644 index 000000000000..ceecad74aef9 --- /dev/null +++ b/include/linux/soundwire/sdw_amd.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2023 Advanced Micro Devices, Inc. All rights reserved. + */ + +#ifndef __SDW_AMD_H +#define __SDW_AMD_H + +#include <linux/soundwire/sdw.h> + +/* AMD pm_runtime quirk definitions */ + +/* + * Force the clock to stop(ClockStopMode0) when suspend callback + * is invoked. + */ +#define AMD_SDW_CLK_STOP_MODE 1 + +/* + * Stop the bus when runtime suspend/system level suspend callback + * is invoked. If set, a complete bus reset and re-enumeration will + * be performed when the bus restarts. In-band wake interrupts are + * not supported in this mode. + */ +#define AMD_SDW_POWER_OFF_MODE 2 +#define ACP_SDW0 0 +#define ACP_SDW1 1 + +struct acp_sdw_pdata { + u16 instance; + /* mutex to protect acp common register access */ + struct mutex *acp_sdw_lock; +}; + +struct sdw_manager_reg_mask { + u32 sw_pad_enable_mask; + u32 sw_pad_pulldown_mask; + u32 acp_sdw_intr_mask; +}; + +/** + * struct sdw_amd_dai_runtime: AMD sdw dai runtime data + * + * @name: SoundWire stream name + * @stream: stream runtime + * @bus: Bus handle + * @stream_type: Stream type + */ +struct sdw_amd_dai_runtime { + char *name; + struct sdw_stream_runtime *stream; + struct sdw_bus *bus; + enum sdw_stream_type stream_type; +}; + +/** + * struct amd_sdw_manager - amd manager driver context + * @bus: bus handle + * @dev: linux device + * @mmio: SoundWire registers mmio base + * @acp_mmio: acp registers mmio base + * @reg_mask: register mask structure per manager instance + * @amd_sdw_irq_thread: SoundWire manager irq workqueue + * @amd_sdw_work: peripheral status work queue + * @probe_work: SoundWire manager probe workqueue + * @acp_sdw_lock: mutex to protect acp share register access + * @status: peripheral devices status array + * @num_din_ports: number of input ports + * @num_dout_ports: number of output ports + * @cols_index: Column index in frame shape + * @rows_index: Rows index in frame shape + * @instance: SoundWire manager instance + * @quirks: SoundWire manager quirks + * @wake_en_mask: wake enable mask per SoundWire manager + * @clk_stopped: flag set to true when clock is stopped + * @power_mode_mask: flag interprets amd SoundWire manager power mode + * @dai_runtime_array: dai runtime array + */ +struct amd_sdw_manager { + struct sdw_bus bus; + struct device *dev; + + void __iomem *mmio; + void __iomem *acp_mmio; + + struct sdw_manager_reg_mask *reg_mask; + struct work_struct amd_sdw_irq_thread; + struct work_struct amd_sdw_work; + struct work_struct probe_work; + /* mutex to protect acp common register access */ + struct mutex *acp_sdw_lock; + + enum sdw_slave_status status[SDW_MAX_DEVICES + 1]; + + int num_din_ports; + int num_dout_ports; + + int cols_index; + int rows_index; + + u32 instance; + u32 quirks; + u32 wake_en_mask; + u32 power_mode_mask; + bool clk_stopped; + + struct sdw_amd_dai_runtime **dai_runtime_array; +}; +#endif diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 91f0dc564fe5..207701aeeb47 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -309,6 +309,12 @@ struct sdw_intel; * @shim_wake: enable/disable in-band wake management * @pre_bank_switch: helper for bus management * @post_bank_switch: helper for bus management + * @sync_arm: helper for multi-link synchronization + * @sync_go_unlocked: helper for multi-link synchronization - + * shim_lock is assumed to be locked at higher level + * @sync_go: helper for multi-link synchronization + * @sync_check_cmdsync_unlocked: helper for multi-link synchronization + * and bank switch - shim_lock is assumed to be locked at higher level */ struct sdw_intel_hw_ops { void (*debugfs_init)(struct sdw_intel *sdw); @@ -330,6 +336,11 @@ struct sdw_intel_hw_ops { int (*pre_bank_switch)(struct sdw_intel *sdw); int (*post_bank_switch)(struct sdw_intel *sdw); + + void (*sync_arm)(struct sdw_intel *sdw); + int (*sync_go_unlocked)(struct sdw_intel *sdw); + int (*sync_go)(struct sdw_intel *sdw); + bool (*sync_check_cmdsync_unlocked)(struct sdw_intel *sdw); }; extern const struct sdw_intel_hw_ops sdw_intel_cnl_hw_ops; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 4fa26b9a3572..cfe42f8cd7a4 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -184,8 +184,18 @@ struct spi_device { u8 chip_select; u8 bits_per_word; bool rt; -#define SPI_NO_TX BIT(31) /* No transmit wire */ -#define SPI_NO_RX BIT(30) /* No receive wire */ +#define SPI_NO_TX BIT(31) /* No transmit wire */ +#define SPI_NO_RX BIT(30) /* No receive wire */ + /* + * TPM specification defines flow control over SPI. Client device + * can insert a wait state on MISO when address is transmitted by + * controller on MOSI. Detecting the wait state in software is only + * possible for full duplex controllers. For controllers that support + * only half-duplex, the wait state detection needs to be implemented + * in hardware. TPM devices would set this flag when hardware flow + * control is expected from SPI controller. + */ +#define SPI_TPM_HW_FLOW BIT(29) /* TPM HW flow control */ /* * All bits defined above should be covered by SPI_MODE_KERNEL_MASK. * The SPI_MODE_KERNEL_MASK has the SPI_MODE_USER_MASK counterpart, @@ -195,7 +205,7 @@ struct spi_device { * These bits must not overlap. A static assert check should make sure of that. * If adding extra bits, make sure to decrease the bit index below as well. */ -#define SPI_MODE_KERNEL_MASK (~(BIT(30) - 1)) +#define SPI_MODE_KERNEL_MASK (~(BIT(29) - 1)) u32 mode; int irq; void *controller_state; @@ -244,7 +254,7 @@ static inline void spi_dev_put(struct spi_device *spi) } /* ctldata is for the bus_controller driver's runtime state */ -static inline void *spi_get_ctldata(struct spi_device *spi) +static inline void *spi_get_ctldata(const struct spi_device *spi) { return spi->controller_state; } @@ -261,12 +271,12 @@ static inline void spi_set_drvdata(struct spi_device *spi, void *data) dev_set_drvdata(&spi->dev, data); } -static inline void *spi_get_drvdata(struct spi_device *spi) +static inline void *spi_get_drvdata(const struct spi_device *spi) { return dev_get_drvdata(&spi->dev); } -static inline u8 spi_get_chipselect(struct spi_device *spi, u8 idx) +static inline u8 spi_get_chipselect(const struct spi_device *spi, u8 idx) { return spi->chip_select; } @@ -276,7 +286,7 @@ static inline void spi_set_chipselect(struct spi_device *spi, u8 idx, u8 chipsel spi->chip_select = chipselect; } -static inline struct gpio_desc *spi_get_csgpiod(struct spi_device *spi, u8 idx) +static inline struct gpio_desc *spi_get_csgpiod(const struct spi_device *spi, u8 idx) { return spi->cs_gpiod; } @@ -1093,6 +1103,9 @@ struct spi_message { unsigned is_dma_mapped:1; + /* spi_prepare_message() was called for this message */ + bool prepared; + /* REVISIT: we might want a flag affecting the behavior of the * last transfer ... allowing things like "read 16 bit length L" * immediately followed by "read L bytes". Basically imposing @@ -1105,11 +1118,11 @@ struct spi_message { */ /* Completion is reported through a callback */ + int status; void (*complete)(void *context); void *context; unsigned frame_length; unsigned actual_length; - int status; /* For optional use by whatever driver currently owns the * spi_message ... between calls to spi_async and then later @@ -1120,9 +1133,6 @@ struct spi_message { /* List of spi_res reources when the spi message is processed */ struct list_head resources; - - /* spi_prepare_message() was called for this message */ - bool prepared; }; static inline void spi_message_init_no_memset(struct spi_message *m) @@ -1295,6 +1305,10 @@ extern int spi_split_transfers_maxsize(struct spi_controller *ctlr, struct spi_message *msg, size_t maxsize, gfp_t gfp); +extern int spi_split_transfers_maxwords(struct spi_controller *ctlr, + struct spi_message *msg, + size_t maxwords, + gfp_t gfp); /*---------------------------------------------------------------------------*/ diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 74796cd7e7a9..41c4b26fb1c1 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -102,6 +102,32 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) return lock_is_held(&ssp->dep_map); } +/* + * Annotations provide deadlock detection for SRCU. + * + * Similar to other lockdep annotations, except there is an additional + * srcu_lock_sync(), which is basically an empty *write*-side critical section, + * see lock_sync() for more information. + */ + +/* Annotates a srcu_read_lock() */ +static inline void srcu_lock_acquire(struct lockdep_map *map) +{ + lock_map_acquire_read(map); +} + +/* Annotates a srcu_read_lock() */ +static inline void srcu_lock_release(struct lockdep_map *map) +{ + lock_map_release(map); +} + +/* Annotates a synchronize_srcu() */ +static inline void srcu_lock_sync(struct lockdep_map *map) +{ + lock_map_sync(map); +} + #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) @@ -109,6 +135,10 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) return 1; } +#define srcu_lock_acquire(m) do { } while (0) +#define srcu_lock_release(m) do { } while (0) +#define srcu_lock_sync(m) do { } while (0) + #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #define SRCU_NMI_UNKNOWN 0x0 @@ -182,7 +212,7 @@ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) srcu_check_nmi_safety(ssp, false); retval = __srcu_read_lock(ssp); - rcu_lock_acquire(&(ssp)->dep_map); + srcu_lock_acquire(&(ssp)->dep_map); return retval; } @@ -254,7 +284,7 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) { WARN_ON_ONCE(idx & ~0x1); srcu_check_nmi_safety(ssp, false); - rcu_lock_release(&(ssp)->dep_map); + srcu_lock_release(&(ssp)->dep_map); __srcu_read_unlock(ssp, idx); } diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 5aa5e0faf6a1..ebd72491af99 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -31,7 +31,7 @@ struct srcu_struct { void srcu_drive_gp(struct work_struct *wp); -#define __SRCU_STRUCT_INIT(name, __ignored) \ +#define __SRCU_STRUCT_INIT(name, __ignored, ___ignored) \ { \ .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ @@ -44,9 +44,9 @@ void srcu_drive_gp(struct work_struct *wp); * Tree SRCU, which needs some per-CPU data. */ #define DEFINE_SRCU(name) \ - struct srcu_struct name = __SRCU_STRUCT_INIT(name, name) + struct srcu_struct name = __SRCU_STRUCT_INIT(name, name, name) #define DEFINE_STATIC_SRCU(name) \ - static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name) + static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name, name) void synchronize_srcu(struct srcu_struct *ssp); diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 558057b517b7..8f3f72480e78 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -58,9 +58,9 @@ struct srcu_node { }; /* - * Per-SRCU-domain structure, similar in function to rcu_state. + * Per-SRCU-domain structure, update-side data linked from srcu_struct. */ -struct srcu_struct { +struct srcu_usage { struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ @@ -68,7 +68,6 @@ struct srcu_struct { struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ - unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ @@ -77,7 +76,6 @@ struct srcu_struct { unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ - struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ @@ -89,32 +87,68 @@ struct srcu_struct { unsigned long reschedule_jiffies; unsigned long reschedule_count; struct delayed_work work; + struct srcu_struct *srcu_ssp; +}; + +/* + * Per-SRCU-domain structure, similar in function to rcu_state. + */ +struct srcu_struct { + unsigned int srcu_idx; /* Current rdr array element. */ + struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ struct lockdep_map dep_map; + struct srcu_usage *srcu_sup; /* Update-side data. */ }; -/* Values for size state variable (->srcu_size_state). */ -#define SRCU_SIZE_SMALL 0 -#define SRCU_SIZE_ALLOC 1 -#define SRCU_SIZE_WAIT_BARRIER 2 -#define SRCU_SIZE_WAIT_CALL 3 -#define SRCU_SIZE_WAIT_CBS1 4 -#define SRCU_SIZE_WAIT_CBS2 5 -#define SRCU_SIZE_WAIT_CBS3 6 -#define SRCU_SIZE_WAIT_CBS4 7 -#define SRCU_SIZE_BIG 8 +// Values for size state variable (->srcu_size_state). Once the state +// has been set to SRCU_SIZE_ALLOC, the grace-period code advances through +// this state machine one step per grace period until the SRCU_SIZE_BIG state +// is reached. Otherwise, the state machine remains in the SRCU_SIZE_SMALL +// state indefinitely. +#define SRCU_SIZE_SMALL 0 // No srcu_node combining tree, ->node == NULL +#define SRCU_SIZE_ALLOC 1 // An srcu_node tree is being allocated, initialized, + // and then referenced by ->node. It will not be used. +#define SRCU_SIZE_WAIT_BARRIER 2 // The srcu_node tree starts being used by everything + // except call_srcu(), especially by srcu_barrier(). + // By the end of this state, all CPUs and threads + // are aware of this tree's existence. +#define SRCU_SIZE_WAIT_CALL 3 // The srcu_node tree starts being used by call_srcu(). + // By the end of this state, all of the call_srcu() + // invocations that were running on a non-boot CPU + // and using the boot CPU's callback queue will have + // completed. +#define SRCU_SIZE_WAIT_CBS1 4 // Don't trust the ->srcu_have_cbs[] grace-period +#define SRCU_SIZE_WAIT_CBS2 5 // sequence elements or the ->srcu_data_have_cbs[] +#define SRCU_SIZE_WAIT_CBS3 6 // CPU-bitmask elements until all four elements of +#define SRCU_SIZE_WAIT_CBS4 7 // each array have been initialized. +#define SRCU_SIZE_BIG 8 // The srcu_node combining tree is fully initialized + // and all aspects of it are being put to use. /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 -#define __SRCU_STRUCT_INIT(name, pcpu_name) \ -{ \ - .sda = &pcpu_name, \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .srcu_gp_seq_needed = -1UL, \ - .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ - __SRCU_DEP_MAP_INIT(name) \ +#define __SRCU_USAGE_INIT(name) \ +{ \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .srcu_gp_seq_needed = -1UL, \ + .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ +} + +#define __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ + .srcu_sup = &usage_name, \ + __SRCU_DEP_MAP_INIT(name) + +#define __SRCU_STRUCT_INIT_MODULE(name, usage_name) \ +{ \ + __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ +} + +#define __SRCU_STRUCT_INIT(name, usage_name, pcpu_name) \ +{ \ + .sda = &pcpu_name, \ + __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ } /* @@ -137,16 +171,18 @@ struct srcu_struct { * See include/linux/percpu-defs.h for the rules on per-CPU variables. */ #ifdef MODULE -# define __DEFINE_SRCU(name, is_static) \ - is_static struct srcu_struct name; \ - extern struct srcu_struct * const __srcu_struct_##name; \ - struct srcu_struct * const __srcu_struct_##name \ +# define __DEFINE_SRCU(name, is_static) \ + static struct srcu_usage name##_srcu_usage = __SRCU_USAGE_INIT(name##_srcu_usage); \ + is_static struct srcu_struct name = __SRCU_STRUCT_INIT_MODULE(name, name##_srcu_usage); \ + extern struct srcu_struct * const __srcu_struct_##name; \ + struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else -# define __DEFINE_SRCU(name, is_static) \ - static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \ - is_static struct srcu_struct name = \ - __SRCU_STRUCT_INIT(name, name##_srcu_data) +# define __DEFINE_SRCU(name, is_static) \ + static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \ + static struct srcu_usage name##_srcu_usage = __SRCU_USAGE_INIT(name##_srcu_usage); \ + is_static struct srcu_struct name = \ + __SRCU_STRUCT_INIT(name, name##_srcu_usage, name##_srcu_data) #endif #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) diff --git a/include/linux/start_kernel.h b/include/linux/start_kernel.h index 8b369a41c03c..a9806a44a605 100644 --- a/include/linux/start_kernel.h +++ b/include/linux/start_kernel.h @@ -8,8 +8,8 @@ /* Define the prototype for start_kernel here, rather than cluttering up something else. */ -extern asmlinkage void __init start_kernel(void); -extern void __init arch_call_rest_init(void); -extern void __ref rest_init(void); +extern asmlinkage void __init __noreturn start_kernel(void); +extern void __init __noreturn arch_call_rest_init(void); +extern void __ref __noreturn rest_init(void); #endif /* _LINUX_START_KERNEL_H */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index a152678b82b7..225751a8fd8e 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -186,6 +186,24 @@ struct stmmac_safety_feature_cfg { u32 tmouten; }; +/* Addresses that may be customized by a platform */ +struct dwmac4_addrs { + u32 dma_chan; + u32 dma_chan_offset; + u32 mtl_chan; + u32 mtl_chan_offset; + u32 mtl_ets_ctrl; + u32 mtl_ets_ctrl_offset; + u32 mtl_txq_weight; + u32 mtl_txq_weight_offset; + u32 mtl_send_slp_cred; + u32 mtl_send_slp_cred_offset; + u32 mtl_high_cred; + u32 mtl_high_cred_offset; + u32 mtl_low_cred; + u32 mtl_low_cred_offset; +}; + struct plat_stmmacenet_data { int bus_id; int phy_addr; @@ -215,7 +233,7 @@ struct plat_stmmacenet_data { int unicast_filter_entries; int tx_fifo_size; int rx_fifo_size; - u32 addr64; + u32 host_dma_width; u32 rx_queues_to_use; u32 tx_queues_to_use; u8 rx_sched_algorithm; @@ -223,6 +241,7 @@ struct plat_stmmacenet_data { struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; void (*fix_mac_speed)(void *priv, unsigned int speed); + int (*fix_soc_reset)(void *priv, void __iomem *ioaddr); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); void (*speed_mode_2500)(struct net_device *ndev, void *priv); @@ -273,5 +292,6 @@ struct plat_stmmacenet_data { bool use_phy_wol; bool sph_disable; bool serdes_up_after_phy_linkup; + const struct dwmac4_addrs *dwmac4_addrs; }; #endif diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index ec5a555df96f..518bd28f5ab8 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -300,17 +300,18 @@ static inline int get_time(char **bpp, time64_t *time) return 0; } -static inline time64_t get_expiry(char **bpp) +static inline int get_expiry(char **bpp, time64_t *rvp) { - time64_t rv; + int error; struct timespec64 boot; - if (get_time(bpp, &rv)) - return 0; - if (rv < 0) - return 0; + error = get_time(bpp, rvp); + if (error) + return error; + getboottime64(&boot); - return rv - boot.tv_sec; + (*rvp) -= boot.tv_sec; + return 0; } #endif /* _LINUX_SUNRPC_CACHE_H_ */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index b8ca3ecaf8d7..8ada7dc802d3 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -90,8 +90,7 @@ struct rpc_task { #endif unsigned char tk_priority : 2,/* Task priority */ tk_garb_retry : 2, - tk_cred_retry : 2, - tk_rebind_retry : 2; + tk_cred_retry : 2; }; typedef void (*rpc_action)(struct rpc_task *); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 877891536c2f..762d7231e574 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -309,17 +309,6 @@ static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst) return (struct sockaddr *) &rqst->rq_daddr; } -static inline void svc_free_res_pages(struct svc_rqst *rqstp) -{ - while (rqstp->rq_next_page != rqstp->rq_respages) { - struct page **pp = --rqstp->rq_next_page; - if (*pp) { - put_page(*pp); - *pp = NULL; - } - } -} - struct svc_deferred_req { u32 prot; /* protocol (UDP or TCP) */ struct svc_xprt *xprt; @@ -422,15 +411,16 @@ struct svc_serv *svc_create(struct svc_program *, unsigned int, int (*threadfn)(void *data)); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); -void svc_rqst_replace_page(struct svc_rqst *rqstp, +bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); +void svc_rqst_release_pages(struct svc_rqst *rqstp); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, int (*threadfn)(void *data)); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); -int svc_process(struct svc_rqst *); +void svc_process(struct svc_rqst *rqstp); int bc_svc_process(struct svc_serv *, struct rpc_rqst *, struct svc_rqst *); int svc_register(const struct svc_serv *, struct net *, const int, diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24aa159d29a7..fbc4bd423b35 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -176,7 +176,7 @@ extern struct svc_rdma_recv_ctxt * extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt); extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma); -extern void svc_rdma_release_rqst(struct svc_rqst *rqstp); +extern void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *ctxt); extern int svc_rdma_recvfrom(struct svc_rqst *); /* svc_rdma_rw.c */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 775368802762..a6b12631db21 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -23,11 +23,11 @@ struct svc_xprt_ops { int (*xpo_sendto)(struct svc_rqst *); int (*xpo_result_payload)(struct svc_rqst *, unsigned int, unsigned int); - void (*xpo_release_rqst)(struct svc_rqst *); + void (*xpo_release_ctxt)(struct svc_xprt *xprt, void *ctxt); void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); void (*xpo_kill_temp_xprt)(struct svc_xprt *); - void (*xpo_start_tls)(struct svc_xprt *); + void (*xpo_handshake)(struct svc_xprt *xprt); }; struct svc_xprt_class { @@ -70,6 +70,9 @@ struct svc_xprt { #define XPT_LOCAL 12 /* connection from loopback interface */ #define XPT_KILL_TEMP 13 /* call xpo_kill_temp_xprt before closing */ #define XPT_CONG_CTRL 14 /* has congestion control */ +#define XPT_HANDSHAKE 15 /* xprt requests a handshake */ +#define XPT_TLS_SESSION 16 /* transport-layer security established */ +#define XPT_PEER_AUTH 17 /* peer has been authenticated */ struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index bcc555c7ae9c..a7116048a4d4 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -38,6 +38,8 @@ struct svc_sock { /* Number of queued send requests */ atomic_t sk_sendqlen; + struct completion sk_handshake_done; + struct page * sk_pages[RPCSVC_MAXPAGES]; /* received data */ }; @@ -56,13 +58,12 @@ static inline u32 svc_sock_final_rec(struct svc_sock *svsk) */ void svc_close_net(struct svc_serv *, struct net *); int svc_recv(struct svc_rqst *, long); -int svc_send(struct svc_rqst *); +void svc_send(struct svc_rqst *rqstp); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); -bool svc_alien_sock(struct net *net, int fd); -int svc_addsock(struct svc_serv *serv, const int fd, - char *name_return, const size_t len, - const struct cred *cred); +int svc_addsock(struct svc_serv *serv, struct net *net, + const int fd, char *name_return, const size_t len, + const struct cred *cred); void svc_init_xprt_sock(void); void svc_cleanup_xprt_sock(void); struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot); diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index df81043b9e71..42b249b4c24b 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -243,11 +243,7 @@ static inline bool is_ssam_device(struct device *d) * Return: Returns the pointer to the &struct ssam_device_driver wrapping the * given device driver @d. */ -static inline -struct ssam_device_driver *to_ssam_device_driver(struct device_driver *d) -{ - return container_of(d, struct ssam_device_driver, driver); -} +#define to_ssam_device_driver(d) container_of_const(d, struct ssam_device_driver, driver) const struct ssam_device_id *ssam_device_id_match(const struct ssam_device_id *table, const struct ssam_device_uid uid); diff --git a/include/linux/suspend.h b/include/linux/suspend.h index cfe19a028918..d0d4598a7b3f 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -68,6 +68,9 @@ struct suspend_stats { int last_failed_errno; int errno[REC_FAILED_NUM]; int last_failed_step; + u64 last_hw_sleep; + u64 total_hw_sleep; + u64 max_hw_sleep; enum suspend_stat_step failed_steps[REC_FAILED_NUM]; }; @@ -489,6 +492,8 @@ void restore_processor_state(void); extern int register_pm_notifier(struct notifier_block *nb); extern int unregister_pm_notifier(struct notifier_block *nb); extern void ksys_sync_helper(void); +extern void pm_report_hw_sleep_time(u64 t); +extern void pm_report_max_hw_sleep(u64 t); #define pm_notifier(fn, pri) { \ static struct notifier_block fn##_nb = \ @@ -526,6 +531,9 @@ static inline int unregister_pm_notifier(struct notifier_block *nb) return 0; } +static inline void pm_report_hw_sleep_time(u64 t) {}; +static inline void pm_report_max_hw_sleep(u64 t) {}; + static inline void ksys_sync_helper(void) {} #define pm_notifier(fn, pri) do { (void)(fn); } while (0) diff --git a/include/linux/swap.h b/include/linux/swap.h index 209a425739a9..3c69cb653cb9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -153,13 +153,28 @@ union swap_header { * memory reclaim */ struct reclaim_state { - unsigned long reclaimed_slab; + /* pages reclaimed outside of LRU-based reclaim */ + unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; +/* + * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based + * reclaim + * @pages: number of pages reclaimed + * + * If the current process is undergoing a reclaim operation, increment the + * number of reclaimed pages by @pages. + */ +static inline void mm_account_reclaimed_pages(unsigned long pages) +{ + if (current->reclaim_state) + current->reclaim_state->reclaimed += pages; +} + #ifdef __KERNEL__ struct address_space; @@ -427,7 +442,6 @@ extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); -extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; @@ -620,18 +634,18 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return vm_swappiness; + return READ_ONCE(vm_swappiness); /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) - return vm_swappiness; + return READ_ONCE(vm_swappiness); - return memcg->swappiness; + return READ_ONCE(memcg->swappiness); } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { - return vm_swappiness; + return READ_ONCE(vm_swappiness); } #endif @@ -641,22 +655,18 @@ extern atomic_t zswap_stored_pages; #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); -static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) +void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); +static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { if (mem_cgroup_disabled()) return; - __cgroup_throttle_swaprate(page, gfp_mask); + __folio_throttle_swaprate(folio, gfp); } #else -static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) -{ -} -#endif static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { - cgroup_throttle_swaprate(&folio->page, gfp); } +#endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index bcef10e20ea4..7af2673b47ba 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -87,6 +87,11 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, * @for_alloc: %true if the pool is used for memory allocation * @nareas: The area number in the pool. * @area_nslabs: The slot number in the area. + * @total_used: The total number of slots in the pool that are currently used + * across all areas. Used only for calculating used_hiwater in + * debugfs. + * @used_hiwater: The high water mark for total_used. Used only for reporting + * in debugfs. */ struct io_tlb_mem { phys_addr_t start; @@ -102,6 +107,10 @@ struct io_tlb_mem { unsigned int area_nslabs; struct io_tlb_area *areas; struct io_tlb_slot *slots; +#ifdef CONFIG_DEBUG_FS + atomic_long_t total_used; + atomic_long_t used_hiwater; +#endif }; extern struct io_tlb_mem io_tlb_default_mem; @@ -180,6 +189,4 @@ static inline bool is_swiotlb_for_alloc(struct device *dev) } #endif /* CONFIG_DMA_RESTRICTED_POOL */ -extern phys_addr_t swiotlb_unencrypted_base; - #endif /* __LINUX_SWIOTLB_H */ diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h index a0ae443fb7df..641ca8880995 100644 --- a/include/linux/syscall_user_dispatch.h +++ b/include/linux/syscall_user_dispatch.h @@ -22,6 +22,12 @@ int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, #define clear_syscall_work_syscall_user_dispatch(tsk) \ clear_task_syscall_work(tsk, SYSCALL_USER_DISPATCH) +int syscall_user_dispatch_get_config(struct task_struct *task, unsigned long size, + void __user *data); + +int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long size, + void __user *data); + #else struct syscall_user_dispatch {}; @@ -35,6 +41,18 @@ static inline void clear_syscall_work_syscall_user_dispatch(struct task_struct * { } +static inline int syscall_user_dispatch_get_config(struct task_struct *task, + unsigned long size, void __user *data) +{ + return -EINVAL; +} + +static inline int syscall_user_dispatch_set_config(struct task_struct *task, + unsigned long size, void __user *data) +{ + return -EINVAL; +} + #endif /* CONFIG_GENERIC_ENTRY */ #endif /* _SYSCALL_USER_DISPATCH_H */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 780690dc08cd..3d08277959af 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -221,14 +221,8 @@ extern void retire_sysctl_set(struct ctl_table_set *set); struct ctl_table_header *__register_sysctl_table( struct ctl_table_set *set, const char *path, struct ctl_table *table); -struct ctl_table_header *__register_sysctl_paths( - struct ctl_table_set *set, - const struct ctl_path *path, struct ctl_table *table); struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table); struct ctl_table_header *register_sysctl_table(struct ctl_table * table); -struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, - struct ctl_table *table); - void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init_bases(void); @@ -277,12 +271,6 @@ static inline struct ctl_table_header *register_sysctl_mount_point(const char *p return NULL; } -static inline struct ctl_table_header *register_sysctl_paths( - const struct ctl_path *path, struct ctl_table *table) -{ - return NULL; -} - static inline struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table) { return NULL; diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index 8ba8b5be5567..c1ef5fc60a3c 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -70,11 +70,16 @@ static inline void sysfb_disable(void) #ifdef CONFIG_EFI extern struct efifb_dmi_info efifb_dmi_list[]; -void sysfb_apply_efi_quirks(struct platform_device *pd); +void sysfb_apply_efi_quirks(void); +void sysfb_set_efifb_fwnode(struct platform_device *pd); #else /* CONFIG_EFI */ -static inline void sysfb_apply_efi_quirks(struct platform_device *pd) +static inline void sysfb_apply_efi_quirks(void) +{ +} + +static inline void sysfb_set_efifb_fwnode(struct platform_device *pd) { } diff --git a/include/linux/tca6416_keypad.h b/include/linux/tca6416_keypad.h index b0d36a9934cc..5cf6f6f82aa7 100644 --- a/include/linux/tca6416_keypad.h +++ b/include/linux/tca6416_keypad.h @@ -25,7 +25,6 @@ struct tca6416_keys_platform_data { unsigned int rep:1; /* enable input subsystem auto repeat */ uint16_t pinmask; uint16_t invert; - int irq_is_gpio; int use_polling; /* use polling if Interrupt is not connected*/ }; #endif diff --git a/include/linux/tcp.h b/include/linux/tcp.h index ca7f05a130d2..b4c08ac86983 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -472,10 +472,12 @@ enum tsq_flags { TCPF_MTU_REDUCED_DEFERRED = (1UL << TCP_MTU_REDUCED_DEFERRED), }; -static inline struct tcp_sock *tcp_sk(const struct sock *sk) -{ - return (struct tcp_sock *)sk; -} +#define tcp_sk(ptr) container_of_const(ptr, struct tcp_sock, inet_conn.icsk_inet.sk) + +/* Variant of tcp_sk() upgrading a const sock to a read/write tcp socket. + * Used in context of (lockless) tcp listeners. + */ +#define tcp_sk_rw(ptr) container_of(ptr, struct tcp_sock, inet_conn.icsk_inet.sk) struct tcp_timewait_sock { struct inet_timewait_sock tw_sk; diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 2bb4bf33f4f3..87837094d549 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -207,41 +207,6 @@ struct thermal_governor { struct list_head governor_list; }; -/* Structure that holds binding parameters for a zone */ -struct thermal_bind_params { - struct thermal_cooling_device *cdev; - - /* - * This is a measure of 'how effectively these devices can - * cool 'this' thermal zone. It shall be determined by - * platform characterization. This value is relative to the - * rest of the weights so a cooling device whose weight is - * double that of another cooling device is twice as - * effective. See Documentation/driver-api/thermal/sysfs-api.rst for more - * information. - */ - int weight; - - /* - * This is a bit mask that gives the binding relation between this - * thermal zone and cdev, for a particular trip point. - * See Documentation/driver-api/thermal/sysfs-api.rst for more information. - */ - int trip_mask; - - /* - * This is an array of cooling state limits. Must have exactly - * 2 * thermal_zone.number_of_trip_points. It is an array consisting - * of tuples <lower-state upper-state> of state limits. Each trip - * will be associated with one state limit tuple when binding. - * A NULL pointer means <THERMAL_NO_LIMITS THERMAL_NO_LIMITS> - * on all trips. - */ - unsigned long *binding_limits; - int (*match) (struct thermal_zone_device *tz, - struct thermal_cooling_device *cdev); -}; - /* Structure to define Thermal Zone parameters */ struct thermal_zone_params { char governor_name[THERMAL_NAME_LENGTH]; @@ -253,9 +218,6 @@ struct thermal_zone_params { */ bool no_hwmon; - int num_tbps; /* Number of tbp entries */ - struct thermal_bind_params *tbp; - /* * Sustainable power (heat) that this thermal zone can dissipate in * mW @@ -297,25 +259,12 @@ struct thermal_zone_params { /* Function declarations */ #ifdef CONFIG_THERMAL_OF -struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data, - const struct thermal_zone_device_ops *ops); - struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, int id, void *data, const struct thermal_zone_device_ops *ops); -void thermal_of_zone_unregister(struct thermal_zone_device *tz); - void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_device *tz); -void thermal_of_zone_unregister(struct thermal_zone_device *tz); - #else -static inline -struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data, - const struct thermal_zone_device_ops *ops) -{ - return ERR_PTR(-ENOTSUPP); -} static inline struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, int id, void *data, @@ -324,10 +273,6 @@ struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, in return ERR_PTR(-ENOTSUPP); } -static inline void thermal_of_zone_unregister(struct thermal_zone_device *tz) -{ -} - static inline void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_device *tz) { @@ -365,6 +310,11 @@ thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int void *, struct thermal_zone_device_ops *, struct thermal_zone_params *, int, int); +void *thermal_zone_device_priv(struct thermal_zone_device *tzd); +const char *thermal_zone_device_type(struct thermal_zone_device *tzd); +int thermal_zone_device_id(struct thermal_zone_device *tzd); +struct device *thermal_zone_device(struct thermal_zone_device *tzd); + int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, unsigned long, unsigned long, @@ -384,6 +334,7 @@ devm_thermal_of_cooling_device_register(struct device *dev, struct device_node *np, char *type, void *devdata, const struct thermal_cooling_device_ops *ops); +void thermal_cooling_device_update(struct thermal_cooling_device *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); @@ -436,6 +387,21 @@ static inline int thermal_zone_get_offset( struct thermal_zone_device *tz) { return -ENODEV; } +static inline void *thermal_zone_device_priv(struct thermal_zone_device *tz) +{ + return NULL; +} + +static inline const char *thermal_zone_device_type(struct thermal_zone_device *tzd) +{ + return NULL; +} + +static inline int thermal_zone_device_id(struct thermal_zone_device *tzd) +{ + return -ENODEV; +} + static inline int thermal_zone_device_enable(struct thermal_zone_device *tz) { return -ENODEV; } diff --git a/include/linux/tick.h b/include/linux/tick.h index bfd571f18cfd..9459fef5b857 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -216,6 +216,7 @@ extern void tick_nohz_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit); extern void tick_nohz_dep_clear_signal(struct signal_struct *signal, enum tick_dep_bits bit); +extern bool tick_nohz_cpu_hotpluggable(unsigned int cpu); /* * The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases @@ -280,6 +281,7 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } static inline void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } static inline void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { } +static inline bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { return true; } static inline void tick_dep_set(enum tick_dep_bits bit) { } static inline void tick_dep_clear(enum tick_dep_bits bit) { } diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4dc97b9f65fb..6a1e8f157255 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -274,13 +274,15 @@ enum tpm2_cc_attrs { #define TPM_VID_ATML 0x1114 enum tpm_chip_flags { - TPM_CHIP_FLAG_TPM2 = BIT(1), - TPM_CHIP_FLAG_IRQ = BIT(2), - TPM_CHIP_FLAG_VIRTUAL = BIT(3), - TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), - TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), + TPM_CHIP_FLAG_BOOTSTRAPPED = BIT(0), + TPM_CHIP_FLAG_TPM2 = BIT(1), + TPM_CHIP_FLAG_IRQ = BIT(2), + TPM_CHIP_FLAG_VIRTUAL = BIT(3), + TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), + TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), - TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), + TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), + TPM_CHIP_FLAG_SUSPENDED = BIT(8), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 0e373222a6df..7c4a0b72334e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -806,6 +806,7 @@ enum { FILTER_TRACE_FN, FILTER_COMM, FILTER_CPU, + FILTER_STACKTRACE, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index e299f29375bb..6811e43c1b5c 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -242,12 +242,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. * - * When lockdep is enabled, we make sure to always do the RCU portions of - * the tracepoint code, regardless of whether tracing is on. However, - * don't check if the condition is false, due to interaction with idle - * instrumentation. This lets us find RCU issues triggered with tracepoints - * even when this tracepoint is off. This code has no purpose other than - * poking RCU a bit. + * When lockdep is enabled, we make sure to always test if RCU is + * "watching" regardless if the tracepoint is enabled or not. Tracepoints + * require RCU to be active, and it should always warn at the tracepoint + * site if it is not watching, as it will need to be active when the + * tracepoint is enabled. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ extern int __traceiter_##name(data_proto); \ @@ -260,9 +259,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) TP_ARGS(args), \ TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ - rcu_read_lock_sched_notrace(); \ - rcu_dereference_sched(__tracepoint_##name.funcs);\ - rcu_read_unlock_sched_notrace(); \ + WARN_ON_ONCE(!rcu_is_watching()); \ } \ } \ __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \ diff --git a/include/linux/tty.h b/include/linux/tty.h index 093935e97f42..e8d5d9997aca 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -227,7 +227,7 @@ struct tty_struct { unsigned long unused[0]; } __aligned(sizeof(unsigned long)) ctrl; - int hw_stopped; + bool hw_stopped; unsigned int receive_room; int flow_change; @@ -387,7 +387,7 @@ extern struct ktermios tty_std_termios; int vcs_init(void); -extern struct class *tty_class; +extern const struct class tty_class; /** * tty_kref_get - get a tty reference diff --git a/include/linux/types.h b/include/linux/types.h index ea8cf60a8a79..688fb943556a 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -175,6 +175,12 @@ typedef struct { } atomic64_t; #endif +typedef struct { + atomic_t refcnt; +} rcuref_t; + +#define RCUREF_INIT(i) { .refcnt = ATOMIC_INIT(i - 1) } + struct list_head { struct list_head *next, *prev; }; diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ab9728138ad6..3064314f4832 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -11,6 +11,28 @@ #include <asm/uaccess.h> /* + * Architectures that support memory tagging (assigning tags to memory regions, + * embedding these tags into addresses that point to these memory regions, and + * checking that the memory and the pointer tags match on memory accesses) + * redefine this macro to strip tags from pointers. + * + * Passing down mm_struct allows to define untagging rules on per-process + * basis. + * + * It's defined as noop for architectures that don't support memory tagging. + */ +#ifndef untagged_addr +#define untagged_addr(addr) (addr) +#endif + +#ifndef untagged_addr_remote +#define untagged_addr_remote(mm, addr) ({ \ + mmap_assert_locked(mm); \ + untagged_addr(addr); \ +}) +#endif + +/* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). diff --git a/include/linux/udp.h b/include/linux/udp.h index a2892e151644..43c1fb2d2c21 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -97,10 +97,7 @@ struct udp_sock { #define UDP_MAX_SEGMENTS (1 << 6UL) -static inline struct udp_sock *udp_sk(const struct sock *sk) -{ - return (struct udp_sock *)sk; -} +#define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) static inline void udp_set_no_check6_tx(struct sock *sk, bool val) { diff --git a/include/linux/uio.h b/include/linux/uio.h index 27e3fd942960..044c1d8c230c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -42,6 +42,7 @@ struct iov_iter_state { struct iov_iter { u8 iter_type; + bool copy_mc; bool nofault; bool data_source; bool user_backed; @@ -49,14 +50,35 @@ struct iov_iter { size_t iov_offset; int last_offset; }; - size_t count; + /* + * Hack alert: overlay ubuf_iovec with iovec + count, so + * that the members resolve correctly regardless of the type + * of iterator used. This means that you can use: + * + * &iter->__ubuf_iovec or iter->__iov + * + * interchangably for the user_backed cases, hence simplifying + * some of the cases that need to deal with both. + */ union { - const struct iovec *iov; - const struct kvec *kvec; - const struct bio_vec *bvec; - struct xarray *xarray; - struct pipe_inode_info *pipe; - void __user *ubuf; + /* + * This really should be a const, but we cannot do that without + * also modifying any of the zero-filling iter init functions. + * Leave it non-const for now, but it should be treated as such. + */ + struct iovec __ubuf_iovec; + struct { + union { + /* use iter_iov() to get the current vec */ + const struct iovec *__iov; + const struct kvec *kvec; + const struct bio_vec *bvec; + struct xarray *xarray; + struct pipe_inode_info *pipe; + void __user *ubuf; + }; + size_t count; + }; }; union { unsigned long nr_segs; @@ -68,6 +90,16 @@ struct iov_iter { }; }; +static inline const struct iovec *iter_iov(const struct iov_iter *iter) +{ + if (iter->iter_type == ITER_UBUF) + return (const struct iovec *) &iter->__ubuf_iovec; + return iter->__iov; +} + +#define iter_iov_addr(iter) (iter_iov(iter)->iov_base + (iter)->iov_offset) +#define iter_iov_len(iter) (iter_iov(iter)->iov_len - (iter)->iov_offset) + static inline enum iter_type iov_iter_type(const struct iov_iter *i) { return i->iter_type; @@ -143,15 +175,6 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) return ret; } -static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) -{ - return (struct iovec) { - .iov_base = iter->iov->iov_base + iter->iov_offset, - .iov_len = min(iter->count, - iter->iov->iov_len - iter->iov_offset), - }; -} - size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i); void iov_iter_advance(struct iov_iter *i, size_t bytes); @@ -173,6 +196,8 @@ static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, { return copy_page_to_iter(&folio->page, offset, bytes, i); } +size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, + size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) @@ -232,8 +257,22 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); +static inline void iov_iter_set_copy_mc(struct iov_iter *i) +{ + i->copy_mc = true; +} + +static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) +{ + return i->copy_mc; +} #else #define _copy_mc_to_iter _copy_to_iter +static inline void iov_iter_set_copy_mc(struct iov_iter *i) { } +static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) +{ + return false; +} #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); @@ -356,10 +395,12 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, + .copy_mc = false, .user_backed = true, .data_source = direction, .ubuf = buf, - .count = count + .count = count, + .nr_segs = 1 }; } /* Flags for iov_iter_get/extract_pages*() */ diff --git a/include/linux/usb.h b/include/linux/usb.h index 9642ee02d713..25f8e62a30ec 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -170,6 +170,12 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt, return usb_find_common_endpoints_reverse(alt, NULL, NULL, NULL, int_out); } +enum usb_wireless_status { + USB_WIRELESS_STATUS_NA = 0, + USB_WIRELESS_STATUS_DISCONNECTED, + USB_WIRELESS_STATUS_CONNECTED, +}; + /** * struct usb_interface - what usb device drivers talk to * @altsetting: array of interface structures, one for each alternate @@ -197,6 +203,10 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt, * following a reset or suspend operation it doesn't support. * @authorized: This allows to (de)authorize individual interfaces instead * a whole device in contrast to the device authorization. + * @wireless_status: if the USB device uses a receiver/emitter combo, whether + * the emitter is connected. + * @wireless_status_work: Used for scheduling wireless status changes + * from atomic context. * @dev: driver model's view of this device * @usb_dev: if an interface is bound to the USB major, this will point * to the sysfs representation for that device. @@ -253,6 +263,8 @@ struct usb_interface { unsigned needs_binding:1; /* needs delayed unbind/rebind */ unsigned resetting_device:1; /* true: bandwidth alloc after reset */ unsigned authorized:1; /* used for interface authorization */ + enum usb_wireless_status wireless_status; + struct work_struct wireless_status_work; struct device dev; /* interface specific device info */ struct device *usb_dev; @@ -291,6 +303,11 @@ void usb_put_intf(struct usb_interface *intf); #define USB_MAXINTERFACES 32 #define USB_MAXIADS (USB_MAXINTERFACES/2) +bool usb_check_bulk_endpoints( + const struct usb_interface *intf, const u8 *ep_addrs); +bool usb_check_int_endpoints( + const struct usb_interface *intf, const u8 *ep_addrs); + /* * USB Resume Timer: Every Host controller driver should drive the resume * signalling on the bus for the amount of time defined by this macro. @@ -704,13 +721,12 @@ struct usb_device { unsigned long active_duration; -#ifdef CONFIG_PM unsigned long connect_time; unsigned do_remote_wakeup:1; unsigned reset_resume:1; unsigned port_is_suspended:1; -#endif + struct wusb_dev *wusb_dev; int slot_id; struct usb2_lpm_parameters l1_params; @@ -887,6 +903,10 @@ static inline int usb_interface_claimed(struct usb_interface *iface) extern void usb_driver_release_interface(struct usb_driver *driver, struct usb_interface *iface); + +int usb_set_wireless_status(struct usb_interface *iface, + enum usb_wireless_status status); + const struct usb_device_id *usb_match_id(struct usb_interface *interface, const struct usb_device_id *id); extern int usb_match_one_id(struct usb_interface *interface, diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 608dc962748b..07531c4f4350 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -150,6 +150,9 @@ struct usb_os_desc_table { * GetStatus() request when the recipient is Interface. * @func_suspend: callback to be called when * SetFeature(FUNCTION_SUSPEND) is reseived + * @func_suspended: Indicates whether the function is in function suspend state. + * @func_wakeup_armed: Indicates whether the function is armed by the host for + * wakeup signaling. * * A single USB function uses one or more interfaces, and should in most * cases support operation at both full and high speeds. Each function is @@ -220,6 +223,8 @@ struct usb_function { int (*get_status)(struct usb_function *); int (*func_suspend)(struct usb_function *, u8 suspend_opt); + bool func_suspended; + bool func_wakeup_armed; /* private: */ /* internals */ struct list_head list; @@ -241,6 +246,7 @@ int config_ep_by_speed_and_alt(struct usb_gadget *g, struct usb_function *f, int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep); +int usb_func_wakeup(struct usb_function *func); #define MAX_CONFIG_INTERFACES 16 /* arbitrary; max 255 */ @@ -413,6 +419,8 @@ extern int composite_dev_prepare(struct usb_composite_driver *composite, extern int composite_os_desc_req_prepare(struct usb_composite_dev *cdev, struct usb_ep *ep0); void composite_dev_cleanup(struct usb_composite_dev *cdev); +void check_remote_wakeup_config(struct usb_gadget *g, + struct usb_configuration *c); static inline struct usb_composite_driver *to_cdriver( struct usb_gadget_driver *gdrv) @@ -435,7 +443,7 @@ static inline struct usb_composite_driver *to_cdriver( * @bcd_webusb_version: 0x0100 by default, WebUSB specification version * @b_webusb_vendor_code: 0x0 by default, vendor code for WebUSB * @landing_page: empty by default, landing page to announce in WebUSB - * @use_webusb:: false by default, interested gadgets set it + * @use_webusb: false by default, interested gadgets set it * @os_desc_config: the configuration to be used with OS descriptors * @setup_pending: true when setup request is queued but not completed * @os_desc_pending: true when os_desc request is queued but not completed diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 00750f7020f3..75bda0783395 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -310,6 +310,8 @@ struct usb_udc; struct usb_gadget_ops { int (*get_frame)(struct usb_gadget *); int (*wakeup)(struct usb_gadget *); + int (*func_wakeup)(struct usb_gadget *gadget, int intf_id); + int (*set_remote_wakeup)(struct usb_gadget *, int set); int (*set_selfpowered) (struct usb_gadget *, int is_selfpowered); int (*vbus_session) (struct usb_gadget *, int is_active); int (*vbus_draw) (struct usb_gadget *, unsigned mA); @@ -384,6 +386,8 @@ struct usb_gadget_ops { * @connected: True if gadget is connected. * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. + * @wakeup_capable: True if gadget is capable of sending remote wakeup. + * @wakeup_armed: True if gadget is armed by the host for remote wakeup. * @irq: the interrupt number for device controller. * @id_number: a unique ID number for ensuring that gadget names are distinct * @@ -445,6 +449,8 @@ struct usb_gadget { unsigned deactivated:1; unsigned connected:1; unsigned lpm_capable:1; + unsigned wakeup_capable:1; + unsigned wakeup_armed:1; int irq; int id_number; }; @@ -601,6 +607,7 @@ static inline int gadget_is_otg(struct usb_gadget *g) #if IS_ENABLED(CONFIG_USB_GADGET) int usb_gadget_frame_number(struct usb_gadget *gadget); int usb_gadget_wakeup(struct usb_gadget *gadget); +int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set); int usb_gadget_set_selfpowered(struct usb_gadget *gadget); int usb_gadget_clear_selfpowered(struct usb_gadget *gadget); int usb_gadget_vbus_connect(struct usb_gadget *gadget); @@ -616,6 +623,8 @@ static inline int usb_gadget_frame_number(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_wakeup(struct usb_gadget *gadget) { return 0; } +static inline int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set) +{ return 0; } static inline int usb_gadget_set_selfpowered(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index b51c07111729..0c7eff91adf4 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -488,9 +488,7 @@ extern void usb_hcd_pci_shutdown(struct pci_dev *dev); extern int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *dev); -#ifdef CONFIG_PM extern const struct dev_pm_ops usb_hcd_pci_pm_ops; -#endif #endif /* CONFIG_USB_PCI */ /* pci-ish (pdev null is ok) buffer alloc/mapping support */ @@ -503,6 +501,11 @@ void *hcd_buffer_alloc(struct usb_bus *bus, size_t size, void hcd_buffer_free(struct usb_bus *bus, size_t size, void *addr, dma_addr_t dma); +void *hcd_buffer_alloc_pages(struct usb_hcd *hcd, + size_t size, gfp_t mem_flags, dma_addr_t *dma); +void hcd_buffer_free_pages(struct usb_hcd *hcd, + size_t size, void *addr, dma_addr_t dma); + /* generic bus glue, needed for host controllers that don't use PCI */ extern irqreturn_t usb_hcd_irq(int irq, void *__hcd); diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index f7bfedb740f5..7eeb5f9c4f0d 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -378,7 +378,7 @@ void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, int usb_serial_bus_register(struct usb_serial_driver *device); void usb_serial_bus_deregister(struct usb_serial_driver *device); -extern struct bus_type usb_serial_bus_type; +extern const struct bus_type usb_serial_bus_type; extern struct tty_driver *usb_serial_tty_driver; static inline void usb_serial_debug_data(struct device *dev, diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 592a3fbed98e..8afa8c3a0973 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -1,54 +1,84 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2021, Microsoft Corporation. + * Copyright (c) 2022, Microsoft Corporation. * * Authors: * Beau Belgrave <beaub@linux.microsoft.com> */ -#ifndef _UAPI_LINUX_USER_EVENTS_H -#define _UAPI_LINUX_USER_EVENTS_H -#include <linux/types.h> -#include <linux/ioctl.h> +#ifndef _LINUX_USER_EVENTS_H +#define _LINUX_USER_EVENTS_H -#ifdef __KERNEL__ -#include <linux/uio.h> -#else -#include <sys/uio.h> -#endif +#include <linux/list.h> +#include <linux/refcount.h> +#include <linux/mm_types.h> +#include <linux/workqueue.h> +#include <uapi/linux/user_events.h> -#define USER_EVENTS_SYSTEM "user_events" -#define USER_EVENTS_PREFIX "u:" +#ifdef CONFIG_USER_EVENTS +struct user_event_mm { + struct list_head mms_link; + struct list_head enablers; + struct mm_struct *mm; + /* Used for one-shot lists, protected by event_mutex */ + struct user_event_mm *next; + refcount_t refcnt; + refcount_t tasks; + struct rcu_work put_rwork; +}; -/* Create dynamic location entry within a 32-bit value */ -#define DYN_LOC(offset, size) ((size) << 16 | (offset)) +extern void user_event_mm_dup(struct task_struct *t, + struct user_event_mm *old_mm); -/* - * Describes an event registration and stores the results of the registration. - * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum - * must set the size and name_args before invocation. - */ -struct user_reg { +extern void user_event_mm_remove(struct task_struct *t); + +static inline void user_events_fork(struct task_struct *t, + unsigned long clone_flags) +{ + struct user_event_mm *old_mm; - /* Input: Size of the user_reg structure being used */ - __u32 size; + if (!t || !current->user_event_mm) + return; - /* Input: Pointer to string with event name, description and flags */ - __u64 name_args; + old_mm = current->user_event_mm; - /* Output: Bitwise index of the event within the status page */ - __u32 status_bit; + if (clone_flags & CLONE_VM) { + t->user_event_mm = old_mm; + refcount_inc(&old_mm->tasks); + return; + } - /* Output: Index of the event to use when writing data */ - __u32 write_index; -} __attribute__((__packed__)); + user_event_mm_dup(t, old_mm); +} -#define DIAG_IOC_MAGIC '*' +static inline void user_events_execve(struct task_struct *t) +{ + if (!t || !t->user_event_mm) + return; + + user_event_mm_remove(t); +} + +static inline void user_events_exit(struct task_struct *t) +{ + if (!t || !t->user_event_mm) + return; + + user_event_mm_remove(t); +} +#else +static inline void user_events_fork(struct task_struct *t, + unsigned long clone_flags) +{ +} -/* Requests to register a user_event */ -#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) +static inline void user_events_execve(struct task_struct *t) +{ +} -/* Requests to delete a user_event */ -#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) +static inline void user_events_exit(struct task_struct *t) +{ +} +#endif /* CONFIG_USER_EVENTS */ -#endif /* _UAPI_LINUX_USER_EVENTS_H */ +#endif /* _LINUX_USER_EVENTS_H */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 3767f18114ef..d78b01524349 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -36,44 +36,57 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) -extern int sysctl_unprivileged_userfaultfd; - extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); -/* - * The mode of operation for __mcopy_atomic and its helpers. - * - * This is almost an implementation detail (mcopy_atomic below doesn't take this - * as a parameter), but it's exposed here because memory-kind-specific - * implementations (e.g. hugetlbfs) need to know the mode of operation. - */ -enum mcopy_atomic_mode { - /* A normal copy_from_user into the destination range. */ - MCOPY_ATOMIC_NORMAL, - /* Don't copy; map the destination range to the zero page. */ - MCOPY_ATOMIC_ZEROPAGE, - /* Just install pte(s) with the existing page(s) in the page cache. */ - MCOPY_ATOMIC_CONTINUE, +/* A combined operation mode + behavior flags. */ +typedef unsigned int __bitwise uffd_flags_t; + +/* Mutually exclusive modes of operation. */ +enum mfill_atomic_mode { + MFILL_ATOMIC_COPY, + MFILL_ATOMIC_ZEROPAGE, + MFILL_ATOMIC_CONTINUE, + NR_MFILL_ATOMIC_MODES, }; -extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +#define MFILL_ATOMIC_MODE_BITS (const_ilog2(NR_MFILL_ATOMIC_MODES - 1) + 1) +#define MFILL_ATOMIC_BIT(nr) BIT(MFILL_ATOMIC_MODE_BITS + (nr)) +#define MFILL_ATOMIC_FLAG(nr) ((__force uffd_flags_t) MFILL_ATOMIC_BIT(nr)) +#define MFILL_ATOMIC_MODE_MASK ((__force uffd_flags_t) (MFILL_ATOMIC_BIT(0) - 1)) + +static inline bool uffd_flags_mode_is(uffd_flags_t flags, enum mfill_atomic_mode expected) +{ + return (flags & MFILL_ATOMIC_MODE_MASK) == ((__force uffd_flags_t) expected); +} + +static inline uffd_flags_t uffd_flags_set_mode(uffd_flags_t flags, enum mfill_atomic_mode mode) +{ + flags &= ~MFILL_ATOMIC_MODE_MASK; + return flags | ((__force uffd_flags_t) mode); +} + +/* Flags controlling behavior. These behavior changes are mode-independent. */ +#define MFILL_ATOMIC_WP MFILL_ATOMIC_FLAG(0) + +extern int mfill_atomic_install_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, - bool newly_allocated, bool wp_copy); - -extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, __u64 mode); -extern ssize_t mfill_zeropage(struct mm_struct *dst_mm, - unsigned long dst_start, - unsigned long len, - atomic_t *mmap_changing); -extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long len, atomic_t *mmap_changing); + bool newly_allocated, uffd_flags_t flags); + +extern ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags); +extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, + unsigned long dst_start, + unsigned long len, + atomic_t *mmap_changing); +extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long len, atomic_t *mmap_changing, + uffd_flags_t flags); extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); -extern long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, +extern long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); /* mm helpers */ @@ -179,6 +192,7 @@ extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); +extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); #else /* CONFIG_USERFAULTFD */ @@ -274,8 +288,30 @@ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ +static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) +{ + /* Only wr-protect mode uses pte markers */ + if (!userfaultfd_wp(vma)) + return false; + + /* File-based uffd-wp always need markers */ + if (!vma_is_anonymous(vma)) + return true; + + /* + * Anonymous uffd-wp only needs the markers if WP_UNPOPULATED + * enabled (to apply markers on zero pages). + */ + return userfaultfd_wp_unpopulated(vma); +} + static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) { #ifdef CONFIG_PTE_MARKER_UFFD_WP diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 6b1a3efa1e0b..43d4a79b273d 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -107,7 +107,4 @@ extern const u8 uuid_index[16]; int guid_parse(const char *uuid, guid_t *u); int uuid_parse(const char *uuid, uuid_t *u); -/* MEI UUID type, don't use anywhere else */ -#include <uapi/linux/uuid.h> - #endif diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 43f59ef10cc9..db1b0eaef4eb 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -10,13 +10,19 @@ #include <linux/if_ether.h> /** - * struct vdpa_calllback - vDPA callback definition. + * struct vdpa_callback - vDPA callback definition. * @callback: interrupt callback function * @private: the data passed to the callback function + * @trigger: the eventfd for the callback (Optional). + * When it is set, the vDPA driver must guarantee that + * signaling it is functional equivalent to triggering + * the callback. Then vDPA parent can signal it directly + * instead of triggering the callback. */ struct vdpa_callback { irqreturn_t (*callback)(void *data); void *private; + struct eventfd_ctx *trigger; }; /** @@ -114,7 +120,7 @@ struct vdpa_dev_set_config { }; /** - * Corresponding file area for device memory mapping + * struct vdpa_map_file - file area for device memory mapping * @file: vma->vm_file for the mapping * @offset: mapping offset in the vm_file */ @@ -143,6 +149,14 @@ struct vdpa_map_file { * @kick_vq: Kick the virtqueue * @vdev: vdpa device * @idx: virtqueue index + * @kick_vq_with_data: Kick the virtqueue and supply extra data + * (only if VIRTIO_F_NOTIFICATION_DATA is negotiated) + * @vdev: vdpa device + * @data for split virtqueue: + * 16 bits vqn and 16 bits next available index. + * @data for packed virtqueue: + * 16 bits vqn, 15 least significant bits of + * next available index and 1 bit next_wrap. * @set_vq_cb: Set the interrupt callback function for * a virtqueue * @vdev: vdpa device @@ -165,10 +179,16 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) + * @get_vendor_vq_stats: Get the vendor statistics of a device. + * @vdev: vdpa device + * @idx: virtqueue index + * @msg: socket buffer holding stats message + * @extack: extack for reporting error messages + * Returns integer: success (0) or error (< 0) * @get_vq_notification: Get the notification area for a virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index - * Returns the notifcation area + * Returns the notification area * @get_vq_irq: Get the irq number of a virtqueue (optional, * but must implemented if require vq irq offloading) * @vdev: vdpa device @@ -250,6 +270,15 @@ struct vdpa_map_file { * @vdev: vdpa device * Returns the iova range supported by * the device. + * @set_vq_affinity: Set the affinity of virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * @cpu_mask: the affinity mask + * Returns integer: success (0) or error (< 0) + * @get_vq_affinity: Get the affinity of virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * Returns the affinity mask * @set_group_asid: Set address space identifier for a * virtqueue group (optional) * @vdev: vdpa device @@ -290,6 +319,14 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * Returns pointer to structure device or error (NULL) + * @bind_mm: Bind the device to a specific address space + * so the vDPA framework can use VA when this + * callback is implemented. (optional) + * @vdev: vdpa device + * @mm: address space to bind + * @unbind_mm: Unbind the device from the address space + * bound using the bind_mm callback. (optional) + * @vdev: vdpa device * @free: Free resources that belongs to vDPA (optional) * @vdev: vdpa device */ @@ -300,6 +337,7 @@ struct vdpa_config_ops { u64 device_area); void (*set_vq_num)(struct vdpa_device *vdev, u16 idx, u32 num); void (*kick_vq)(struct vdpa_device *vdev, u16 idx); + void (*kick_vq_with_data)(struct vdpa_device *vdev, u32 data); void (*set_vq_cb)(struct vdpa_device *vdev, u16 idx, struct vdpa_callback *cb); void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready); @@ -340,6 +378,10 @@ struct vdpa_config_ops { const void *buf, unsigned int len); u32 (*get_generation)(struct vdpa_device *vdev); struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); + int (*set_vq_affinity)(struct vdpa_device *vdev, u16 idx, + const struct cpumask *cpu_mask); + const struct cpumask *(*get_vq_affinity)(struct vdpa_device *vdev, + u16 idx); /* DMA ops */ int (*set_map)(struct vdpa_device *vdev, unsigned int asid, @@ -351,6 +393,8 @@ struct vdpa_config_ops { int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group, unsigned int asid); struct device *(*get_vq_dma_dev)(struct vdpa_device *vdev, u16 idx); + int (*bind_mm)(struct vdpa_device *vdev, struct mm_struct *mm); + void (*unbind_mm)(struct vdpa_device *vdev); /* Free device resources */ void (*free)(struct vdpa_device *vdev); @@ -506,6 +550,8 @@ struct vdpa_mgmtdev_ops { * @config_attr_mask: bit mask of attributes of type enum vdpa_attr that * management device support during dev_add callback * @list: list entry + * @supported_features: features supported by device + * @max_supported_vqs: maximum number of virtqueues supported by device */ struct vdpa_mgmt_dev { struct device *device; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 93134b023968..2c137ea94a3e 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -60,7 +60,6 @@ struct vfio_device { void (*put_kvm)(struct kvm *kvm); #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_device *iommufd_device; - struct iommufd_ctx *iommufd_ictx; bool iommufd_attached; #endif }; @@ -68,6 +67,7 @@ struct vfio_device { /** * struct vfio_device_ops - VFIO bus driver device callbacks * + * @name: Name of the device driver. * @init: initialize private fields in device structure * @release: Reclaim private fields in device structure * @bind_iommufd: Called when binding the device to an iommufd @@ -140,6 +140,8 @@ int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id); #endif /** + * struct vfio_migration_ops - VFIO bus device driver migration callbacks + * * @migration_set_state: Optional callback to change the migration state for * devices that support migration. It's mandatory for * VFIO_DEVICE_FEATURE_MIGRATION migration support. @@ -165,6 +167,8 @@ struct vfio_migration_ops { }; /** + * struct vfio_log_ops - VFIO bus device driver logging callbacks + * * @log_start: Optional callback to ask the device start DMA logging. * @log_stop: Optional callback to ask the device stop DMA logging. * @log_read_and_clear: Optional callback to ask the device read diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 2b472514c49b..b93238db94e3 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -34,8 +34,8 @@ struct virtqueue { unsigned int index; unsigned int num_free; unsigned int num_max; - void *priv; bool reset; + void *priv; }; int virtqueue_add_outbuf(struct virtqueue *vq, @@ -84,14 +84,14 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *vq); void *virtqueue_detach_unused_buf(struct virtqueue *vq); -unsigned int virtqueue_get_vring_size(struct virtqueue *vq); +unsigned int virtqueue_get_vring_size(const struct virtqueue *vq); -bool virtqueue_is_broken(struct virtqueue *vq); +bool virtqueue_is_broken(const struct virtqueue *vq); -const struct vring *virtqueue_get_vring(struct virtqueue *vq); -dma_addr_t virtqueue_get_desc_addr(struct virtqueue *vq); -dma_addr_t virtqueue_get_avail_addr(struct virtqueue *vq); -dma_addr_t virtqueue_get_used_addr(struct virtqueue *vq); +const struct vring *virtqueue_get_vring(const struct virtqueue *vq); +dma_addr_t virtqueue_get_desc_addr(const struct virtqueue *vq); +dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *vq); +dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq); int virtqueue_resize(struct virtqueue *vq, u32 num, void (*recycle)(struct virtqueue *vq, void *buf)); @@ -147,7 +147,7 @@ int virtio_device_restore(struct virtio_device *dev); #endif void virtio_reset_device(struct virtio_device *dev); -size_t virtio_max_dma_size(struct virtio_device *vdev); +size_t virtio_max_dma_size(const struct virtio_device *vdev); #define virtio_device_for_each_vq(vdev, vq) \ list_for_each_entry(vq, &vdev->vqs, list) diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 8b95b69ef694..9b33df741b63 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -58,6 +58,7 @@ do { \ struct virtio_device; struct virtqueue; +struct device; /* * Creates a virtqueue and allocates the descriptor ring. If @@ -117,4 +118,6 @@ void vring_del_virtqueue(struct virtqueue *vq); void vring_transport_features(struct virtio_device *vdev); irqreturn_t vring_interrupt(int irq, void *_vq); + +u32 vring_notification_data(struct virtqueue *_vq); #endif /* _LINUX_VIRTIO_RING_H */ diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 3f9c16611306..c58453699ee9 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -245,4 +245,5 @@ u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit); void virtio_transport_deliver_tap_pkt(struct sk_buff *skb); int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list); +int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor); #endif /* _LINUX_VIRTIO_VSOCK_H */ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 7f5d1caf5890..8abfa1240040 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -150,6 +150,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, DIRECT_MAP_LEVEL2_SPLIT, DIRECT_MAP_LEVEL3_SPLIT, #endif +#ifdef CONFIG_PER_VMA_LOCK_STATS + VMA_LOCK_SUCCESS, + VMA_LOCK_ABORT, + VMA_LOCK_RETRY, + VMA_LOCK_MISS, +#endif NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 69250efa03d1..c720be70c8dd 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -14,6 +14,7 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ +struct iov_iter; /* in uio.h */ /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ @@ -131,12 +132,8 @@ extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); #ifdef CONFIG_MMU -extern void __init vmalloc_init(void); extern unsigned long vmalloc_nr_pages(void); #else -static inline void vmalloc_init(void) -{ -} static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif @@ -251,7 +248,7 @@ static inline void set_vm_flush_reset_perms(void *addr) #endif /* for /proc/kcore */ -extern long vread(char *buf, char *addr, unsigned long count); +extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count); /* * Internals. Don't use.. diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 19cf5b6892ce..fed855bae6d8 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -125,6 +125,12 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif +#ifdef CONFIG_PER_VMA_LOCK_STATS +#define count_vm_vma_lock_event(x) count_vm_event(x) +#else +#define count_vm_vma_lock_event(x) do {} while (0) +#endif + #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 1991a02c6431..c3a8117dabe8 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -32,6 +32,9 @@ struct vringh { /* Can we get away with weak barriers? */ bool weak_barriers; + /* Use user's VA */ + bool use_va; + /* Last available index we saw (ie. where we're up to). */ u16 last_avail_idx; @@ -54,6 +57,9 @@ struct vringh { void (*notify)(struct vringh *); }; +struct virtio_device; +typedef void vrh_callback_t(struct virtio_device *, struct vringh *); + /** * struct vringh_config_ops - ops for creating a host vring from a virtio driver * @find_vrhs: find the host vrings and instantiate them @@ -65,8 +71,6 @@ struct vringh { * Returns 0 on success or error status * @del_vrhs: free the host vrings found by find_vrhs(). */ -struct virtio_device; -typedef void vrh_callback_t(struct virtio_device *, struct vringh *); struct vringh_config_ops { int (*find_vrhs)(struct virtio_device *vdev, unsigned nhvrs, struct vringh *vrhs[], vrh_callback_t *callbacks[]); @@ -81,6 +85,12 @@ struct vringh_range { /** * struct vringh_iov - iovec mangler. + * @iov: array of iovecs to operate on + * @consumed: number of bytes consumed within iov[i] + * @i: index of current iovec + * @used: number of iovecs present in @iov + * @max_num: maximum number of iovecs. + * corresponds to allocated memory of @iov * * Mangles iovec in place, and restores it. * Remaining data is iov + i, of used - i elements. @@ -93,6 +103,12 @@ struct vringh_iov { /** * struct vringh_kiov - kvec mangler. + * @iov: array of iovecs to operate on + * @consumed: number of bytes consumed within iov[i] + * @i: index of current iovec + * @used: number of iovecs present in @iov + * @max_num: maximum number of iovecs. + * corresponds to allocated memory of @iov * * Mangles kvec in place, and restores it. * Remaining data is iov + i, of used - i elements. @@ -284,6 +300,12 @@ int vringh_init_iotlb(struct vringh *vrh, u64 features, struct vring_avail *avail, struct vring_used *used); +int vringh_init_iotlb_va(struct vringh *vrh, u64 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used); + int vringh_getdesc_iotlb(struct vringh *vrh, struct vringh_kiov *riov, struct vringh_kiov *wiov, diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h index 848db1b1569f..919d999a8c1d 100644 --- a/include/linux/vt_buffer.h +++ b/include/linux/vt_buffer.h @@ -16,7 +16,7 @@ #include <linux/string.h> -#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_MDA_CONSOLE) +#if IS_ENABLED(CONFIG_VGA_CONSOLE) || IS_ENABLED(CONFIG_MDA_CONSOLE) #include <asm/vga.h> #endif diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ac551b8ee7d9..683efe29fa69 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -68,7 +68,6 @@ enum { WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, - WORK_OFFQ_CANCELING = (1 << __WORK_OFFQ_CANCELING), /* * When a work item is off queue, its high bits point to the last @@ -79,12 +78,6 @@ enum { WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, - WORK_OFFQ_POOL_NONE = (1LU << WORK_OFFQ_POOL_BITS) - 1, - - /* convenience constants */ - WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, - WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, - WORK_STRUCT_NO_POOL = (unsigned long)WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, @@ -94,6 +87,14 @@ enum { WORKER_DESC_LEN = 24, }; +/* Convenience constants - of type 'unsigned long', not 'enum'! */ +#define WORK_OFFQ_CANCELING (1ul << __WORK_OFFQ_CANCELING) +#define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) +#define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) + +#define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) +#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) + struct work_struct { atomic_long_t data; struct list_head entry; @@ -472,6 +473,7 @@ extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_all_workqueues(void); +extern void show_freezable_workqueues(void); extern void show_one_workqueue(struct workqueue_struct *wq); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 46020373e155..fba937999fbf 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -70,8 +70,6 @@ struct writeback_control { */ unsigned no_cgroup_owner:1; - unsigned punt_to_cgroup:1; /* cgrp punting, see __REQ_CGROUP_PUNT */ - /* To enable batching of swap writes to non-block-device backends, * "plug" can be set point to a 'struct swap_iocb *'. When all swap * writes have been submitted, if with swap_iocb is not NULL, @@ -97,9 +95,6 @@ static inline blk_opf_t wbc_to_write_flags(struct writeback_control *wbc) { blk_opf_t flags = 0; - if (wbc->punt_to_cgroup) - flags = REQ_CGROUP_PUNT; - if (wbc->sync_mode == WB_SYNC_ALL) flags |= REQ_SYNC; else if (wbc->for_kupdate || wbc->for_background) diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 24d76500b1cc..01fa15506286 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -64,11 +64,21 @@ struct wwan_port_ops { poll_table *wait); }; +/** struct wwan_port_caps - The WWAN port capbilities + * @frag_len: WWAN port TX fragments length + * @headroom_len: WWAN port TX fragments reserved headroom length + */ +struct wwan_port_caps { + size_t frag_len; + unsigned int headroom_len; +}; + /** * wwan_create_port - Add a new WWAN port * @parent: Device to use as parent and shared by all WWAN ports * @type: WWAN port type * @ops: WWAN port operations + * @caps: WWAN port capabilities * @drvdata: Pointer to caller driver data * * Allocate and register a new WWAN port. The port will be automatically exposed @@ -86,6 +96,7 @@ struct wwan_port_ops { struct wwan_port *wwan_create_port(struct device *parent, enum wwan_port_type type, const struct wwan_port_ops *ops, + struct wwan_port_caps *caps, void *drvdata); /** diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 6af72461397d..d591ef59aa98 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -47,6 +47,22 @@ struct xattr_handler { size_t size, int flags); }; +/** + * xattr_handler_can_list - check whether xattr can be listed + * @handler: handler for this type of xattr + * @dentry: dentry whose inode xattr to list + * + * Determine whether the xattr associated with @dentry can be listed given + * @handler. + * + * Return: true if xattr can be listed, false if not. + */ +static inline bool xattr_handler_can_list(const struct xattr_handler *handler, + struct dentry *dentry) +{ + return handler && (!handler->list || handler->list(dentry)); +} + const char *xattr_full_name(const struct xattr_handler *, const char *); struct xattr { @@ -78,7 +94,7 @@ int vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); -int xattr_supported_namespace(struct inode *inode, const char *prefix); +int xattr_supports_user_prefix(struct inode *inode); static inline const char *xattr_prefix(const struct xattr_handler *handler) { @@ -109,5 +125,6 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); +int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name); #endif /* _LINUX_XATTR_H */ |