diff options
Diffstat (limited to 'include/linux')
347 files changed, 7033 insertions, 3323 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index b7165e52b3c6..28c3fb2bef0d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -242,9 +242,6 @@ static inline bool acpi_gicc_is_usable(struct acpi_madt_generic_interrupt *gicc) return gicc->flags & ACPI_MADT_ENABLED; } -/* the following numa functions are architecture-dependent */ -void acpi_numa_slit_init (struct acpi_table_slit *slit); - #if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else @@ -267,8 +264,6 @@ static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } #endif -int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); - #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1) @@ -421,7 +416,7 @@ extern char *wmi_get_acpi_device_uid(const char *guid); extern char acpi_video_backlight_string[]; extern long acpi_is_video_device(acpi_handle handle); -extern int acpi_blacklisted(void); + extern void acpi_osi_setup(char *str); extern bool acpi_osi_is_win8(void); @@ -573,9 +568,13 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_CPCV2_SUPPORT 0x00000040 #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 +#define OSC_SB_FAST_THERMAL_SAMPLING_SUPPORT 0x00000200 +#define OSC_SB_OVER_16_PSTATES_SUPPORT 0x00000400 +#define OSC_SB_GED_SUPPORT 0x00000800 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 -#define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_IRQ_RESOURCE_SOURCE_SUPPORT 0x00002000 #define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 +#define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00020000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_PRM_SUPPORT 0x00200000 #define OSC_SB_FFH_OPR_SUPPORT 0x00400000 @@ -1170,6 +1169,7 @@ static inline void acpi_ec_set_gpe_wake_mask(u8 action) {} #endif #ifdef CONFIG_ACPI +char *acpi_handle_path(acpi_handle handle); __printf(3, 4) void acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...); @@ -1232,7 +1232,7 @@ bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); -int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, int index, +int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, @@ -1245,7 +1245,7 @@ static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, { return false; } -static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, +static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable) { return -ENXIO; @@ -1258,10 +1258,10 @@ static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable); } -static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, +static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *con_id, int index) { - return acpi_dev_gpio_irq_wake_get_by(adev, name, index, NULL); + return acpi_dev_gpio_irq_wake_get_by(adev, con_id, index, NULL); } static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) @@ -1547,4 +1547,25 @@ static inline void acpi_use_parent_companion(struct device *dev) ACPI_COMPANION_SET(dev, ACPI_COMPANION(dev->parent)); } +#ifdef CONFIG_ACPI_HMAT +int hmat_update_target_coordinates(int nid, struct access_coordinate *coord, + enum access_coordinate_class access); +#else +static inline int hmat_update_target_coordinates(int nid, + struct access_coordinate *coord, + enum access_coordinate_class access) +{ + return -EOPNOTSUPP; +} +#endif + +#ifdef CONFIG_ACPI_NUMA +bool acpi_node_backed_by_real_pxm(int nid); +#else +static inline bool acpi_node_backed_by_real_pxm(int nid) +{ + return false; +} +#endif + #endif /*_LINUX_ACPI_H*/ diff --git a/include/linux/aer.h b/include/linux/aer.h index ae0fae70d4bd..4b97f38f3fcf 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -18,11 +18,8 @@ struct pci_dev; -struct aer_header_log_regs { - u32 dw0; - u32 dw1; - u32 dw2; - u32 dw3; +struct pcie_tlp_log { + u32 dw[4]; }; struct aer_capability_regs { @@ -33,13 +30,15 @@ struct aer_capability_regs { u32 cor_status; u32 cor_mask; u32 cap_control; - struct aer_header_log_regs header_log; + struct pcie_tlp_log header_log; u32 root_command; u32 root_status; u16 cor_err_source; u16 uncor_err_source; }; +int pcie_read_tlp_log(struct pci_dev *dev, int where, struct pcie_tlp_log *log); + #if defined(CONFIG_PCIEAER) int pci_aer_clear_nonfatal_status(struct pci_dev *dev); int pcie_aer_is_native(struct pci_dev *dev); diff --git a/include/linux/amba/pl022.h b/include/linux/amba/pl022.h index 9bf58aac0df2..d7b07d0311e1 100644 --- a/include/linux/amba/pl022.h +++ b/include/linux/amba/pl022.h @@ -16,6 +16,7 @@ #ifndef _SSP_PL022_H #define _SSP_PL022_H +#include <linux/dmaengine.h> #include <linux/types.h> /** @@ -224,6 +225,7 @@ struct dma_chan; * struct pl022_ssp_master - device.platform_data for SPI controller devices. * @bus_id: identifier for this bus * @enable_dma: if true enables DMA driven transfers. + * @dma_filter: callback filter for dma_request_channel. * @dma_rx_param: parameter to locate an RX DMA channel. * @dma_tx_param: parameter to locate a TX DMA channel. * @autosuspend_delay: delay in ms following transfer completion before the @@ -235,7 +237,7 @@ struct dma_chan; struct pl022_ssp_controller { u16 bus_id; u8 enable_dma:1; - bool (*dma_filter)(struct dma_chan *chan, void *filter_param); + dma_filter_fn dma_filter; void *dma_rx_param; void *dma_tx_param; int autosuspend_delay; diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index 6ad02ad9c7b4..d58fc022ec46 100644 --- a/include/linux/amd-pstate.h +++ b/include/linux/amd-pstate.h @@ -39,19 +39,31 @@ struct amd_aperf_mperf { * @cppc_req_cached: cached performance request hints * @highest_perf: the maximum performance an individual processor may reach, * assuming ideal conditions + * For platforms that do not support the preferred core feature, the + * highest_pef may be configured with 166 or 255, to avoid max frequency + * calculated wrongly. we take the fixed value as the highest_perf. * @nominal_perf: the maximum sustained performance level of the processor, * assuming ideal operating conditions * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power * savings are achieved * @lowest_perf: the absolute lowest performance level of the processor - * @max_freq: the frequency that mapped to highest_perf - * @min_freq: the frequency that mapped to lowest_perf - * @nominal_freq: the frequency that mapped to nominal_perf - * @lowest_nonlinear_freq: the frequency that mapped to lowest_nonlinear_perf + * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher + * priority. + * @min_limit_perf: Cached value of the performance corresponding to policy->min + * @max_limit_perf: Cached value of the performance corresponding to policy->max + * @min_limit_freq: Cached value of policy->min (in khz) + * @max_limit_freq: Cached value of policy->max (in khz) + * @max_freq: the frequency (in khz) that mapped to highest_perf + * @min_freq: the frequency (in khz) that mapped to lowest_perf + * @nominal_freq: the frequency (in khz) that mapped to nominal_perf + * @lowest_nonlinear_freq: the frequency (in khz) that mapped to lowest_nonlinear_perf * @cur: Difference of Aperf/Mperf/tsc count between last and current sample * @prev: Last Aperf/Mperf/tsc count value read from register - * @freq: current cpu frequency value + * @freq: current cpu frequency value (in khz) * @boost_supported: check whether the Processor or SBIOS supports boost mode + * @hw_prefcore: check whether HW supports preferred core featue. + * Only when hw_prefcore and early prefcore param are true, + * AMD P-State driver supports preferred core featue. * @epp_policy: Last saved policy used to set energy-performance preference * @epp_cached: Cached CPPC energy-performance preference value * @policy: Cpufreq policy value @@ -70,6 +82,7 @@ struct amd_cpudata { u32 nominal_perf; u32 lowest_nonlinear_perf; u32 lowest_perf; + u32 prefcore_ranking; u32 min_limit_perf; u32 max_limit_perf; u32 min_limit_freq; @@ -85,6 +98,7 @@ struct amd_cpudata { u64 freq; bool boost_supported; + bool hw_prefcore; /* EPP feature related attributes*/ s16 epp_policy; @@ -114,4 +128,10 @@ static const char * const amd_pstate_mode_string[] = { [AMD_PSTATE_GUIDED] = "guided", NULL, }; + +struct quirk_entry { + u32 nominal_freq; + u32 lowest_freq; +}; + #endif /* _LINUX_AMD_PSTATE_H */ diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 93a5f16d03f3..edef565c2a1a 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -9,12 +9,17 @@ #ifndef _LINUX_ANON_INODES_H #define _LINUX_ANON_INODES_H +#include <linux/types.h> + struct file_operations; struct inode; struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); +struct file *anon_inode_getfile_fmode(const char *name, + const struct file_operations *fops, + void *priv, int flags, fmode_t f_mode); struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index a63d61ca55af..b721f360d759 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -60,14 +60,14 @@ void topology_scale_freq_tick(void); void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus); void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus); -DECLARE_PER_CPU(unsigned long, thermal_pressure); +DECLARE_PER_CPU(unsigned long, hw_pressure); -static inline unsigned long topology_get_thermal_pressure(int cpu) +static inline unsigned long topology_get_hw_pressure(int cpu) { - return per_cpu(thermal_pressure, cpu); + return per_cpu(hw_pressure, cpu); } -void topology_update_thermal_pressure(const struct cpumask *cpus, +void topology_update_hw_pressure(const struct cpumask *cpus, unsigned long capped_freq); struct cpu_topology { diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index c906f666ff5d..c82d56768101 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -126,6 +126,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { u32 id; + u32 properties; int vm_id; bool mode_32bit; uuid_t uuid; @@ -221,12 +222,29 @@ struct ffa_partition_info { #define FFA_PARTITION_DIRECT_SEND BIT(1) /* partition can send and receive indirect messages. */ #define FFA_PARTITION_INDIRECT_MSG BIT(2) +/* partition can receive notifications */ +#define FFA_PARTITION_NOTIFICATION_RECV BIT(3) /* partition runs in the AArch64 execution state. */ #define FFA_PARTITION_AARCH64_EXEC BIT(8) u32 properties; u32 uuid[4]; }; +static inline +bool ffa_partition_check_property(struct ffa_device *dev, u32 property) +{ + return dev->properties & property; +} + +#define ffa_partition_supports_notify_recv(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_NOTIFICATION_RECV) + +#define ffa_partition_supports_indirect_msg(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_INDIRECT_MSG) + +#define ffa_partition_supports_direct_recv(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_DIRECT_RECV) + /* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP} which pass data via registers */ struct ffa_send_direct_data { unsigned long data0; /* w3/x3 */ @@ -236,6 +254,14 @@ struct ffa_send_direct_data { unsigned long data4; /* w7/x7 */ }; +struct ffa_indirect_msg_hdr { + u32 flags; + u32 res0; + u32 offset; + u32 send_recv_id; + u32 size; +}; + struct ffa_mem_region_addr_range { /* The base IPA of the constituent memory region, aligned to 4 kiB */ u64 address; @@ -396,6 +422,7 @@ struct ffa_msg_ops { void (*mode_32bit_set)(struct ffa_device *dev); int (*sync_send_receive)(struct ffa_device *dev, struct ffa_send_direct_data *data); + int (*indirect_send)(struct ffa_device *dev, void *buf, size_t sz); }; struct ffa_mem_ops { diff --git a/include/linux/bio.h b/include/linux/bio.h index 875d792bffff..d5379548d684 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -615,6 +615,13 @@ static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) bl->tail = bl2->tail; } +static inline void bio_list_merge_init(struct bio_list *bl, + struct bio_list *bl2) +{ + bio_list_merge(bl, bl2); + bio_list_init(bl2); +} + static inline void bio_list_merge_head(struct bio_list *bl, struct bio_list *bl2) { @@ -824,5 +831,9 @@ static inline void bio_clear_polled(struct bio *bio) struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, blk_opf_t opf, gfp_t gfp); +struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new); + +struct bio *blk_alloc_discard_bio(struct block_device *bdev, + sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask); #endif /* __LINUX_BIO_H */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index fb3a9c93ac86..8c4768c44a01 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -83,6 +83,10 @@ struct device; * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start + * bitmap_read(map, start, nbits) Read an nbits-sized value from + * map at start + * bitmap_write(map, value, start, nbits) Write an nbits-sized value to + * map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long @@ -222,9 +226,11 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = 0; @@ -234,7 +240,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = ~0UL; @@ -245,7 +251,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = *src; @@ -522,17 +528,18 @@ static inline void bitmap_replace(unsigned long *dst, * * (Bits 0, 1, 2, 3, 4, 5 are copied to the bits 0, 1, 4, 8, 9, 12) * - * A more 'visual' description of the operation: - * src: 0000000001011010 - * |||||| - * +------+||||| - * | +----+|||| - * | |+----+||| - * | || +-+|| - * | || | || - * mask: ...v..vv...v..vv - * ...0..11...0..10 - * dst: 0000001100000010 + * A more 'visual' description of the operation:: + * + * src: 0000000001011010 + * |||||| + * +------+||||| + * | +----+|||| + * | |+----+||| + * | || +-+|| + * | || | || + * mask: ...v..vv...v..vv + * ...0..11...0..10 + * dst: 0000001100000010 * * A relationship exists between bitmap_scatter() and bitmap_gather(). * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation. @@ -568,16 +575,17 @@ static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, * * (Bits 0, 1, 4, 8, 9, 12 are copied to the bits 0, 1, 2, 3, 4, 5) * - * A more 'visual' description of the operation: - * mask: ...v..vv...v..vv - * src: 0000001100000010 - * ^ ^^ ^ 0 - * | || | 10 - * | || > 010 - * | |+--> 1010 - * | +--> 11010 - * +----> 011010 - * dst: 0000000000011010 + * A more 'visual' description of the operation:: + * + * mask: ...v..vv...v..vv + * src: 0000001100000010 + * ^ ^^ ^ 0 + * | || | 10 + * | || > 010 + * | |+--> 1010 + * | +--> 11010 + * +----> 011010 + * dst: 0000000000011010 * * A relationship exists between bitmap_gather() and bitmap_scatter(). See * bitmap_scatter() for the bitmap scatter detailed operations. @@ -720,38 +728,83 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) } /** - * bitmap_get_value8 - get an 8-bit value within a memory region + * bitmap_read - read a value of n-bits from the memory region * @map: address to the bitmap memory region - * @start: bit offset of the 8-bit value; must be a multiple of 8 + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG * - * Returns the 8-bit value located at the @start bit offset within the @src - * memory region. + * Returns: value of @nbits bits located at the @start bit offset within the + * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return + * value is undefined. */ -static inline unsigned long bitmap_get_value8(const unsigned long *map, - unsigned long start) +static inline unsigned long bitmap_read(const unsigned long *map, + unsigned long start, + unsigned long nbits) { - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; + size_t index = BIT_WORD(start); + unsigned long offset = start % BITS_PER_LONG; + unsigned long space = BITS_PER_LONG - offset; + unsigned long value_low, value_high; - return (map[index] >> offset) & 0xFF; + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return 0; + + if (space >= nbits) + return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits); + + value_low = map[index] & BITMAP_FIRST_WORD_MASK(start); + value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits); + return (value_low >> offset) | (value_high << space); } /** - * bitmap_set_value8 - set an 8-bit value within a memory region + * bitmap_write - write n-bit value within a memory region * @map: address to the bitmap memory region - * @value: the 8-bit value; values wider than 8 bits may clobber bitmap - * @start: bit offset of the 8-bit value; must be a multiple of 8 + * @value: value to write, clamped to nbits + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG. + * + * bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(), + * i.e. bits beyond @nbits are ignored: + * + * for (bit = 0; bit < nbits; bit++) + * __assign_bit(start + bit, bitmap, val & BIT(bit)); + * + * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed. */ -static inline void bitmap_set_value8(unsigned long *map, unsigned long value, - unsigned long start) -{ - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; - - map[index] &= ~(0xFFUL << offset); +static inline void bitmap_write(unsigned long *map, unsigned long value, + unsigned long start, unsigned long nbits) +{ + size_t index; + unsigned long offset; + unsigned long space; + unsigned long mask; + bool fit; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return; + + mask = BITMAP_LAST_WORD_MASK(nbits); + value &= mask; + offset = start % BITS_PER_LONG; + space = BITS_PER_LONG - offset; + fit = space >= nbits; + index = BIT_WORD(start); + + map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start)); map[index] |= value << offset; + if (fit) + return; + + map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits); + map[index + 1] |= (value >> space); } +#define bitmap_get_value8(map, start) \ + bitmap_read(map, start, BITS_PER_BYTE) +#define bitmap_set_value8(map, value, start) \ + bitmap_write(map, value, start, BITS_PER_BYTE) + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 2ba557e067fe..b25dc8742124 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -21,6 +21,8 @@ #define BITS_TO_U32(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) + extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); @@ -80,6 +82,7 @@ __check_bitop_pr(__test_and_set_bit); __check_bitop_pr(__test_and_clear_bit); __check_bitop_pr(__test_and_change_bit); __check_bitop_pr(test_bit); +__check_bitop_pr(test_bit_acquire); #undef __check_bitop_pr @@ -272,23 +275,11 @@ static inline unsigned long fns(unsigned long word, unsigned int n) * @addr: the address to start counting from * @value: the value to assign */ -static __always_inline void assign_bit(long nr, volatile unsigned long *addr, - bool value) -{ - if (value) - set_bit(nr, addr); - else - clear_bit(nr, addr); -} +#define assign_bit(nr, addr, value) \ + ((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr))) -static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, - bool value) -{ - if (value) - __set_bit(nr, addr); - else - __clear_bit(nr, addr); -} +#define __assign_bit(nr, addr, value) \ + ((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr))) /** * __ptr_set_bit - Set bit in a pointer's value diff --git a/include/linux/bits.h b/include/linux/bits.h index 7c0cf5031abe..0eb24d21aac2 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -4,6 +4,7 @@ #include <linux/const.h> #include <vdso/bits.h> +#include <uapi/linux/bits.h> #include <asm/bitsperlong.h> #define BIT_MASK(nr) (UL(1) << ((nr) % BITS_PER_LONG)) @@ -30,15 +31,8 @@ #define GENMASK_INPUT_CHECK(h, l) 0 #endif -#define __GENMASK(h, l) \ - (((~UL(0)) - (UL(1) << (l)) + 1) & \ - (~UL(0) >> (BITS_PER_LONG - 1 - (h)))) #define GENMASK(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l)) - -#define __GENMASK_ULL(h, l) \ - (((~ULL(0)) - (ULL(1) << (l)) + 1) & \ - (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) #define GENMASK_ULL(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d3d8fd8e229b..89ba6b16fe8b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -54,8 +54,8 @@ typedef __u32 __bitwise req_flags_t; /* Look at ->special_vec for the actual data payload instead of the bio chain. */ #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)) +/* The request completion needs to be signaled to zone write pluging. */ +#define RQF_ZONE_WRITE_PLUGGING ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) #define RQF_RESV ((__force req_flags_t)(1 << 23)) @@ -1150,85 +1150,4 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, } void blk_dump_rq_flags(struct request *, char *); -#ifdef CONFIG_BLK_DEV_ZONED -static inline unsigned int blk_rq_zone_no(struct request *rq) -{ - return disk_zone_no(rq->q->disk, blk_rq_pos(rq)); -} - -static inline unsigned int blk_rq_zone_is_seq(struct request *rq) -{ - return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq)); -} - -/** - * blk_rq_is_seq_zoned_write() - Check if @rq requires write serialization. - * @rq: Request to examine. - * - * Note: REQ_OP_ZONE_APPEND requests do not require serialization. - */ -static inline bool blk_rq_is_seq_zoned_write(struct request *rq) -{ - return op_needs_zoned_write_locking(req_op(rq)) && - blk_rq_zone_is_seq(rq); -} - -bool blk_req_needs_zone_write_lock(struct request *rq); -bool blk_req_zone_write_trylock(struct request *rq); -void __blk_req_zone_write_lock(struct request *rq); -void __blk_req_zone_write_unlock(struct request *rq); - -static inline void blk_req_zone_write_lock(struct request *rq) -{ - if (blk_req_needs_zone_write_lock(rq)) - __blk_req_zone_write_lock(rq); -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ - if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) - __blk_req_zone_write_unlock(rq); -} - -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return rq->q->disk->seq_zones_wlock && - test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock); -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - if (!blk_req_needs_zone_write_lock(rq)) - return true; - return !blk_req_zone_is_write_locked(rq); -} -#else /* CONFIG_BLK_DEV_ZONED */ -static inline bool blk_rq_is_seq_zoned_write(struct request *rq) -{ - return false; -} - -static inline bool blk_req_needs_zone_write_lock(struct request *rq) -{ - return false; -} - -static inline void blk_req_zone_write_lock(struct request *rq) -{ -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ -} -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return false; -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - return true; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - #endif /* BLK_MQ_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cb1526ec44b5..25dbf1097085 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -88,15 +88,9 @@ struct block_device { /* * Block error status values. See block/blk-core:blk_errors for the details. - * Alpha cannot write a byte atomically, so we need to use 32-bit value. */ -#if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__) -typedef u32 __bitwise blk_status_t; -typedef u32 blk_short_t; -#else typedef u8 __bitwise blk_status_t; typedef u16 blk_short_t; -#endif #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) #define BLK_STS_TIMEOUT ((__force blk_status_t)2) @@ -137,25 +131,13 @@ typedef u16 blk_short_t; #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) /* - * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone - * related resources are unavailable, but the driver can guarantee the queue - * will be rerun in the future once the resources become available again. - * - * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references - * a zone specific resource and IO to a different zone on the same device could - * still be served. Examples of that are zones that are write-locked, but a read - * to the same zone could be served. - */ -#define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14) - -/* * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently open. The same command should be successful if resubmitted * after the number of open zones decreases below the device's limits, which is * reported in the request_queue's max_open_zones. */ -#define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)15) +#define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)14) /* * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion @@ -164,20 +146,20 @@ typedef u16 blk_short_t; * after the number of active zones decreases below the device's limits, which * is reported in the request_queue's max_active_zones. */ -#define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) +#define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)15) /* * BLK_STS_OFFLINE is returned from the driver when the target device is offline * or is being taken offline. This could help differentiate the case where a * device is intentionally being shut down from a real I/O error. */ -#define BLK_STS_OFFLINE ((__force blk_status_t)17) +#define BLK_STS_OFFLINE ((__force blk_status_t)16) /* * BLK_STS_DURATION_LIMIT is returned from the driver when the target device * aborted the command because it exceeded one of its Command Duration Limits. */ -#define BLK_STS_DURATION_LIMIT ((__force blk_status_t)18) +#define BLK_STS_DURATION_LIMIT ((__force blk_status_t)17) /** * blk_path_error - returns true if error may be path related @@ -234,7 +216,12 @@ struct bio { struct bvec_iter bi_iter; - blk_qc_t bi_cookie; + union { + /* for polled bios: */ + blk_qc_t bi_cookie; + /* for plugged zoned writes only: */ + unsigned int __bi_nr_segments; + }; bio_end_io_t *bi_end_io; void *bi_private; #ifdef CONFIG_BLK_CGROUP @@ -304,7 +291,8 @@ enum { BIO_QOS_THROTTLED, /* bio went through rq_qos throttle path */ BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, - BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ + BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */ + BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */ BIO_FLAG_LAST }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f9b87c39cab0..fd5951dd6b7d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -128,6 +128,8 @@ typedef unsigned int __bitwise blk_mode_t; #define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) /* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */ #define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5)) +/* return partition scanning errors */ +#define BLK_OPEN_STRICT_SCAN ((__force blk_mode_t)(1 << 6)) struct gendisk { /* @@ -177,22 +179,21 @@ struct gendisk { #ifdef CONFIG_BLK_DEV_ZONED /* - * Zoned block device information for request dispatch control. - * nr_zones is the total number of zones of the device. This is always - * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones - * bits which indicates if a zone is conventional (bit set) or - * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones - * bits which indicates if a zone is write locked, that is, if a write - * request targeting the zone was dispatched. - * - * Reads of this information must be protected with blk_queue_enter() / - * blk_queue_exit(). Modifying this information is only allowed while - * no requests are being processed. See also blk_mq_freeze_queue() and - * blk_mq_unfreeze_queue(). + * Zoned block device information. Reads of this information must be + * protected with blk_queue_enter() / blk_queue_exit(). Modifying this + * information is only allowed while no requests are being processed. + * See also blk_mq_freeze_queue() and blk_mq_unfreeze_queue(). */ unsigned int nr_zones; + unsigned int zone_capacity; unsigned long *conv_zones_bitmap; - unsigned long *seq_zones_wlock; + unsigned int zone_wplugs_hash_bits; + spinlock_t zone_wplugs_lock; + struct mempool_s *zone_wplugs_pool; + struct hlist_head *zone_wplugs_hash; + struct list_head zone_wplugs_err_list; + struct work_struct zone_wplugs_work; + struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ #if IS_ENABLED(CONFIG_CDROM) @@ -231,6 +232,19 @@ static inline unsigned int disk_openers(struct gendisk *disk) return atomic_read(&disk->part0->bd_openers); } +/** + * disk_has_partscan - return %true if partition scanning is enabled on a disk + * @disk: disk to check + * + * Returns %true if partitions scanning is enabled for @disk, or %false if + * partition scanning is disabled either permanently or temporarily. + */ +static inline bool disk_has_partscan(struct gendisk *disk) +{ + return !(disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) && + !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. @@ -329,8 +343,7 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, sector_t sectors, sector_t nr_sectors); -int blk_revalidate_disk_zones(struct gendisk *disk, - void (*update_driver_data)(struct gendisk *disk)); +int blk_revalidate_disk_zones(struct gendisk *disk); /* * Independent access ranges: struct blk_independent_access_range describes @@ -447,8 +460,6 @@ struct request_queue { atomic_t nr_active_requests_shared_tags; - unsigned int required_elevator_features; - struct blk_mq_tags *sched_shared_tags; struct list_head icq_list; @@ -631,15 +642,6 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) return sector >> ilog2(disk->queue->limits.chunk_sectors); } -static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) -{ - if (!blk_queue_is_zoned(disk->queue)) - return false; - if (!disk->conv_zones_bitmap) - return true; - return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap); -} - static inline void disk_set_max_open_zones(struct gendisk *disk, unsigned int max_open_zones) { @@ -662,6 +664,7 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) return bdev->bd_disk->queue->limits.max_active_zones; } +bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int bdev_nr_zones(struct block_device *bdev) { @@ -672,10 +675,6 @@ static inline unsigned int disk_nr_zones(struct gendisk *disk) { return 0; } -static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) -{ - return false; -} static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { return 0; @@ -689,6 +688,10 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { return 0; } +static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) +{ + return false; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_depth(struct request_queue *q) @@ -853,9 +856,11 @@ static inline unsigned int bio_zone_no(struct bio *bio) return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); } -static inline unsigned int bio_zone_is_seq(struct bio *bio) +static inline bool bio_straddles_zones(struct bio *bio) { - return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); + return bio_sectors(bio) && + bio_zone_no(bio) != + disk_zone_no(bio->bi_bdev->bd_disk, bio_end_sector(bio) - 1); } /* @@ -892,18 +897,25 @@ int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim); int queue_limits_set(struct request_queue *q, struct queue_limits *lim); +/** + * queue_limits_cancel_update - cancel an atomic update of queue limits + * @q: queue to update + * + * This functions cancels an atomic update of the queue limits started by + * queue_limits_start_update() and should be used when an error occurs after + * starting update. + */ +static inline void queue_limits_cancel_update(struct request_queue *q) +{ + mutex_unlock(&q->limits_lock); +} + /* * Access functions for manipulating queue properties */ -void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit); -extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); -extern void blk_queue_max_segments(struct request_queue *, unsigned short); -extern void blk_queue_max_discard_segments(struct request_queue *, - unsigned short); void blk_queue_max_secure_erase_sectors(struct request_queue *q, unsigned int max_sectors); -extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, @@ -920,7 +932,6 @@ void disk_update_readahead(struct gendisk *disk); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); -extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, @@ -928,10 +939,6 @@ extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, sector_t offset, const char *pfx); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); -extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); -extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); -extern void blk_queue_dma_alignment(struct request_queue *, int); -extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); @@ -940,17 +947,6 @@ disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges); void disk_set_independent_access_ranges(struct gendisk *disk, struct blk_independent_access_ranges *iars); -/* - * Elevator features for blk_queue_required_elevator_features: - */ -/* Supports zoned block devices sequential write constraint */ -#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0) - -extern void blk_queue_required_elevator_features(struct request_queue *q, - unsigned int features); -extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, - struct device *dev); - bool __must_check blk_get_queue(struct request_queue *); extern void blk_put_queue(struct request_queue *); @@ -1154,12 +1150,29 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) +static inline unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l) +{ + unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors); + + return min_not_zero(l->max_zone_append_sectors, max_sectors); +} + +static inline unsigned int queue_max_zone_append_sectors(struct request_queue *q) { + if (!blk_queue_is_zoned(q)) + return 0; + + return queue_limits_max_zone_append_sectors(&q->limits); +} - const struct queue_limits *l = &q->limits; +static inline bool queue_emulates_zone_append(struct request_queue *q) +{ + return blk_queue_is_zoned(q) && !q->limits.max_zone_append_sectors; +} - return min(l->max_zone_append_sectors, l->max_sectors); +static inline bool bdev_emulates_zone_append(struct block_device *bdev) +{ + return queue_emulates_zone_append(bdev_get_queue(bdev)); } static inline unsigned int @@ -1301,18 +1314,6 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) return disk_zone_no(bdev->bd_disk, sec); } -/* Whether write serialization is required for @op on zoned devices. */ -static inline bool op_needs_zoned_write_locking(enum req_op op) -{ - return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES; -} - -static inline bool bdev_op_is_zoned_write(struct block_device *bdev, - enum req_op op) -{ - return bdev_is_zoned(bdev) && op_needs_zoned_write_locking(op); -} - static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); @@ -1328,6 +1329,12 @@ static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev, return sector & (bdev_zone_sectors(bdev) - 1); } +static inline sector_t bio_offset_from_zone_start(struct bio *bio) +{ + return bdev_offset_from_zone_start(bio->bi_bdev, + bio->bi_iter.bi_sector); +} + static inline bool bdev_is_zone_start(struct block_device *bdev, sector_t sector) { @@ -1575,6 +1582,7 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev) int bdev_freeze(struct block_device *bdev); int bdev_thaw(struct block_device *bdev); +void bdev_fput(struct file *bdev_file); struct io_comp_batch { struct request *req_list; diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index ca73940e26df..3f4b4ac527ca 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -10,6 +10,7 @@ #ifdef __KERNEL__ #include <linux/kernel.h> #include <linux/types.h> +bool __init cmdline_has_extra_options(void); #else /* !__KERNEL__ */ /* * NOTE: This is only for tools/bootconfig, because tools/bootconfig will @@ -287,7 +288,12 @@ int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos); int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ -void __init xbc_exit(void); +void __init _xbc_exit(bool early); + +static inline void xbc_exit(void) +{ + _xbc_exit(false); +} /* XBC embedded bootconfig data in kernel */ #ifdef CONFIG_BOOT_CONFIG_EMBED diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4f20f62f9d63..90094400cc63 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -184,8 +184,8 @@ struct bpf_map_ops { }; enum { - /* Support at most 10 fields in a BTF type */ - BTF_FIELDS_MAX = 10, + /* Support at most 11 fields in a BTF type */ + BTF_FIELDS_MAX = 11, }; enum btf_field_type { @@ -202,6 +202,7 @@ enum btf_field_type { BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), + BPF_WORKQUEUE = (1 << 10), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -238,6 +239,7 @@ struct btf_record { u32 field_mask; int spin_lock_off; int timer_off; + int wq_off; int refcount_off; struct btf_field fields[]; }; @@ -312,6 +314,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "bpf_spin_lock"; case BPF_TIMER: return "bpf_timer"; + case BPF_WORKQUEUE: + return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; @@ -340,6 +344,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); + case BPF_WORKQUEUE: + return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -367,6 +373,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); + case BPF_WORKQUEUE: + return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -406,6 +414,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_WORKQUEUE: case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -525,6 +534,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); +void bpf_wq_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, @@ -1116,8 +1126,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i void *func_addr); void *arch_alloc_bpf_trampoline(unsigned int size); void arch_free_bpf_trampoline(void *image, unsigned int size); -void arch_protect_bpf_trampoline(void *image, unsigned int size); -void arch_unprotect_bpf_trampoline(void *image, unsigned int size); +int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size); int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); @@ -1266,6 +1275,7 @@ int bpf_dynptr_check_size(u32 size); u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len); void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); +bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); @@ -1574,12 +1584,26 @@ struct bpf_link { enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; - struct work_struct work; + /* rcu is used before freeing, work can be used to schedule that + * RCU-based freeing before that, so they never overlap + */ + union { + struct rcu_head rcu; + struct work_struct work; + }; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); + /* deallocate link resources callback, called without RCU grace period + * waiting + */ void (*dealloc)(struct bpf_link *link); + /* deallocate link resources callback, called after RCU grace period; + * if underlying BPF program is sleepable we go through tasks trace + * RCU GP and then "classic" RCU GP + */ + void (*dealloc_deferred)(struct bpf_link *link); int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); @@ -1608,6 +1632,12 @@ struct bpf_tracing_link { struct bpf_prog *tgt_prog; }; +struct bpf_raw_tp_link { + struct bpf_link link; + struct bpf_raw_event_map *btp; + u64 cookie; +}; + struct bpf_link_primer { struct bpf_link *link; struct file *file; @@ -2190,6 +2220,7 @@ void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); +void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); @@ -2991,6 +3022,7 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); @@ -3089,6 +3121,11 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ diff --git a/include/linux/bpf_crypto.h b/include/linux/bpf_crypto.h new file mode 100644 index 000000000000..a41e71d4e2d9 --- /dev/null +++ b/include/linux/bpf_crypto.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#ifndef _BPF_CRYPTO_H +#define _BPF_CRYPTO_H + +struct bpf_crypto_type { + void *(*alloc_tfm)(const char *algo); + void (*free_tfm)(void *tfm); + int (*has_algo)(const char *algo); + int (*setkey)(void *tfm, const u8 *key, unsigned int keylen); + int (*setauthsize)(void *tfm, unsigned int authsize); + int (*encrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv); + int (*decrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv); + unsigned int (*ivsize)(void *tfm); + unsigned int (*statesize)(void *tfm); + u32 (*get_flags)(void *tfm); + struct module *owner; + char name[14]; +}; + +int bpf_crypto_register_type(const struct bpf_crypto_type *type); +int bpf_crypto_unregister_type(const struct bpf_crypto_type *type); + +#endif /* _BPF_CRYPTO_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7cb1b75eee38..50aa87f8d77f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -421,11 +421,13 @@ struct bpf_verifier_state { struct bpf_active_lock active_lock; bool speculative; bool active_rcu_lock; + u32 active_preempt_lock; /* If this state was ever pointed-to by other state's loop_entry field * this flag would be set to true. Used to avoid freeing such states * while they are still in use. */ bool used_as_loop_entry; + bool in_sleepable; /* first and last insn idx of this verifier state */ u32 first_insn_idx; @@ -502,6 +504,13 @@ struct bpf_loop_inline_state { u32 callback_subprogno; /* valid when fit_for_inline is true */ }; +/* pointer and state for maps */ +struct bpf_map_ptr_state { + struct bpf_map *map_ptr; + bool poison; + bool unpriv; +}; + /* Possible states for alu_state member. */ #define BPF_ALU_SANITIZE_SRC (1U << 0) #define BPF_ALU_SANITIZE_DST (1U << 1) @@ -514,7 +523,7 @@ struct bpf_loop_inline_state { struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ - unsigned long map_ptr_state; /* pointer/poison value for maps */ + struct bpf_map_ptr_state map_ptr_state; s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ struct { diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 9e97ced2896d..14fa93268630 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -65,7 +65,8 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); struct request_queue *bsg_setup_queue(struct device *dev, const char *name, - bsg_job_fn *job_fn, bsg_timeout_fn *timeout, int dd_job_size); + struct queue_limits *lim, bsg_job_fn *job_fn, + bsg_timeout_fn *timeout, int dd_job_size); void bsg_remove_queue(struct request_queue *q); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index e24aabfe8ecc..c0e3e1426a82 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -3,6 +3,8 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#include <linux/types.h> /* for u32 */ + struct btf_id_set { u32 cnt; u32 ids[]; diff --git a/include/linux/buildid.h b/include/linux/buildid.h index 8a582d242f06..20aa3c2d89f7 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -11,7 +11,7 @@ int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size); -#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_CRASH_CORE) +#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_VMCORE_INFO) extern unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX]; void init_vmlinux_build_id(void); #else diff --git a/include/linux/bus/stm32_firewall_device.h b/include/linux/bus/stm32_firewall_device.h new file mode 100644 index 000000000000..18e0a2fc3816 --- /dev/null +++ b/include/linux/bus/stm32_firewall_device.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023, STMicroelectronics - All Rights Reserved + */ + +#ifndef STM32_FIREWALL_DEVICE_H +#define STM32_FIREWALL_DEVICE_H + +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/types.h> + +#define STM32_FIREWALL_MAX_EXTRA_ARGS 5 + +/* Opaque reference to stm32_firewall_controller */ +struct stm32_firewall_controller; + +/** + * struct stm32_firewall - Information on a device's firewall. Each device can have more than one + * firewall. + * + * @firewall_ctrl: Pointer referencing a firewall controller of the device. It is + * opaque so a device cannot manipulate the controller's ops or access + * the controller's data + * @extra_args: Extra arguments that are implementation dependent + * @entry: Name of the firewall entry + * @extra_args_size: Number of extra arguments + * @firewall_id: Firewall ID associated the device for this firewall controller + */ +struct stm32_firewall { + struct stm32_firewall_controller *firewall_ctrl; + u32 extra_args[STM32_FIREWALL_MAX_EXTRA_ARGS]; + const char *entry; + size_t extra_args_size; + u32 firewall_id; +}; + +#if IS_ENABLED(CONFIG_STM32_FIREWALL) +/** + * stm32_firewall_get_firewall - Get the firewall(s) associated to given device. + * The firewall controller reference is always the first argument + * of each of the access-controller property entries. + * The firewall ID is always the second argument of each of the + * access-controller property entries. + * If there's no argument linked to the phandle, then the firewall ID + * field is set to U32_MAX, which is an invalid ID. + * + * @np: Device node to parse + * @firewall: Array of firewall references + * @nb_firewall: Number of firewall references to get. Must be at least 1. + * + * Returns 0 on success, -ENODEV if there's no match with a firewall controller or appropriate errno + * code if error occurred. + */ +int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, + unsigned int nb_firewall); + +/** + * stm32_firewall_grant_access - Request firewall access rights and grant access. + * + * @firewall: Firewall reference containing the ID to check against its firewall + * controller + * + * Returns 0 if access is granted, -EACCES if access is denied, -ENODEV if firewall is null or + * appropriate errno code if error occurred + */ +int stm32_firewall_grant_access(struct stm32_firewall *firewall); + +/** + * stm32_firewall_release_access - Release access granted from a call to + * stm32_firewall_grant_access(). + * + * @firewall: Firewall reference containing the ID to check against its firewall + * controller + */ +void stm32_firewall_release_access(struct stm32_firewall *firewall); + +/** + * stm32_firewall_grant_access_by_id - Request firewall access rights of a given device + * based on a specific firewall ID + * + * Warnings: + * There is no way to ensure that the given ID will correspond to the firewall referenced in the + * device node if the ID did not come from stm32_firewall_get_firewall(). In that case, this + * function must be used with caution. + * This function should be used for subsystem resources that do not have the same firewall ID + * as their parent. + * U32_MAX is an invalid ID. + * + * @firewall: Firewall reference containing the firewall controller + * @subsystem_id: Firewall ID of the subsystem resource + * + * Returns 0 if access is granted, -EACCES if access is denied, -ENODEV if firewall is null or + * appropriate errno code if error occurred + */ +int stm32_firewall_grant_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id); + +/** + * stm32_firewall_release_access_by_id - Release access granted from a call to + * stm32_firewall_grant_access_by_id(). + * + * Warnings: + * There is no way to ensure that the given ID will correspond to the firewall referenced in the + * device node if the ID did not come from stm32_firewall_get_firewall(). In that case, this + * function must be used with caution. + * This function should be used for subsystem resources that do not have the same firewall ID + * as their parent. + * U32_MAX is an invalid ID. + * + * @firewall: Firewall reference containing the firewall controller + * @subsystem_id: Firewall ID of the subsystem resource + */ +void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id); + +#else /* CONFIG_STM32_FIREWALL */ + +int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, + unsigned int nb_firewall); +{ + return -ENODEV; +} + +int stm32_firewall_grant_access(struct stm32_firewall *firewall) +{ + return -ENODEV; +} + +void stm32_firewall_release_access(struct stm32_firewall *firewall) +{ +} + +int stm32_firewall_grant_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id) +{ + return -ENODEV; +} + +void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id) +{ +} + +#endif /* CONFIG_STM32_FIREWALL */ +#endif /* STM32_FIREWALL_DEVICE_H */ diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index d504eb4b49ab..2cb15fe4fe12 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -138,4 +138,10 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level) #define use_arch_cache_info() (false) #endif +#ifndef CONFIG_ARCH_HAS_CPU_CACHE_ALIASING +#define cpu_dcache_is_aliasing() false +#else +#include <asm/cachetype.h> +#endif + #endif /* _LINUX_CACHEINFO_H */ diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index cb0d6cd1c12f..60693a145894 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -90,6 +90,14 @@ enum cc_attr { * Examples include TDX Guest. */ CC_ATTR_HOTPLUG_DISABLED, + + /** + * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host. + * + * The host kernel is running with the necessary features + * enabled to run SEV-SNP guests. + */ + CC_ATTR_HOST_SEV_SNP, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM @@ -107,10 +115,14 @@ enum cc_attr { * * FALSE - Specified Confidential Computing attribute is not active */ bool cc_platform_has(enum cc_attr attr); +void cc_platform_set(enum cc_attr attr); +void cc_platform_clear(enum cc_attr attr); #else /* !CONFIG_ARCH_HAS_CC_PLATFORM */ static inline bool cc_platform_has(enum cc_attr attr) { return false; } +static inline void cc_platform_set(enum cc_attr attr) { } +static inline void cc_platform_clear(enum cc_attr attr) { } #endif /* CONFIG_ARCH_HAS_CC_PLATFORM */ diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h index 6355a36a3f81..b57118aaa679 100644 --- a/include/linux/cdx/cdx_bus.h +++ b/include/linux/cdx/cdx_bus.h @@ -12,6 +12,7 @@ #include <linux/device.h> #include <linux/list.h> #include <linux/mod_devicetable.h> +#include <linux/msi.h> #define MAX_CDX_DEV_RESOURCES 4 #define CDX_CONTROLLER_ID_SHIFT 4 @@ -21,13 +22,25 @@ struct cdx_controller; enum { + CDX_DEV_MSI_CONF, CDX_DEV_BUS_MASTER_CONF, CDX_DEV_RESET_CONF, + CDX_DEV_MSI_ENABLE, +}; + +struct cdx_msi_config { + u64 addr; + u32 data; + u16 msi_index; }; struct cdx_device_config { u8 type; - bool bus_master_enable; + union { + struct cdx_msi_config msi; + bool bus_master_enable; + bool msi_enable; + }; }; typedef int (*cdx_bus_enable_cb)(struct cdx_controller *cdx, u8 bus_num); @@ -87,6 +100,7 @@ struct cdx_ops { * struct cdx_controller: CDX controller object * @dev: Linux device associated with the CDX controller. * @priv: private data + * @msi_domain: MSI domain * @id: Controller ID * @controller_registered: controller registered with bus * @ops: CDX controller ops @@ -94,6 +108,7 @@ struct cdx_ops { struct cdx_controller { struct device *dev; void *priv; + struct irq_domain *msi_domain; u32 id; bool controller_registered; struct cdx_ops *ops; @@ -120,9 +135,13 @@ struct cdx_controller { * @req_id: Requestor ID associated with CDX device * @is_bus: Is this bus device * @enabled: is this bus enabled + * @msi_dev_id: MSI Device ID associated with CDX device + * @num_msi: Number of MSI's supported by the 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. + * @irqchip_lock: lock to synchronize irq/msi configuration + * @msi_write_pending: MSI write pending for this device */ struct cdx_device { struct device dev; @@ -144,7 +163,11 @@ struct cdx_device { u32 req_id; bool is_bus; bool enabled; + u32 msi_dev_id; + u32 num_msi; const char *driver_override; + struct mutex irqchip_lock; + bool msi_write_pending; }; #define to_cdx_device(_dev) \ @@ -237,4 +260,32 @@ int cdx_set_master(struct cdx_device *cdx_dev); */ int cdx_clear_master(struct cdx_device *cdx_dev); +#ifdef CONFIG_GENERIC_MSI_IRQ +/** + * cdx_enable_msi - Enable MSI for the CDX device. + * @cdx_dev: device pointer + * + * Return: 0 for success, -errno on failure + */ +int cdx_enable_msi(struct cdx_device *cdx_dev); + +/** + * cdx_disable_msi - Disable MSI for the CDX device. + * @cdx_dev: device pointer + */ +void cdx_disable_msi(struct cdx_device *cdx_dev); + +#else /* CONFIG_GENERIC_MSI_IRQ */ + +static inline int cdx_enable_msi(struct cdx_device *cdx_dev) +{ + return -ENODEV; +} + +static inline void cdx_disable_msi(struct cdx_device *cdx_dev) +{ +} + +#endif /* CONFIG_GENERIC_MSI_IRQ */ + #endif /* _CDX_BUS_H_ */ diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 1293c38ddb7f..4a537260f655 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1084,18 +1084,28 @@ void of_fixed_factor_clk_setup(struct device_node *node); * @hw: handle between common and hardware-specific interfaces * @mult: multiplier * @div: divider + * @acc: fixed accuracy in ppb + * @flags: behavior modifying flags * * Clock with a fixed multiplier and divider. The output frequency is the * parent clock rate divided by div and multiplied by mult. - * Implements .recalc_rate, .set_rate and .round_rate + * Implements .recalc_rate, .set_rate, .round_rate and .recalc_accuracy + * + * Flags: + * * CLK_FIXED_FACTOR_FIXED_ACCURACY - Use the value in @acc instead of the + * parent clk accuracy. */ struct clk_fixed_factor { struct clk_hw hw; unsigned int mult; unsigned int div; + unsigned long acc; + unsigned int flags; }; +#define CLK_FIXED_FACTOR_FIXED_ACCURACY BIT(0) + #define to_clk_fixed_factor(_hw) container_of(_hw, struct clk_fixed_factor, hw) extern const struct clk_ops clk_fixed_factor_ops; @@ -1106,10 +1116,24 @@ void clk_unregister_fixed_factor(struct clk *clk); struct clk_hw *clk_hw_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); +struct clk_hw *clk_hw_register_fixed_factor_fwname(struct device *dev, + struct device_node *np, const char *name, const char *fw_name, + unsigned long flags, unsigned int mult, unsigned int div); +struct clk_hw *clk_hw_register_fixed_factor_with_accuracy_fwname(struct device *dev, + struct device_node *np, const char *name, const char *fw_name, + unsigned long flags, unsigned int mult, unsigned int div, + unsigned long acc); void clk_hw_unregister_fixed_factor(struct clk_hw *hw); struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); +struct clk_hw *devm_clk_hw_register_fixed_factor_fwname(struct device *dev, + struct device_node *np, const char *name, const char *fw_name, + unsigned long flags, unsigned int mult, unsigned int div); +struct clk_hw *devm_clk_hw_register_fixed_factor_with_accuracy_fwname(struct device *dev, + struct device_node *np, const char *name, const char *fw_name, + unsigned long flags, unsigned int mult, unsigned int div, + unsigned long acc); struct clk_hw *devm_clk_hw_register_fixed_factor_index(struct device *dev, const char *name, unsigned int index, unsigned long flags, unsigned int mult, unsigned int div); diff --git a/include/linux/clk.h b/include/linux/clk.h index 06f1b292f8a0..0fa56d672532 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -202,6 +202,18 @@ bool clk_is_match(const struct clk *p, const struct clk *q); int clk_rate_exclusive_get(struct clk *clk); /** + * devm_clk_rate_exclusive_get - devm variant of clk_rate_exclusive_get + * @dev: device the exclusivity is bound to + * @clk: clock source + * + * Calls clk_rate_exclusive_get() on @clk and registers a devm cleanup handler + * on @dev to call clk_rate_exclusive_put(). + * + * Must not be called from within atomic context. + */ +int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk); + +/** * clk_rate_exclusive_put - release exclusivity over the rate control of a * producer * @clk: clock source @@ -274,6 +286,11 @@ static inline int clk_rate_exclusive_get(struct clk *clk) return 0; } +static inline int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk) +{ + return 0; +} + static inline void clk_rate_exclusive_put(struct clk *clk) {} #endif @@ -479,6 +496,22 @@ int __must_check devm_clk_bulk_get_all(struct device *dev, struct clk_bulk_data **clks); /** + * devm_clk_bulk_get_all_enable - Get and enable all clocks of the consumer (managed) + * @dev: device for clock "consumer" + * @clks: pointer to the clk_bulk_data table of consumer + * + * Returns success (0) or negative errno. + * + * This helper function allows drivers to get all clocks of the + * consumer and enables them in one operation with management. + * The clks will automatically be disabled and freed when the device + * is unbound. + */ + +int __must_check devm_clk_bulk_get_all_enable(struct device *dev, + struct clk_bulk_data **clks); + +/** * devm_clk_get - lookup and obtain a managed reference to a clock producer. * @dev: device for clock "consumer" * @id: clock consumer ID @@ -968,6 +1001,12 @@ static inline int __must_check devm_clk_bulk_get_all(struct device *dev, return 0; } +static inline int __must_check devm_clk_bulk_get_all_enable(struct device *dev, + struct clk_bulk_data **clks) +{ + return 0; +} + static inline struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id) { diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index cbfcbf186ce3..e656f63efdce 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -13,11 +13,14 @@ /** * struct clk_omap_reg - OMAP register declaration * @offset: offset from the master IP module base address + * @bit: register bit offset * @index: index of the master IP module + * @flags: flags */ struct clk_omap_reg { void __iomem *ptr; u16 offset; + u8 bit; u8 index; u8 flags; }; diff --git a/include/linux/cma.h b/include/linux/cma.h index 63873b93deaa..9db877506ea8 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -6,12 +6,8 @@ #include <linux/types.h> #include <linux/numa.h> -/* - * There is always at least global CMA area and a few optional - * areas configured in kernel .config. - */ #ifdef CONFIG_CMA_AREAS -#define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) +#define MAX_CMA_AREAS CONFIG_CMA_AREAS #endif #define CMA_MAX_NAME 64 diff --git a/include/linux/cmpxchg-emu.h b/include/linux/cmpxchg-emu.h new file mode 100644 index 000000000000..998deec67740 --- /dev/null +++ b/include/linux/cmpxchg-emu.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Emulated 1-byte and 2-byte cmpxchg operations for architectures + * lacking direct support for these sizes. These are implemented in terms + * of 4-byte cmpxchg operations. + * + * Copyright (C) 2024 Paul E. McKenney. + */ + +#ifndef __LINUX_CMPXCHG_EMU_H +#define __LINUX_CMPXCHG_EMU_H + +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new); + +#endif /* __LINUX_CMPXCHG_EMU_H */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index ddab1ef22bee..49feac0162a5 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -9,7 +9,7 @@ * Clang prior to 17 is being silly and considers many __cleanup() variables * as unused (because they are, their sole purpose is to go out of scope). * - * https://reviews.llvm.org/D152180 + * https://github.com/llvm/llvm-project/commit/877210faa447f4cc7db87812f8ed80e398fedd61 */ #undef __cleanup #define __cleanup(func) __maybe_unused __attribute__((__cleanup__(func))) @@ -114,11 +114,7 @@ #define __diag_str(s) __diag_str1(s) #define __diag(s) _Pragma(__diag_str(clang diagnostic s)) -#if CONFIG_CLANG_VERSION >= 110000 -#define __diag_clang_11(s) __diag(s) -#else -#define __diag_clang_11(s) -#endif +#define __diag_clang_13(s) __diag(s) #define __diag_ignore_all(option, comment) \ - __diag_clang(11, ignore, option) + __diag_clang(13, ignore, option) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 52730e423681..8c252e073bd8 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -116,6 +116,14 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, */ #define __stringify_label(n) #n +#define __annotate_reachable(c) ({ \ + asm volatile(__stringify_label(c) ":\n\t" \ + ".pushsection .discard.reachable\n\t" \ + ".long " __stringify_label(c) "b - .\n\t" \ + ".popsection\n\t"); \ +}) +#define annotate_reachable() __annotate_reachable(__COUNTER__) + #define __annotate_unreachable(c) ({ \ asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.unreachable\n\t" \ @@ -128,6 +136,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define __annotate_jump_table __section(".rodata..c_jump_table") #else /* !CONFIG_OBJTOOL */ +#define annotate_reachable() #define annotate_unreachable() #define __annotate_jump_table #endif /* CONFIG_OBJTOOL */ @@ -259,7 +268,7 @@ static inline void *offset_to_ptr(const int *off) * - When one operand is a null pointer constant (i.e. when x is an integer * constant expression) and the other is an object pointer (i.e. our * third operand), the conditional operator returns the type of the - * object pointer operand (i.e. "int *). Here, within the sizeof(), we + * object pointer operand (i.e. "int *"). Here, within the sizeof(), we * would then get: * sizeof(*((int *)(...)) == sizeof(int) == 4 * - When one operand is a void pointer (i.e. when x is not an integer diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3e64ec0f7ac8..d1a9dbb8e1a7 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -99,17 +99,17 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute * * When -falign-functions=N is in use, we must avoid the cold attribute as - * contemporary versions of GCC drop the alignment for cold functions. Worse, - * GCC can implicitly mark callees of cold functions as cold themselves, so - * it's not sufficient to add __function_aligned here as that will not ensure - * that callees are correctly aligned. + * GCC drops the alignment for cold functions. Worse, GCC can implicitly mark + * callees of cold functions as cold themselves, so it's not sufficient to add + * __function_aligned here as that will not ensure that callees are correctly + * aligned. * * See: * * https://lore.kernel.org/lkml/Y77%2FqVgvaJidFpYt@FVFF77S0Q05N * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c9 */ -#if !defined(CONFIG_CC_IS_GCC) || (CONFIG_FUNCTION_ALIGNMENT == 0) +#if defined(CONFIG_CC_HAS_SANE_FUNCTION_ALIGNMENT) || (CONFIG_FUNCTION_ALIGNMENT == 0) #define __cold __attribute__((__cold__)) #else #define __cold @@ -273,15 +273,44 @@ struct ftrace_likely_data { * disable all instrumentation. See Kconfig.kcsan where this is mandatory. */ # define __no_kcsan __no_sanitize_thread __disable_sanitizer_instrumentation +/* + * Type qualifier to mark variables where all data-racy accesses should be + * ignored by KCSAN. Note, the implementation simply marks these variables as + * volatile, since KCSAN will treat such accesses as "marked". + */ +# define __data_racy volatile # define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused #else # define __no_kcsan +# define __data_racy +#endif + +#ifdef __SANITIZE_MEMORY__ +/* + * Similarly to KASAN and KCSAN, KMSAN loses function attributes of inlined + * functions, therefore disabling KMSAN checks also requires disabling inlining. + * + * __no_sanitize_or_inline effectively prevents KMSAN from reporting errors + * within the function and marks all its outputs as initialized. + */ +# define __no_sanitize_or_inline __no_kmsan_checks notrace __maybe_unused #endif #ifndef __no_sanitize_or_inline #define __no_sanitize_or_inline __always_inline #endif +/* + * Apply __counted_by() when the Endianness matches to increase test coverage. + */ +#ifdef __LITTLE_ENDIAN +#define __counted_by_le(member) __counted_by(member) +#define __counted_by_be(member) +#else +#define __counted_by_le(member) +#define __counted_by_be(member) __counted_by(member) +#endif + /* Do not trap wrapping arithmetic within an annotated function. */ #ifdef CONFIG_UBSAN_SIGNED_WRAP # define __signed_wrap __attribute__((no_sanitize("signed-integer-overflow"))) diff --git a/include/linux/console.h b/include/linux/console.h index 779d388af8a0..31a8f5b85f5d 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -18,6 +18,7 @@ #include <linux/bits.h> #include <linux/rculist.h> #include <linux/types.h> +#include <linux/vesa.h> struct vc_data; struct console_font_op; @@ -36,63 +37,91 @@ enum vc_intensity; /** * struct consw - callbacks for consoles * + * @owner: the module to get references of when this console is used + * @con_startup: set up the console and return its name (like VGA, EGA, ...) + * @con_init: initialize the console on @vc. @init is true for the very first + * call on this @vc. + * @con_deinit: deinitialize the console from @vc. + * @con_clear: erase @count characters at [@x, @y] on @vc. @count >= 1. + * @con_putc: emit one character with attributes @ca to [@x, @y] on @vc. + * (optional -- @con_putcs would be called instead) + * @con_putcs: emit @count characters with attributes @s to [@x, @y] on @vc. + * @con_cursor: enable/disable cursor depending on @enable * @con_scroll: move lines from @top to @bottom in direction @dir by @lines. * Return true if no generic handling should be done. * Invoked by csi_M and printing to the console. - * @con_set_palette: sets the palette of the console to @table (optional) + * @con_switch: notifier about the console switch; it is supposed to return + * true if a redraw is needed. + * @con_blank: blank/unblank the console. The target mode is passed in @blank. + * @mode_switch is set if changing from/to text/graphics. The hook + * is supposed to return true if a redraw is needed. + * @con_font_set: set console @vc font to @font with height @vpitch. @flags can + * be %KD_FONT_FLAG_DONT_RECALC. (optional) + * @con_font_get: fetch the current font on @vc of height @vpitch into @font. + * (optional) + * @con_font_default: set default font on @vc. @name can be %NULL or font name + * to search for. @font can be filled back. (optional) + * @con_resize: resize the @vc console to @width x @height. @from_user is true + * when this change comes from the user space. + * @con_set_palette: sets the palette of the console @vc to @table (optional) * @con_scrolldelta: the contents of the console should be scrolled by @lines. * Invoked by user. (optional) + * @con_set_origin: set origin (see &vc_data::vc_origin) of the @vc. If not + * provided or returns false, the origin is set to + * @vc->vc_screenbuf. (optional) + * @con_save_screen: save screen content into @vc->vc_screenbuf. Called e.g. + * upon entering graphics. (optional) + * @con_build_attr: build attributes based on @color, @intensity and other + * parameters. The result is used for both normal and erase + * characters. (optional) + * @con_invert_region: invert a region of length @count on @vc starting at @p. + * (optional) + * @con_debug_enter: prepare the console for the debugger. This includes, but + * is not limited to, unblanking the console, loading an + * appropriate palette, and allowing debugger generated output. + * (optional) + * @con_debug_leave: restore the console to its pre-debug state as closely as + * possible. (optional) */ struct consw { struct module *owner; const char *(*con_startup)(void); - void (*con_init)(struct vc_data *vc, int init); + void (*con_init)(struct vc_data *vc, bool init); void (*con_deinit)(struct vc_data *vc); - void (*con_clear)(struct vc_data *vc, int sy, int sx, int height, - int width); - void (*con_putc)(struct vc_data *vc, int c, int ypos, int xpos); - void (*con_putcs)(struct vc_data *vc, const unsigned short *s, - int count, int ypos, int xpos); - void (*con_cursor)(struct vc_data *vc, int mode); + void (*con_clear)(struct vc_data *vc, unsigned int y, + unsigned int x, unsigned int count); + void (*con_putc)(struct vc_data *vc, u16 ca, unsigned int y, + unsigned int x); + void (*con_putcs)(struct vc_data *vc, const u16 *s, + unsigned int count, unsigned int ypos, + unsigned int xpos); + void (*con_cursor)(struct vc_data *vc, bool enable); bool (*con_scroll)(struct vc_data *vc, unsigned int top, unsigned int bottom, enum con_scroll dir, unsigned int lines); - int (*con_switch)(struct vc_data *vc); - int (*con_blank)(struct vc_data *vc, int blank, int mode_switch); - int (*con_font_set)(struct vc_data *vc, struct console_font *font, - unsigned int vpitch, unsigned int flags); + bool (*con_switch)(struct vc_data *vc); + bool (*con_blank)(struct vc_data *vc, enum vesa_blank_mode blank, + bool mode_switch); + int (*con_font_set)(struct vc_data *vc, + const struct console_font *font, + unsigned int vpitch, unsigned int flags); int (*con_font_get)(struct vc_data *vc, struct console_font *font, unsigned int vpitch); int (*con_font_default)(struct vc_data *vc, - struct console_font *font, char *name); + struct console_font *font, const char *name); int (*con_resize)(struct vc_data *vc, unsigned int width, - unsigned int height, unsigned int user); + unsigned int height, bool from_user); void (*con_set_palette)(struct vc_data *vc, const unsigned char *table); void (*con_scrolldelta)(struct vc_data *vc, int lines); - int (*con_set_origin)(struct vc_data *vc); + bool (*con_set_origin)(struct vc_data *vc); void (*con_save_screen)(struct vc_data *vc); u8 (*con_build_attr)(struct vc_data *vc, u8 color, enum vc_intensity intensity, bool blink, bool underline, bool reverse, bool italic); void (*con_invert_region)(struct vc_data *vc, u16 *p, int count); - u16 *(*con_screen_pos)(const struct vc_data *vc, int offset); - unsigned long (*con_getxy)(struct vc_data *vc, unsigned long position, - int *px, int *py); - /* - * Flush the video console driver's scrollback buffer - */ - void (*con_flush_scrollback)(struct vc_data *vc); - /* - * Prepare the console for the debugger. This includes, but is not - * limited to, unblanking the console, loading an appropriate - * palette, and allowing debugger generated output. - */ - int (*con_debug_enter)(struct vc_data *vc); - /* - * Restore the console to its pre-debug state as closely as possible. - */ - int (*con_debug_leave)(struct vc_data *vc); + void (*con_debug_enter)(struct vc_data *vc); + void (*con_debug_leave)(struct vc_data *vc); }; extern const struct consw *conswitchp; @@ -112,32 +141,21 @@ int con_is_bound(const struct consw *csw); int do_unregister_con_driver(const struct consw *csw); int do_take_over_console(const struct consw *sw, int first, int last, int deflt); void give_up_console(const struct consw *sw); -#ifdef CONFIG_HW_CONSOLE -int con_debug_enter(struct vc_data *vc); -int con_debug_leave(void); +#ifdef CONFIG_VT +void con_debug_enter(struct vc_data *vc); +void con_debug_leave(void); #else -static inline int con_debug_enter(struct vc_data *vc) -{ - return 0; -} -static inline int con_debug_leave(void) -{ - return 0; -} +static inline void con_debug_enter(struct vc_data *vc) { } +static inline void con_debug_leave(void) { } #endif -/* cursor */ -#define CM_DRAW (1) -#define CM_ERASE (2) -#define CM_MOVE (3) - /* * The interface for a console, or any other device that wants to capture * console messages (printer driver?) */ /** - * cons_flags - General console flags + * enum cons_flags - General console flags * @CON_PRINTBUFFER: Used by newly registered consoles to avoid duplicate * output of messages that were already shown by boot * consoles or read by userspace via syslog() syscall. @@ -218,7 +236,7 @@ struct nbcon_state { static_assert(sizeof(struct nbcon_state) <= sizeof(int)); /** - * nbcon_prio - console owner priority for nbcon consoles + * enum nbcon_prio - console owner priority for nbcon consoles * @NBCON_PRIO_NONE: Unused * @NBCON_PRIO_NORMAL: Normal (non-emergency) usage * @NBCON_PRIO_EMERGENCY: Emergency output (WARN/OOPS...) @@ -450,7 +468,7 @@ static inline bool console_is_registered(const struct console *con) * for_each_console() - Iterator over registered consoles * @con: struct console pointer used as loop cursor * - * The console list and the console->flags are immutable while iterating. + * The console list and the &console.flags are immutable while iterating. * * Requires console_list_lock to be held. */ @@ -520,12 +538,6 @@ void vcs_remove_sysfs(int index); */ extern atomic_t ignore_console_lock_warning; -/* VESA Blanking Levels */ -#define VESA_NO_BLANKING 0 -#define VESA_VSYNC_SUSPEND 1 -#define VESA_HSYNC_SUSPEND 2 -#define VESA_POWERDOWN 3 - extern void console_init(void); /* For deferred console takeover */ diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 539f1cd45309..20f564e98552 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -151,7 +151,6 @@ struct vc_data { DECLARE_BITMAP(vc_tab_stop, VC_TABSTOPS_COUNT); /* Tab stops. 256 columns. */ unsigned char vc_palette[16*3]; /* Colour palette for VGA+ */ unsigned short * vc_translate; - unsigned int vc_resize_user; /* resize request from user */ unsigned int vc_bell_pitch; /* Console bell pitch */ unsigned int vc_bell_duration; /* Console bell duration */ unsigned short vc_cur_blink_ms; /* Cursor blink duration */ diff --git a/include/linux/coredump.h b/include/linux/coredump.h index d3eba4360150..0904ba010341 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -30,6 +30,8 @@ struct coredump_params { struct core_vma_metadata *vma_meta; }; +extern unsigned int core_file_note_size_limit; + /* * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. diff --git a/include/linux/coresight.h b/include/linux/coresight.h index a4cb7dd6ca23..5f288d475490 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -35,7 +35,7 @@ #define CORESIGHT_UNLOCK 0xc5acce55 -extern struct bus_type coresight_bustype; +extern const struct bus_type coresight_bustype; enum coresight_dev_type { CORESIGHT_DEV_TYPE_SINK, @@ -226,13 +226,26 @@ struct coresight_sysfs_link { * by @coresight_ops. * @access: Device i/o access abstraction for this device. * @dev: The device entity associated to this component. - * @refcnt: keep track of what is in use. + * @mode: This tracer's mode, i.e sysFS, Perf or disabled. This is + * actually an 'enum cs_mode', but is stored in an atomic type. + * This is always accessed through local_read() and local_set(), + * but wherever it's done from within the Coresight device's lock, + * a non-atomic read would also work. This is the main point of + * synchronisation between code happening inside the sysfs mode's + * coresight_mutex and outside when running in Perf mode. A compare + * and exchange swap is done to atomically claim one mode or the + * other. + * @refcnt: keep track of what is in use. Only access this outside of the + * device's spinlock when the coresight_mutex held and mode == + * CS_MODE_SYSFS. Otherwise it must be accessed from inside the + * spinlock. * @orphan: true if the component has connections that haven't been linked. - * @enable: 'true' if component is currently part of an active path. - * @activated: 'true' only if a _sink_ has been activated. A sink can be - * activated but not yet enabled. Enabling for a _sink_ - * happens when a source has been selected and a path is enabled - * from source to that sink. + * @sysfs_sink_activated: 'true' when a sink has been selected for use via sysfs + * by writing a 1 to the 'enable_sink' file. A sink can be + * activated but not yet enabled. Enabling for a _sink_ happens + * when a source has been selected and a path is enabled from + * source to that sink. A sink can also become enabled but not + * activated if it's used via Perf. * @ea: Device attribute for sink representation under PMU directory. * @def_sink: cached reference to default sink found for this device. * @nr_links: number of sysfs links created to other components from this @@ -250,11 +263,11 @@ struct coresight_device { const struct coresight_ops *ops; struct csdev_access access; struct device dev; - atomic_t refcnt; + local_t mode; + int refcnt; bool orphan; - bool enable; /* true only if configured as part of a path */ /* sink specific fields */ - bool activated; /* true only if a sink is part of a path */ + bool sysfs_sink_activated; struct dev_ext_attribute *ea; struct coresight_device *def_sink; /* sysfs links between components */ @@ -378,8 +391,6 @@ struct coresight_ops { const struct coresight_ops_helper *helper_ops; }; -#if IS_ENABLED(CONFIG_CORESIGHT) - static inline u32 csdev_access_relaxed_read32(struct csdev_access *csa, u32 offset) { @@ -569,11 +580,43 @@ static inline bool coresight_is_percpu_sink(struct coresight_device *csdev) (csdev->subtype.sink_subtype == CORESIGHT_DEV_SUBTYPE_SINK_PERCPU_SYSMEM); } +/* + * Atomically try to take the device and set a new mode. Returns true on + * success, false if the device is already taken by someone else. + */ +static inline bool coresight_take_mode(struct coresight_device *csdev, + enum cs_mode new_mode) +{ + return local_cmpxchg(&csdev->mode, CS_MODE_DISABLED, new_mode) == + CS_MODE_DISABLED; +} + +static inline enum cs_mode coresight_get_mode(struct coresight_device *csdev) +{ + return local_read(&csdev->mode); +} + +static inline void coresight_set_mode(struct coresight_device *csdev, + enum cs_mode new_mode) +{ + enum cs_mode current_mode = coresight_get_mode(csdev); + + /* + * Changing to a new mode must be done from an already disabled state + * unless it's synchronized with coresight_take_mode(). Otherwise the + * device is already in use and signifies a locking issue. + */ + WARN(new_mode != CS_MODE_DISABLED && current_mode != CS_MODE_DISABLED && + current_mode != new_mode, "Device already in use\n"); + + local_set(&csdev->mode, new_mode); +} + extern struct coresight_device * coresight_register(struct coresight_desc *desc); extern void coresight_unregister(struct coresight_device *csdev); -extern int coresight_enable(struct coresight_device *csdev); -extern void coresight_disable(struct coresight_device *csdev); +extern int coresight_enable_sysfs(struct coresight_device *csdev); +extern void coresight_disable_sysfs(struct coresight_device *csdev); extern int coresight_timeout(struct csdev_access *csa, u32 offset, int position, int value); @@ -598,83 +641,6 @@ void coresight_relaxed_write64(struct coresight_device *csdev, u64 val, u32 offset); void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset); -#else -static inline struct coresight_device * -coresight_register(struct coresight_desc *desc) { return NULL; } -static inline void coresight_unregister(struct coresight_device *csdev) {} -static inline int -coresight_enable(struct coresight_device *csdev) { return -ENOSYS; } -static inline void coresight_disable(struct coresight_device *csdev) {} - -static inline int coresight_timeout(struct csdev_access *csa, u32 offset, - int position, int value) -{ - return 1; -} - -static inline int coresight_claim_device_unlocked(struct coresight_device *csdev) -{ - return -EINVAL; -} - -static inline int coresight_claim_device(struct coresight_device *csdev) -{ - return -EINVAL; -} - -static inline void coresight_disclaim_device(struct coresight_device *csdev) {} -static inline void coresight_disclaim_device_unlocked(struct coresight_device *csdev) {} - -static inline bool coresight_loses_context_with_cpu(struct device *dev) -{ - return false; -} - -static inline u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset) -{ - WARN_ON_ONCE(1); - return 0; -} - -static inline u32 coresight_read32(struct coresight_device *csdev, u32 offset) -{ - WARN_ON_ONCE(1); - return 0; -} - -static inline void coresight_write32(struct coresight_device *csdev, u32 val, u32 offset) -{ -} - -static inline void coresight_relaxed_write32(struct coresight_device *csdev, - u32 val, u32 offset) -{ -} - -static inline u64 coresight_relaxed_read64(struct coresight_device *csdev, - u32 offset) -{ - WARN_ON_ONCE(1); - return 0; -} - -static inline u64 coresight_read64(struct coresight_device *csdev, u32 offset) -{ - WARN_ON_ONCE(1); - return 0; -} - -static inline void coresight_relaxed_write64(struct coresight_device *csdev, - u64 val, u32 offset) -{ -} - -static inline void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset) -{ -} - -#endif /* IS_ENABLED(CONFIG_CORESIGHT) */ - extern int coresight_get_cpu(struct device *dev); struct coresight_platform_data *coresight_get_platform_data(struct device *dev); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ae5a20cf2f9c..861c3bfc5f17 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -130,7 +130,7 @@ static inline void cpu_maps_update_done(void) static inline int add_cpu(unsigned int cpu) { return 0;} #endif /* CONFIG_SMP */ -extern struct bus_type cpu_subsys; +extern const struct bus_type cpu_subsys; extern int lockdep_is_cpus_held(void); @@ -221,7 +221,18 @@ void cpuhp_report_idle_dead(void); static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +#ifdef CONFIG_CPU_MITIGATIONS extern bool cpu_mitigations_off(void); extern bool cpu_mitigations_auto_nosmt(void); +#else +static inline bool cpu_mitigations_off(void) +{ + return true; +} +static inline bool cpu_mitigations_auto_nosmt(void) +{ + return false; +} +#endif #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index afda5f24d3dd..20f7e98ee8af 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -241,6 +241,12 @@ 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); + +DECLARE_PER_CPU(unsigned long, cpufreq_pressure); +static inline unsigned long cpufreq_get_pressure(int cpu) +{ + return READ_ONCE(per_cpu(cpufreq_pressure, cpu)); +} #else static inline unsigned int cpufreq_get(unsigned int cpu) { @@ -263,6 +269,11 @@ static inline bool cpufreq_supports_freq_invariance(void) return false; } static inline void disable_cpufreq(void) { } +static inline void cpufreq_update_limits(unsigned int cpu) { } +static inline unsigned long cpufreq_get_pressure(int cpu) +{ + return 0; +} #endif #ifdef CONFIG_CPU_FREQ_STAT @@ -568,9 +579,7 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, /* * The polling frequency depends on the capability of the processor. Default - * polling frequency is 1000 times the transition latency of the processor. The - * ondemand governor will work on any processor with transition latency <= 10ms, - * using appropriate sampling rate. + * polling frequency is 1000 times the transition latency of the processor. */ #define LATENCY_MULTIPLIER (1000) @@ -694,26 +703,6 @@ struct cpufreq_frequency_table { * order */ }; -#if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP) -int dev_pm_opp_init_cpufreq_table(struct device *dev, - struct cpufreq_frequency_table **table); -void dev_pm_opp_free_cpufreq_table(struct device *dev, - struct cpufreq_frequency_table **table); -#else -static inline int dev_pm_opp_init_cpufreq_table(struct device *dev, - struct cpufreq_frequency_table - **table) -{ - return -EINVAL; -} - -static inline void dev_pm_opp_free_cpufreq_table(struct device *dev, - struct cpufreq_frequency_table - **table) -{ -} -#endif - /* * cpufreq_for_each_entry - iterate over a cpufreq_frequency_table * @pos: the cpufreq_frequency_table * to use as a loop cursor. @@ -1021,6 +1010,18 @@ static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy, efficiencies); } +static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy, int idx) +{ + unsigned int freq; + + if (idx < 0) + return false; + + freq = policy->freq_table[idx].frequency; + + return freq == clamp_val(freq, policy->min, policy->max); +} + static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) @@ -1054,7 +1055,8 @@ retry: return 0; } - if (idx < 0 && efficiencies) { + /* Limit frequency index to honor policy->min/max */ + if (!cpufreq_is_in_limits(policy, idx) && efficiencies) { efficiencies = false; goto retry; } @@ -1149,8 +1151,7 @@ static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_ if (ret < 0) continue; - if (pargs->np == args.np && pargs->args_count == args.args_count && - !memcmp(pargs->args, args.args, sizeof(args.args[0]) * args.args_count)) + if (of_phandle_args_equal(pargs, &args)) cpumask_set_cpu(cpu, cpumask); of_node_put(args.np); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 35e78ddb2b37..7a5785f405b6 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -146,6 +146,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_MIPS_GIC_STARTING, CPUHP_AP_IRQ_LOONGARCH_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, + CPUHP_AP_IRQ_RISCV_IMSIC_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1c29947db848..e8c412ee6400 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -188,6 +188,23 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask } /** + * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 + * @srcp1: the first input + * @srcp2: the second input + * @srcp3: the third input + * + * Return: >= nr_cpu_ids if no cpus set in all. + */ +static inline +unsigned int cpumask_first_and_and(const struct cpumask *srcp1, + const struct cpumask *srcp2, + const struct cpumask *srcp3) +{ + return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + cpumask_bits(srcp3), small_cpumask_bits); +} + +/** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * @@ -389,6 +406,29 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) } /** + * cpumask_any_and_but - pick a "random" cpu from *mask1 & *mask2, but not this one. + * @mask1: the first input cpumask + * @mask2: the second input cpumask + * @cpu: the cpu to ignore + * + * Returns >= nr_cpu_ids if no cpus set. + */ +static inline +unsigned int cpumask_any_and_but(const struct cpumask *mask1, + const struct cpumask *mask2, + unsigned int cpu) +{ + unsigned int i; + + cpumask_check(cpu); + i = cpumask_first_and(mask1, mask2); + if (i != cpu) + return i; + + return cpumask_next_and(cpu, mask1, mask2); +} + +/** * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 @@ -853,7 +893,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) */ static inline unsigned int cpumask_size(void) { - return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long); + return bitmap_size(large_cpumask_bits); } /* diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 9eaeaafe0cad..d33352c2e386 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -5,129 +5,58 @@ #include <linux/linkage.h> #include <linux/elfcore.h> #include <linux/elf.h> -#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION -#include <asm/crash_core.h> -#endif -/* Location of a reserved region to hold the crash kernel. - */ -extern struct resource crashk_res; -extern struct resource crashk_low_res; +struct kimage; + +struct crash_mem { + unsigned int max_nr_ranges; + unsigned int nr_ranges; + struct range ranges[] __counted_by(max_nr_ranges); +}; -#define CRASH_CORE_NOTE_NAME "CORE" -#define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) -#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4) -#define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4) +#ifdef CONFIG_CRASH_DUMP +int crash_shrink_memory(unsigned long new_size); +ssize_t crash_get_memory_size(void); + +#ifndef arch_kexec_protect_crashkres /* - * The per-cpu notes area is a list of notes terminated by a "NULL" - * note header. For kdump, the code in vmcore.c runs in the context - * of the second kernel to combine them into one note. + * Protection mechanism for crashkernel reserved memory after + * the kdump kernel is loaded. + * + * Provide an empty default implementation here -- architecture + * code may override this */ -#define CRASH_CORE_NOTE_BYTES ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ - CRASH_CORE_NOTE_NAME_BYTES + \ - CRASH_CORE_NOTE_DESC_BYTES) - -#define VMCOREINFO_BYTES PAGE_SIZE -#define VMCOREINFO_NOTE_NAME "VMCOREINFO" -#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) -#define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ - VMCOREINFO_NOTE_NAME_BYTES + \ - VMCOREINFO_BYTES) - -typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4]; -/* Per cpu memory for storing cpu states in case of system crash. */ -extern note_buf_t __percpu *crash_notes; - -void crash_update_vmcoreinfo_safecopy(void *ptr); -void crash_save_vmcoreinfo(void); -void arch_crash_save_vmcoreinfo(void); -__printf(1, 2) -void vmcoreinfo_append_str(const char *fmt, ...); -phys_addr_t paddr_vmcoreinfo_note(void); - -#define VMCOREINFO_OSRELEASE(value) \ - vmcoreinfo_append_str("OSRELEASE=%s\n", value) -#define VMCOREINFO_BUILD_ID() \ - ({ \ - static_assert(sizeof(vmlinux_build_id) == 20); \ - vmcoreinfo_append_str("BUILD-ID=%20phN\n", vmlinux_build_id); \ - }) - -#define VMCOREINFO_PAGESIZE(value) \ - vmcoreinfo_append_str("PAGESIZE=%ld\n", value) -#define VMCOREINFO_SYMBOL(name) \ - vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) -#define VMCOREINFO_SYMBOL_ARRAY(name) \ - vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)name) -#define VMCOREINFO_SIZE(name) \ - vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ - (unsigned long)sizeof(name)) -#define VMCOREINFO_STRUCT_SIZE(name) \ - vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ - (unsigned long)sizeof(struct name)) -#define VMCOREINFO_OFFSET(name, field) \ - vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ - (unsigned long)offsetof(struct name, field)) -#define VMCOREINFO_TYPE_OFFSET(name, field) \ - vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ - (unsigned long)offsetof(name, field)) -#define VMCOREINFO_LENGTH(name, value) \ - vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) -#define VMCOREINFO_NUMBER(name) \ - vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) -#define VMCOREINFO_CONFIG(name) \ - vmcoreinfo_append_str("CONFIG_%s=y\n", #name) - -extern unsigned char *vmcoreinfo_data; -extern size_t vmcoreinfo_size; -extern u32 *vmcoreinfo_note; - -Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, - void *data, size_t data_len); -void final_note(Elf_Word *buf); - -int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, - unsigned long long *crash_size, unsigned long long *crash_base, - unsigned long long *low_size, bool *high); - -#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION -#ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE -#define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) +static inline void arch_kexec_protect_crashkres(void) { } #endif -#ifndef CRASH_ALIGN -#define CRASH_ALIGN SZ_2M + +#ifndef arch_kexec_unprotect_crashkres +static inline void arch_kexec_unprotect_crashkres(void) { } #endif -#ifndef CRASH_ADDR_LOW_MAX -#define CRASH_ADDR_LOW_MAX SZ_4G + + + +#ifndef arch_crash_handle_hotplug_event +static inline void arch_crash_handle_hotplug_event(struct kimage *image) { } #endif -#ifndef CRASH_ADDR_HIGH_MAX -#define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM() + +int crash_check_update_elfcorehdr(void); + +#ifndef crash_hotplug_cpu_support +static inline int crash_hotplug_cpu_support(void) { return 0; } +#endif + +#ifndef crash_hotplug_memory_support +static inline int crash_hotplug_memory_support(void) { return 0; } #endif -void __init reserve_crashkernel_generic(char *cmdline, - unsigned long long crash_size, - unsigned long long crash_base, - unsigned long long crash_low_size, - bool high); -#else -static inline void __init reserve_crashkernel_generic(char *cmdline, - unsigned long long crash_size, - unsigned long long crash_base, - unsigned long long crash_low_size, - bool high) -{} +#ifndef crash_get_elfcorehdr_size +static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; } #endif /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 -struct crash_mem { - unsigned int max_nr_ranges; - unsigned int nr_ranges; - struct range ranges[] __counted_by(max_nr_ranges); -}; - extern int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mstart, unsigned long long mend); @@ -144,4 +73,23 @@ struct kexec_segment; #define KEXEC_CRASH_HP_REMOVE_MEMORY 4 #define KEXEC_CRASH_HP_INVALID_CPU -1U +extern void __crash_kexec(struct pt_regs *regs); +extern void crash_kexec(struct pt_regs *regs); +int kexec_should_crash(struct task_struct *p); +int kexec_crash_loaded(void); +void crash_save_cpu(struct pt_regs *regs, int cpu); +extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); + +#else /* !CONFIG_CRASH_DUMP*/ +struct pt_regs; +struct task_struct; +struct kimage; +static inline void __crash_kexec(struct pt_regs *regs) { } +static inline void crash_kexec(struct pt_regs *regs) { } +static inline int kexec_should_crash(struct task_struct *p) { return 0; } +static inline int kexec_crash_loaded(void) { return 0; } +static inline void crash_save_cpu(struct pt_regs *regs, int cpu) {}; +static inline int kimage_crash_copy_vmcoreinfo(struct kimage *image) { return 0; }; +#endif /* CONFIG_CRASH_DUMP*/ + #endif /* LINUX_CRASH_CORE_H */ diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h new file mode 100644 index 000000000000..5a9df944fb80 --- /dev/null +++ b/include/linux/crash_reserve.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_CRASH_RESERVE_H +#define LINUX_CRASH_RESERVE_H + +#include <linux/linkage.h> +#include <linux/elfcore.h> +#include <linux/elf.h> +#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +#include <asm/crash_reserve.h> +#endif + +/* Location of a reserved region to hold the crash kernel. + */ +extern struct resource crashk_res; +extern struct resource crashk_low_res; + +int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base, + unsigned long long *low_size, bool *high); + +#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +#ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE +#define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) +#endif +#ifndef CRASH_ALIGN +#define CRASH_ALIGN SZ_2M +#endif +#ifndef CRASH_ADDR_LOW_MAX +#define CRASH_ADDR_LOW_MAX SZ_4G +#endif +#ifndef CRASH_ADDR_HIGH_MAX +#define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM() +#endif + +void __init reserve_crashkernel_generic(char *cmdline, + unsigned long long crash_size, + unsigned long long crash_base, + unsigned long long crash_low_size, + bool high); +#else +static inline void __init reserve_crashkernel_generic(char *cmdline, + unsigned long long crash_size, + unsigned long long crash_base, + unsigned long long crash_low_size, + bool high) +{} +#endif +#endif /* LINUX_CRASH_RESERVE_H */ diff --git a/include/linux/damon.h b/include/linux/damon.h index 5881e4ac30be..886d07294f4e 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -127,18 +127,60 @@ enum damos_action { }; /** + * enum damos_quota_goal_metric - Represents the metric to be used as the goal + * + * @DAMOS_QUOTA_USER_INPUT: User-input value. + * @DAMOS_QUOTA_SOME_MEM_PSI_US: System level some memory PSI in us. + * @NR_DAMOS_QUOTA_GOAL_METRICS: Number of DAMOS quota goal metrics. + * + * Metrics equal to larger than @NR_DAMOS_QUOTA_GOAL_METRICS are unsupported. + */ +enum damos_quota_goal_metric { + DAMOS_QUOTA_USER_INPUT, + DAMOS_QUOTA_SOME_MEM_PSI_US, + NR_DAMOS_QUOTA_GOAL_METRICS, +}; + +/** + * struct damos_quota_goal - DAMOS scheme quota auto-tuning goal. + * @metric: Metric to be used for representing the goal. + * @target_value: Target value of @metric to achieve with the tuning. + * @current_value: Current value of @metric. + * @last_psi_total: Last measured total PSI + * @list: List head for siblings. + * + * Data structure for getting the current score of the quota tuning goal. The + * score is calculated by how close @current_value and @target_value are. Then + * the score is entered to DAMON's internal feedback loop mechanism to get the + * auto-tuned quota. + * + * If @metric is DAMOS_QUOTA_USER_INPUT, @current_value should be manually + * entered by the user, probably inside the kdamond callbacks. Otherwise, + * DAMON sets @current_value with self-measured value of @metric. + */ +struct damos_quota_goal { + enum damos_quota_goal_metric metric; + unsigned long target_value; + unsigned long current_value; + /* metric-dependent fields */ + union { + u64 last_psi_total; + }; + struct list_head list; +}; + +/** * struct damos_quota - Controls the aggressiveness of the given scheme. + * @reset_interval: Charge reset interval in milliseconds. * @ms: Maximum milliseconds that the scheme can use. * @sz: Maximum bytes of memory that the action can be applied. - * @reset_interval: Charge reset interval in milliseconds. + * @goals: Head of quota tuning goals (&damos_quota_goal) list. + * @esz: Effective size quota in bytes. * * @weight_sz: Weight of the region's size for prioritization. * @weight_nr_accesses: Weight of the region's nr_accesses for prioritization. * @weight_age: Weight of the region's age for prioritization. * - * @get_score: Feedback function for self-tuning quota. - * @get_score_arg: Parameter for @get_score - * * To avoid consuming too much CPU time or IO resources for applying the * &struct damos->action to large memory, DAMON allows users to set time and/or * size quotas. The quotas can be set by writing non-zero values to &ms and @@ -151,42 +193,35 @@ enum damos_action { * throughput of the scheme's action. DAMON then compares it against &sz and * uses smaller one as the effective quota. * + * If @goals is not empt, DAMON calculates yet another size quota based on the + * goals using its internal feedback loop algorithm, for every @reset_interval. + * Then, if the new size quota is smaller than the effective quota, it uses the + * new size quota as the effective quota. + * + * The resulting effective size quota in bytes is set to @esz. + * * For selecting regions within the quota, DAMON prioritizes current scheme's * target memory regions using the &struct damon_operations->get_scheme_score. * You could customize the prioritization logic by setting &weight_sz, * &weight_nr_accesses, and &weight_age, because monitoring operations are * encouraged to respect those. - * - * If @get_score function pointer is set, DAMON calls it back with - * @get_score_arg and get the return value of it for every @reset_interval. - * Then, DAMON adjusts the effective quota using the return value as a feedback - * score to the current quota, using its internal feedback loop algorithm. - * - * The feedback loop algorithem assumes the quota input and the feedback score - * output are in a positive proportional relationship, and the goal of the - * tuning is getting the feedback screo value of 10,000. If @ms and/or @sz are - * set together, those work as a hard limit quota. If neither @ms nor @sz are - * set, the mechanism starts from the quota of one byte. */ struct damos_quota { + unsigned long reset_interval; unsigned long ms; unsigned long sz; - unsigned long reset_interval; + struct list_head goals; + unsigned long esz; unsigned int weight_sz; unsigned int weight_nr_accesses; unsigned int weight_age; - unsigned long (*get_score)(void *arg); - void *get_score_arg; - /* private: */ /* For throughput estimation */ unsigned long total_charged_sz; unsigned long total_charged_ns; - unsigned long esz; /* Effective size quota in bytes */ - /* For charging the quota */ unsigned long charged_sz; unsigned long charged_from; @@ -640,6 +675,12 @@ static inline unsigned long damon_sz_region(struct damon_region *r) #define damon_for_each_scheme_safe(s, next, ctx) \ list_for_each_entry_safe(s, next, &(ctx)->schemes, list) +#define damos_for_each_quota_goal(goal, quota) \ + list_for_each_entry(goal, "a->goals, list) + +#define damos_for_each_quota_goal_safe(goal, next, quota) \ + list_for_each_entry_safe(goal, next, &(quota)->goals, list) + #define damos_for_each_filter(f, scheme) \ list_for_each_entry(f, &(scheme)->filters, list) @@ -673,6 +714,12 @@ struct damos_filter *damos_new_filter(enum damos_filter_type type, void damos_add_filter(struct damos *s, struct damos_filter *f); void damos_destroy_filter(struct damos_filter *f); +struct damos_quota_goal *damos_new_quota_goal( + enum damos_quota_goal_metric metric, + unsigned long target_value); +void damos_add_quota_goal(struct damos_quota *q, struct damos_quota_goal *g); +void damos_destroy_quota_goal(struct damos_quota_goal *goal); + struct damos *damon_new_scheme(struct damos_access_pattern *pattern, enum damos_action action, unsigned long apply_interval_us, diff --git a/include/linux/dax.h b/include/linux/dax.h index b463502b16e1..9d3e3327af4c 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -63,6 +63,8 @@ void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool dax_synchronous(struct dax_device *dax_dev); +void set_dax_nocache(struct dax_device *dax_dev); +void set_dax_nomc(struct dax_device *dax_dev); void set_dax_synchronous(struct dax_device *dax_dev); size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); @@ -86,11 +88,7 @@ static inline void *dax_holder(struct dax_device *dax_dev) static inline struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) { - /* - * Callers should check IS_ENABLED(CONFIG_DAX) to know if this - * NULL is an error or expected. - */ - return NULL; + return ERR_PTR(-EOPNOTSUPP); } static inline void put_dax(struct dax_device *dax_dev) { @@ -109,6 +107,12 @@ static inline bool dax_synchronous(struct dax_device *dax_dev) { return true; } +static inline void set_dax_nocache(struct dax_device *dax_dev) +{ +} +static inline void set_dax_nomc(struct dax_device *dax_dev) +{ +} static inline void set_dax_synchronous(struct dax_device *dax_dev) { } @@ -124,9 +128,6 @@ static inline size_t dax_recovery_write(struct dax_device *dax_dev, } #endif -void set_dax_nocache(struct dax_device *dax_dev); -void set_dax_nomc(struct dax_device *dax_dev); - struct writeback_control; #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); diff --git a/include/linux/devcoredump.h b/include/linux/devcoredump.h index c008169ed2c6..c8f7eb6cc191 100644 --- a/include/linux/devcoredump.h +++ b/include/linux/devcoredump.h @@ -63,6 +63,8 @@ void dev_coredumpm(struct device *dev, struct module *owner, void dev_coredumpsg(struct device *dev, struct scatterlist *table, size_t datalen, gfp_t gfp); + +void dev_coredump_put(struct device *dev); #else static inline void dev_coredumpv(struct device *dev, void *data, size_t datalen, gfp_t gfp) @@ -85,6 +87,9 @@ static inline void dev_coredumpsg(struct device *dev, struct scatterlist *table, { _devcd_free_sgtable(table); } +static inline void dev_coredump_put(struct device *dev) +{ +} #endif /* CONFIG_DEV_COREDUMP */ #endif /* __DEVCOREDUMP_H */ diff --git a/include/linux/device.h b/include/linux/device.h index 97c4b046c09d..b9f5464f44ed 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1247,6 +1247,7 @@ void device_link_del(struct device_link *link); 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); +void device_link_wait_removal(void); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ diff --git a/include/linux/dio.h b/include/linux/dio.h index 5abd07361eb5..2b5923909f96 100644 --- a/include/linux/dio.h +++ b/include/linux/dio.h @@ -68,7 +68,7 @@ struct dio_bus { }; extern struct dio_bus dio_bus; /* Single DIO bus */ -extern struct bus_type dio_bus_type; +extern const struct bus_type dio_bus_type; /* * DIO device IDs diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 75e7d8cbb532..d1503b815a78 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -64,6 +64,9 @@ void dm_bufio_set_sector_offset(struct dm_bufio_client *c, sector_t start); void *dm_bufio_read(struct dm_bufio_client *c, sector_t block, struct dm_buffer **bp); +void *dm_bufio_read_with_ioprio(struct dm_bufio_client *c, sector_t block, + struct dm_buffer **bp, unsigned short ioprio); + /* * Like dm_bufio_read, but return buffer from cache, don't read * it. If the buffer is not in the cache, return NULL. @@ -86,6 +89,10 @@ void *dm_bufio_new(struct dm_bufio_client *c, sector_t block, void dm_bufio_prefetch(struct dm_bufio_client *c, sector_t block, unsigned int n_blocks); +void dm_bufio_prefetch_with_ioprio(struct dm_bufio_client *c, + sector_t block, unsigned int n_blocks, + unsigned short ioprio); + /* * Release a reference obtained with dm_bufio_{read,get,new}. The data * pointer and dm_buffer pointer is no longer valid after this call. diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index 7595142f3fc5..7b2968612b7e 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -80,7 +80,8 @@ void dm_io_client_destroy(struct dm_io_client *client); * error occurred doing io to the corresponding region. */ int dm_io(struct dm_io_request *io_req, unsigned int num_regions, - struct dm_io_region *region, unsigned int long *sync_error_bits); + struct dm_io_region *region, unsigned int long *sync_error_bits, + unsigned short ioprio); #endif /* __KERNEL__ */ #endif /* _LINUX_DM_IO_H */ diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 8ff4add71f88..36216d28d8bd 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -370,8 +370,10 @@ struct dma_buf { */ struct module *owner; +#if IS_ENABLED(CONFIG_DEBUG_FS) /** @list_node: node for dma_buf accounting and debugging. */ struct list_head list_node; +#endif /** @priv: exporter specific private data for this buffer object. */ void *priv; diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h index e443be4d3b4b..1e491c5dcac2 100644 --- a/include/linux/dma/k3-udma-glue.h +++ b/include/linux/dma/k3-udma-glue.h @@ -26,6 +26,11 @@ struct k3_udma_glue_tx_channel; struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev, const char *name, struct k3_udma_glue_tx_channel_cfg *cfg); +struct k3_udma_glue_tx_channel * +k3_udma_glue_request_tx_chn_for_thread_id(struct device *dev, + struct k3_udma_glue_tx_channel_cfg *cfg, + struct device_node *udmax_np, u32 thread_id); + void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn); int k3_udma_glue_push_tx_chn(struct k3_udma_glue_tx_channel *tx_chn, struct cppi5_host_desc_t *desc_tx, @@ -109,6 +114,11 @@ struct k3_udma_glue_rx_channel *k3_udma_glue_request_rx_chn( const char *name, struct k3_udma_glue_rx_channel_cfg *cfg); +struct k3_udma_glue_rx_channel * +k3_udma_glue_request_remote_rx_chn_for_thread_id(struct device *dev, + struct k3_udma_glue_rx_channel_cfg *cfg, + struct device_node *udmax_np, u32 thread_id); + void k3_udma_glue_release_rx_chn(struct k3_udma_glue_rx_channel *rx_chn); int k3_udma_glue_enable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn); void k3_udma_glue_disable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn); diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 5693a4be0d9a..281298e77a15 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -50,6 +50,9 @@ struct dql { unsigned int adj_limit; /* limit + num_completed */ unsigned int last_obj_cnt; /* Count at last queuing */ + /* Stall threshold (in jiffies), defined by user */ + unsigned short stall_thrs; + unsigned long history_head; /* top 58 bits of jiffies */ /* stall entries, a bit per entry */ unsigned long history[DQL_HIST_LEN]; @@ -71,8 +74,6 @@ struct dql { unsigned int min_limit; /* Minimum limit */ unsigned int slack_hold_time; /* Time to measure slack */ - /* Stall threshold (in jiffies), defined by user */ - unsigned short stall_thrs; /* Longest stall detected, reported to user */ unsigned short stall_max; unsigned long last_reap; /* Last reap (in jiffies) */ @@ -83,27 +84,11 @@ struct dql { #define DQL_MAX_OBJECT (UINT_MAX / 16) #define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT) -/* - * Record number of objects queued. Assumes that caller has already checked - * availability in the queue with dql_avail. - */ -static inline void dql_queued(struct dql *dql, unsigned int count) +/* Populate the bitmap to be processed later in dql_check_stall() */ +static inline void dql_queue_stall(struct dql *dql) { unsigned long map, now, now_hi, i; - BUG_ON(count > DQL_MAX_OBJECT); - - dql->last_obj_cnt = count; - - /* We want to force a write first, so that cpu do not attempt - * to get cache line containing last_obj_cnt, num_queued, adj_limit - * in Shared state, but directly does a Request For Ownership - * It is only a hint, we use barrier() only. - */ - barrier(); - - dql->num_queued += count; - now = jiffies; now_hi = now / BITS_PER_LONG; @@ -133,6 +118,31 @@ static inline void dql_queued(struct dql *dql, unsigned int count) WRITE_ONCE(DQL_HIST_ENT(dql, now_hi), map | BIT_MASK(now)); } +/* + * Record number of objects queued. Assumes that caller has already checked + * availability in the queue with dql_avail. + */ +static inline void dql_queued(struct dql *dql, unsigned int count) +{ + if (WARN_ON_ONCE(count > DQL_MAX_OBJECT)) + return; + + dql->last_obj_cnt = count; + + /* We want to force a write first, so that cpu do not attempt + * to get cache line containing last_obj_cnt, num_queued, adj_limit + * in Shared state, but directly does a Request For Ownership + * It is only a hint, we use barrier() only. + */ + barrier(); + + dql->num_queued += count; + + /* Only populate stall information if the threshold is set */ + if (READ_ONCE(dql->stall_thrs)) + dql_queue_stall(dql); +} + /* Returns how many objects can be queued, < 0 indicates over limit. */ static inline int dql_avail(const struct dql *dql) { diff --git a/include/linux/efi.h b/include/linux/efi.h index c74f47711f0b..418e555459da 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -386,6 +386,7 @@ void efi_native_runtime_setup(void); #define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define APPLE_PROPERTIES_PROTOCOL_GUID EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb, 0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0) #define EFI_TCG2_PROTOCOL_GUID EFI_GUID(0x607f766c, 0x7455, 0x42be, 0x93, 0x0b, 0xe4, 0xd7, 0x6d, 0xb2, 0x72, 0x0f) +#define EFI_TCG2_FINAL_EVENTS_TABLE_GUID EFI_GUID(0x1e2ed096, 0x30e2, 0x4254, 0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25) #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) @@ -400,6 +401,8 @@ void efi_native_runtime_setup(void); #define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) #define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) #define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) +#define EFI_CC_MEASUREMENT_PROTOCOL_GUID EFI_GUID(0x96751a3d, 0x72f4, 0x41a6, 0xa7, 0x94, 0xed, 0x5d, 0x0e, 0x67, 0xae, 0x6b) +#define EFI_CC_FINAL_EVENTS_TABLE_GUID EFI_GUID(0xdd4a4648, 0x2de7, 0x4665, 0x96, 0x4d, 0x21, 0xd9, 0xef, 0x5f, 0xb4, 0x46) /* * This GUID is used to pass to the kernel proper the struct screen_info @@ -411,7 +414,6 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_LOADER_ENTRY_GUID EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf, 0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f) #define LINUX_EFI_RANDOM_SEED_TABLE_GUID EFI_GUID(0x1ce1e5bc, 0x7ceb, 0x42f2, 0x81, 0xe5, 0x8a, 0xad, 0xf1, 0x80, 0xf5, 0x7b) #define LINUX_EFI_TPM_EVENT_LOG_GUID EFI_GUID(0xb7799cb0, 0xeca2, 0x4943, 0x96, 0x67, 0x1f, 0xae, 0x07, 0xb7, 0x47, 0xfa) -#define LINUX_EFI_TPM_FINAL_LOG_GUID EFI_GUID(0x1e2ed096, 0x30e2, 0x4254, 0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25) #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) #define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68) #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) @@ -692,6 +694,11 @@ extern struct efi { extern struct mm_struct efi_mm; +static inline bool mm_is_efi(struct mm_struct *mm) +{ + return IS_ENABLED(CONFIG_EFI) && mm == &efi_mm; +} + static inline int efi_guidcmp (efi_guid_t left, efi_guid_t right) { @@ -1065,12 +1072,11 @@ static inline u64 efivar_reserved_space(void) { return 0; } #endif /* - * The maximum size of VariableName + Data = 1024 - * Therefore, it's reasonable to save that much - * space in each part of the structure, - * and we use a page for reading/writing. + * There is no actual upper limit specified for the variable name size. + * + * This limit exists only for practical purposes, since name conversions + * are bounds-checked and name data is occasionally stored in-line. */ - #define EFI_VAR_NAME_LEN 1024 int efivars_register(struct efivars *efivars, diff --git a/include/linux/einj-cxl.h b/include/linux/einj-cxl.h new file mode 100644 index 000000000000..624ff6ff41f9 --- /dev/null +++ b/include/linux/einj-cxl.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * CXL protocol Error INJection support. + * + * Copyright (c) 2023 Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Ben Cheatham <benjamin.cheatham@amd.com> + */ +#ifndef EINJ_CXL_H +#define EINJ_CXL_H + +#include <linux/errno.h> +#include <linux/types.h> + +struct pci_dev; +struct seq_file; + +#if IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL) +int einj_cxl_available_error_type_show(struct seq_file *m, void *v); +int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type); +int einj_cxl_inject_rch_error(u64 rcrb, u64 type); +bool einj_cxl_is_initialized(void); +#else /* !IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL) */ +static inline int einj_cxl_available_error_type_show(struct seq_file *m, + void *v) +{ + return -ENXIO; +} + +static inline int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type) +{ + return -ENXIO; +} + +static inline int einj_cxl_inject_rch_error(u64 rcrb, u64 type) +{ + return -ENXIO; +} + +static inline bool einj_cxl_is_initialized(void) { return false; } +#endif /* CONFIG_ACPI_APEI_EINJ_CXL */ + +#endif /* EINJ_CXL_H */ diff --git a/include/linux/elf.h b/include/linux/elf.h index c9a46c4e183b..5c402788da19 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -65,7 +65,7 @@ extern Elf64_Dyn _DYNAMIC []; struct file; struct coredump_params; -#ifndef ARCH_HAVE_EXTRA_ELF_NOTES +#ifndef CONFIG_ARCH_HAVE_EXTRA_ELF_NOTES static inline int elf_coredump_extra_notes_size(void) { return 0; } static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) { return 0; } #else diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 88d91e087471..1ff52020cf75 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -5,6 +5,7 @@ #include <linux/device.h> #include <linux/jump_label.h> #include <linux/kobject.h> +#include <linux/kref.h> #include <linux/rcupdate.h> #include <linux/sched/cpufreq.h> #include <linux/sched/topology.h> @@ -12,6 +13,7 @@ /** * struct em_perf_state - Performance state of a performance domain + * @performance: CPU performance (capacity) at a given frequency * @frequency: The frequency in KHz, for consistency with CPUFreq * @power: The power consumed at this level (by 1 CPU or by a registered * device). It can be a total power: static and dynamic. @@ -20,6 +22,7 @@ * @flags: see "em_perf_state flags" description below. */ struct em_perf_state { + unsigned long performance; unsigned long frequency; unsigned long power; unsigned long cost; @@ -37,8 +40,20 @@ struct em_perf_state { #define EM_PERF_STATE_INEFFICIENT BIT(0) /** + * struct em_perf_table - Performance states table + * @rcu: RCU used for safe access and destruction + * @kref: Reference counter to track the users + * @state: List of performance states, in ascending order + */ +struct em_perf_table { + struct rcu_head rcu; + struct kref kref; + struct em_perf_state state[]; +}; + +/** * struct em_perf_domain - Performance domain - * @table: List of performance states, in ascending order + * @em_table: Pointer to the runtime modifiable em_perf_table * @nr_perf_states: Number of performance states * @flags: See "em_perf_domain flags" * @cpus: Cpumask covering the CPUs of the domain. It's here @@ -53,7 +68,7 @@ struct em_perf_state { * field is unused. */ struct em_perf_domain { - struct em_perf_state *table; + struct em_perf_table __rcu *em_table; int nr_perf_states; unsigned long flags; unsigned long cpus[]; @@ -98,27 +113,6 @@ struct em_perf_domain { #define EM_MAX_NUM_CPUS 16 #endif -/* - * To avoid an overflow on 32bit machines while calculating the energy - * use a different order in the operation. First divide by the 'cpu_scale' - * which would reduce big value stored in the 'cost' field, then multiply by - * the 'sum_util'. This would allow to handle existing platforms, which have - * e.g. power ~1.3 Watt at max freq, so the 'cost' value > 1mln micro-Watts. - * In such scenario, where there are 4 CPUs in the Perf. Domain the 'sum_util' - * could be 4096, then multiplication: 'cost' * 'sum_util' would overflow. - * This reordering of operations has some limitations, we lose small - * precision in the estimation (comparing to 64bit platform w/o reordering). - * - * We are safe on 64bit machine. - */ -#ifdef CONFIG_64BIT -#define em_estimate_energy(cost, sum_util, scale_cpu) \ - (((cost) * (sum_util)) / (scale_cpu)) -#else -#define em_estimate_energy(cost, sum_util, scale_cpu) \ - (((cost) / (scale_cpu)) * (sum_util)) -#endif - struct em_data_callback { /** * active_power() - Provide power at the next performance state of @@ -168,40 +162,49 @@ struct em_data_callback { struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); +int em_dev_update_perf_domain(struct device *dev, + struct em_perf_table __rcu *new_table); int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span, bool microwatts); void em_dev_unregister_perf_domain(struct device *dev); +struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd); +void em_table_free(struct em_perf_table __rcu *table); +int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, + int nr_states); +int em_dev_update_chip_binning(struct device *dev); /** * em_pd_get_efficient_state() - Get an efficient performance state from the EM - * @pd : Performance domain for which we want an efficient frequency - * @freq : Frequency to map with the EM + * @table: List of performance states, in ascending order + * @nr_perf_states: Number of performance states + * @max_util: Max utilization to map with the EM + * @pd_flags: Performance Domain flags * * It is called from the scheduler code quite frequently and as a consequence * doesn't implement any check. * - * Return: An efficient performance state, high enough to meet @freq + * Return: An efficient performance state id, high enough to meet @max_util * requirement. */ -static inline -struct em_perf_state *em_pd_get_efficient_state(struct em_perf_domain *pd, - unsigned long freq) +static inline int +em_pd_get_efficient_state(struct em_perf_state *table, int nr_perf_states, + unsigned long max_util, unsigned long pd_flags) { struct em_perf_state *ps; int i; - for (i = 0; i < pd->nr_perf_states; i++) { - ps = &pd->table[i]; - if (ps->frequency >= freq) { - if (pd->flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES && + for (i = 0; i < nr_perf_states; i++) { + ps = &table[i]; + if (ps->performance >= max_util) { + if (pd_flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES && ps->flags & EM_PERF_STATE_INEFFICIENT) continue; - break; + return i; } } - return ps; + return nr_perf_states - 1; } /** @@ -224,9 +227,13 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util, unsigned long allowed_cpu_cap) { - unsigned long freq, ref_freq, scale_cpu; + struct em_perf_table *em_table; struct em_perf_state *ps; - int cpu; + int i; + +#ifdef CONFIG_SCHED_DEBUG + WARN_ONCE(!rcu_read_lock_held(), "EM: rcu read lock needed\n"); +#endif if (!sum_util) return 0; @@ -234,31 +241,29 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, /* * In order to predict the performance state, map the utilization of * the most utilized CPU of the performance domain to a requested - * frequency, like schedutil. Take also into account that the real - * frequency might be set lower (due to thermal capping). Thus, clamp + * performance, like schedutil. Take also into account that the real + * performance might be set lower (due to thermal capping). Thus, clamp * max utilization to the allowed CPU capacity before calculating - * effective frequency. + * effective performance. */ - cpu = cpumask_first(to_cpumask(pd->cpus)); - scale_cpu = arch_scale_cpu_capacity(cpu); - ref_freq = arch_scale_freq_ref(cpu); - max_util = min(max_util, allowed_cpu_cap); - freq = map_util_freq(max_util, ref_freq, scale_cpu); /* * Find the lowest performance state of the Energy Model above the - * requested frequency. + * requested performance. */ - ps = em_pd_get_efficient_state(pd, freq); + em_table = rcu_dereference(pd->em_table); + i = em_pd_get_efficient_state(em_table->state, pd->nr_perf_states, + max_util, pd->flags); + ps = &em_table->state[i]; /* - * The capacity of a CPU in the domain at the performance state (ps) - * can be computed as: + * The performance (capacity) of a CPU in the domain at the performance + * state (ps) can be computed as: * - * ps->freq * scale_cpu - * ps->cap = -------------------- (1) - * cpu_max_freq + * ps->freq * scale_cpu + * ps->performance = -------------------- (1) + * cpu_max_freq * * So, ignoring the costs of idle states (which are not available in * the EM), the energy consumed by this CPU at that performance state @@ -266,9 +271,10 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * * ps->power * cpu_util * cpu_nrg = -------------------- (2) - * ps->cap + * ps->performance * - * since 'cpu_util / ps->cap' represents its percentage of busy time. + * since 'cpu_util / ps->performance' represents its percentage of busy + * time. * * NOTE: Although the result of this computation actually is in * units of power, it can be manipulated as an energy value @@ -278,9 +284,9 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product * of two terms: * - * ps->power * cpu_max_freq cpu_util - * cpu_nrg = ------------------------ * --------- (3) - * ps->freq scale_cpu + * ps->power * cpu_max_freq + * cpu_nrg = ------------------------ * cpu_util (3) + * ps->freq * scale_cpu * * The first term is static, and is stored in the em_perf_state struct * as 'ps->cost'. @@ -290,11 +296,9 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * total energy of the domain (which is the simple sum of the energy of * all of its CPUs) can be factorized as: * - * ps->cost * \Sum cpu_util - * pd_nrg = ------------------------ (4) - * scale_cpu + * pd_nrg = ps->cost * \Sum cpu_util (4) */ - return em_estimate_energy(ps->cost, sum_util, scale_cpu); + return ps->cost * sum_util; } /** @@ -309,6 +313,23 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) return pd->nr_perf_states; } +/** + * em_perf_state_from_pd() - Get the performance states table of perf. + * domain + * @pd : performance domain for which this must be done + * + * To use this function the rcu_read_lock() should be hold. After the usage + * of the performance states table is finished, the rcu_read_unlock() should + * be called. + * + * Return: the pointer to performance states table of the performance domain + */ +static inline +struct em_perf_state *em_perf_state_from_pd(struct em_perf_domain *pd) +{ + return rcu_dereference(pd->em_table)->state; +} + #else struct em_data_callback {}; #define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) { } @@ -343,6 +364,33 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) { return 0; } +static inline +struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd) +{ + return NULL; +} +static inline void em_table_free(struct em_perf_table __rcu *table) {} +static inline +int em_dev_update_perf_domain(struct device *dev, + struct em_perf_table __rcu *new_table) +{ + return -EINVAL; +} +static inline +struct em_perf_state *em_perf_state_from_pd(struct em_perf_domain *pd) +{ + return NULL; +} +static inline +int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, + int nr_states) +{ + return -EINVAL; +} +static inline int em_dev_update_chip_binning(struct device *dev) +{ + return -EINVAL; +} #endif #endif diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 224645f17c33..2ad1ffa4ccb9 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -71,6 +71,12 @@ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; #define eth_stp_addr eth_reserved_addr_base +static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) = +{ 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; + +static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) = +{ 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; + /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address @@ -430,18 +436,16 @@ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) { - u8 base[ETH_ALEN] = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; - return ether_addr_equal_masked(addr, base, mask); + return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask); } static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) { - u8 base[ETH_ALEN] = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; - return ether_addr_equal_masked(addr, base, mask); + return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask); } static inline bool ether_addr_is_ip_mcast(const u8 *addr) @@ -608,6 +612,31 @@ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, } /** + * eth_skb_pkt_type - Assign packet type if destination address does not match + * @skb: Assigned a packet type if address does not match @dev address + * @dev: Network device used to compare packet address against + * + * If the destination MAC address of the packet does not match the network + * device address, assign an appropriate packet type. + */ +static inline void eth_skb_pkt_type(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct ethhdr *eth = eth_hdr(skb); + + if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { + if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { + if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } else { + skb->pkt_type = PACKET_OTHERHOST; + } + } +} + +/** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad * diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9901e563f706..6fd9107d3cc0 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -480,6 +480,26 @@ struct ethtool_rmon_stats { ); }; +/** + * struct ethtool_ts_stats - HW timestamping statistics + * @pkts: Number of packets successfully timestamped by the hardware. + * @lost: Number of hardware timestamping requests where the timestamping + * information from the hardware never arrived for submission with + * the skb. + * @err: Number of arbitrary timestamp generation error events that the + * hardware encountered, exclusive of @lost statistics. Cases such + * as resource exhaustion, unavailability, firmware errors, and + * detected illogical timestamp values not submitted with the skb + * are inclusive to this counter. + */ +struct ethtool_ts_stats { + struct_group(tx_stats, + u64 pkts; + u64 lost; + u64 err; + ); +}; + #define ETH_MODULE_EEPROM_PAGE_LEN 128 #define ETH_MODULE_MAX_I2C_ADDRESS 0x7f @@ -755,7 +775,10 @@ struct ethtool_rxfh_param { * @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(). + * ethtool_op_get_ts_info(). Drivers must not zero statistics which they + * don't report. The stats structure is initialized to ETHTOOL_STAT_NOT_SET + * indicating driver does not report statistics. + * @get_ts_stats: Query the device hardware timestamping statistics. * @get_module_info: Get the size and type of the eeprom contained within * a plug-in module. * @get_module_eeprom: Get the eeprom information from the plug-in module @@ -898,6 +921,8 @@ struct ethtool_ops { struct ethtool_dump *, void *); int (*set_dump)(struct net_device *, struct ethtool_dump *); int (*get_ts_info)(struct net_device *, struct ethtool_ts_info *); + void (*get_ts_stats)(struct net_device *dev, + struct ethtool_ts_stats *ts_stats); int (*get_module_info)(struct net_device *, struct ethtool_modinfo *); int (*get_module_eeprom)(struct net_device *, diff --git a/include/linux/evm.h b/include/linux/evm.h index d48d6da32315..ddece4a6b25d 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -26,6 +26,8 @@ extern int evm_protected_xattr_if_enabled(const char *req_xattr_name); extern int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, int buffer_size, char type, bool canonical_fmt); +extern bool evm_metadata_changed(struct inode *inode, + struct inode *metadata_inode); #ifdef CONFIG_FS_POSIX_ACL extern int posix_xattr_acl(const char *xattrname); #else @@ -76,5 +78,11 @@ static inline int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, return -EOPNOTSUPP; } +static inline bool evm_metadata_changed(struct inode *inode, + struct inode *metadata_inode) +{ + return false; +} + #endif /* CONFIG_EVM */ #endif /* LINUX_EVM_H */ diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 053137a0fe45..a357287eac1e 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -27,6 +27,7 @@ #define F2FS_BYTES_TO_BLK(bytes) ((bytes) >> F2FS_BLKSIZE_BITS) #define F2FS_BLK_TO_BYTES(blk) ((blk) << F2FS_BLKSIZE_BITS) +#define F2FS_BLK_END_BYTES(blk) (F2FS_BLK_TO_BYTES(blk + 1) - 1) /* 0, 1(node nid), 2(meta nid) are reserved node id */ #define F2FS_RESERVED_NODE_NUM 3 @@ -40,12 +41,6 @@ #define F2FS_ENC_UTF8_12_1 1 -#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) - /* This flag is used by node and meta inodes, and by recovery */ #define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO) @@ -81,6 +76,7 @@ enum stop_cp_reason { STOP_CP_REASON_CORRUPTED_SUMMARY, STOP_CP_REASON_UPDATE_INODE, STOP_CP_REASON_FLUSH_FAIL, + STOP_CP_REASON_NO_SEGMENT, STOP_CP_REASON_MAX, }; diff --git a/include/linux/fb.h b/include/linux/fb.h index 05dc9624897d..811e47f9d1c3 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -2,28 +2,30 @@ #ifndef _LINUX_FB_H #define _LINUX_FB_H -#include <linux/refcount.h> -#include <linux/kgdb.h> #include <uapi/linux/fb.h> #define FBIO_CURSOR _IOWR('F', 0x08, struct fb_cursor_user) -#include <linux/fs.h> -#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/printk.h> +#include <linux/refcount.h> +#include <linux/types.h> #include <linux/workqueue.h> -#include <linux/notifier.h> -#include <linux/list.h> -#include <linux/backlight.h> -#include <linux/slab.h> #include <asm/fb.h> -struct vm_area_struct; -struct fb_info; +struct backlight_device; struct device; +struct device_node; +struct fb_info; struct file; +struct i2c_adapter; +struct inode; +struct module; +struct notifier_block; +struct page; struct videomode; -struct device_node; +struct vm_area_struct; /* Definitions below are used in the parsed monitor specs */ #define FB_DPMS_ACTIVE_OFF 1 @@ -143,9 +145,13 @@ struct fb_event { void *data; }; +/* Enough for the VT console needs, see its max_font_width/height */ +#define FB_MAX_BLIT_WIDTH 64 +#define FB_MAX_BLIT_HEIGHT 128 + struct fb_blit_caps { - u32 x; - u32 y; + DECLARE_BITMAP(x, FB_MAX_BLIT_WIDTH); + DECLARE_BITMAP(y, FB_MAX_BLIT_HEIGHT); u32 len; u32 flags; }; @@ -192,10 +198,12 @@ struct fb_pixmap { u32 scan_align; /* alignment per scanline */ u32 access_align; /* alignment per read/write (bits) */ u32 flags; /* see FB_PIXMAP_* */ - u32 blit_x; /* supported bit block dimensions (1-32)*/ - u32 blit_y; /* Format: blit_x = 1 << (width - 1) */ - /* blit_y = 1 << (height - 1) */ - /* if 0, will be set to 0xffffffff (all)*/ + /* supported bit block dimensions */ + /* Format: test_bit(width - 1, blit_x) */ + /* test_bit(height - 1, blit_y) */ + /* if zero, will be set to full (all) */ + DECLARE_BITMAP(blit_x, FB_MAX_BLIT_WIDTH); + DECLARE_BITMAP(blit_y, FB_MAX_BLIT_HEIGHT); /* access methods */ void (*writeio)(struct fb_info *info, void __iomem *dst, void *src, unsigned int size); void (*readio) (struct fb_info *info, void *dst, void __iomem *src, unsigned int size); @@ -686,6 +694,10 @@ extern int fb_deferred_io_fsync(struct file *file, loff_t start, __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \ __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys) +#define FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(__prefix, __damage_range, __damage_area) \ + __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \ + __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys) + /* * Initializes struct fb_ops for deferred I/O. */ @@ -840,14 +852,7 @@ extern int fb_find_mode(struct fb_var_screeninfo *var, const struct fb_videomode *default_mode, unsigned int default_bpp); -#if defined(CONFIG_VIDEO_NOMODESET) bool fb_modesetting_disabled(const char *drvname); -#else -static inline bool fb_modesetting_disabled(const char *drvname) -{ - return false; -} -#endif /* * Convenience logging macros diff --git a/include/linux/file.h b/include/linux/file.h index 169692cb1906..45d0f4800abd 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -84,6 +84,7 @@ static inline void fdput_pos(struct fd f) } DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) +DEFINE_CLASS(fd_raw, struct fd, fdput(_T), fdget_raw(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); diff --git a/include/linux/filter.h b/include/linux/filter.h index c99bc3df2d28..0f12cf01070e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -75,6 +75,9 @@ struct ctl_table_header; /* unused opcode to mark special load instruction. Same as BPF_MSH */ #define BPF_PROBE_MEM32 0xa0 +/* unused opcode to mark special atomic instruction */ +#define BPF_PROBE_ATOMIC 0xe0 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 @@ -178,6 +181,25 @@ struct ctl_table_header; .off = 0, \ .imm = 0 }) +/* Special (internal-only) form of mov, used to resolve per-CPU addrs: + * dst_reg = src_reg + <percpu_base_off> + * BPF_ADDR_PERCPU is used as a special insn->off value. + */ +#define BPF_ADDR_PERCPU (-1) + +#define BPF_MOV64_PERCPU_REG(DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = BPF_ADDR_PERCPU, \ + .imm = 0 }) + +static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; +} + /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ @@ -228,6 +250,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } +/* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers + * to pointers in user vma. + */ +static inline bool insn_is_cast_user(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && + insn->off == BPF_ADDR_SPACE_CAST && + insn->imm == 1U << 16; +} + /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) @@ -644,14 +676,16 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, cant_migrate(); if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; - u64 start = sched_clock(); + u64 duration, start = sched_clock(); unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); + + duration = sched_clock() - start; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); - u64_stats_add(&stats->nsecs, sched_clock() - start); + u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); @@ -887,20 +921,22 @@ bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -static inline void bpf_prog_lock_ro(struct bpf_prog *fp) +static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); - set_memory_ro((unsigned long)fp, fp->pages); + return set_memory_ro((unsigned long)fp, fp->pages); } #endif + return 0; } -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) +static inline int __must_check +bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); @@ -957,12 +993,16 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); +bool bpf_jit_inlines_helper_call(s32 imm); bool bpf_jit_supports_subprog_tailcalls(void); +bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); +bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); +u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); diff --git a/include/linux/find.h b/include/linux/find.h index 5e4f39ef2e72..28ec5a03393a 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -29,6 +29,8 @@ unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsign unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); +unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, + const unsigned long *addr3, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); @@ -345,6 +347,31 @@ unsigned long find_first_and_bit(const unsigned long *addr1, } #endif +/** + * find_first_and_and_bit - find the first set bit in 3 memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @addr3: The third address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the first set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_and_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_and_and_bit(addr1, addr2, addr3, size); +} + #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region @@ -405,7 +432,7 @@ unsigned long find_next_and_bit_wrap(const unsigned long *addr1, { unsigned long bit = find_next_and_bit(addr1, addr2, size, offset); - if (bit < size) + if (bit < size || offset == 0) return bit; bit = find_first_and_bit(addr1, addr2, offset); @@ -413,8 +440,8 @@ unsigned long find_next_and_bit_wrap(const unsigned long *addr1, } /** - * find_next_bit_wrap - find the next set bit in both memory regions - * @addr: The first address to base the search on + * find_next_bit_wrap - find the next set bit in a memory region + * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * @@ -427,7 +454,7 @@ unsigned long find_next_bit_wrap(const unsigned long *addr, { unsigned long bit = find_next_bit(addr, size, offset); - if (bit < size) + if (bit < size || offset == 0) return bit; bit = find_first_bit(addr, offset); diff --git a/include/linux/firewire.h b/include/linux/firewire.h index dd9f2d765e68..00abe0e5d602 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -463,7 +463,8 @@ 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[]; /* tx: Top of 1394 isoch. data_block */ + /* tx: Top of 1394 isoch. data_block */ + u32 header[] __counted_by(header_length); }; #define FW_ISO_CONTEXT_TRANSMIT 0 diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 0311858b46ce..f026f8926d79 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <linux/compiler.h> +#include <linux/cleanup.h> #include <linux/gfp.h> #define FW_ACTION_NOUEVENT 0 @@ -198,4 +199,6 @@ static inline void firmware_upload_unregister(struct fw_upload *fw_upload) int firmware_request_cache(struct device *device, const char *name); +DEFINE_FREE(firmware, struct firmware *, release_firmware(_T)) + #endif diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 29cd11d5a3cf..82687e07a7c2 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -123,7 +123,6 @@ struct cs_dsp_client_ops; * @sysclk_mask: Mask of frequency bits within sysclk register (ADSP1 only) * @sysclk_shift: Shift of frequency bits within sysclk register (ADSP1 only) * @alg_regions: List of currently loaded algorithm regions - * @fw_file_name: Filename of the current firmware * @fw_name: Name of the current firmware * @fw_id: ID of the current firmware, obtained from the wmfw * @fw_id_version: Version of the firmware, obtained from the wmfw @@ -239,8 +238,12 @@ void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp); int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int event_id); int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, const void *buf, size_t len); +int cs_dsp_coeff_lock_and_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + const void *buf, size_t len); int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, void *buf, size_t len); +int cs_dsp_coeff_lock_and_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + void *buf, size_t len); struct cs_dsp_coeff_ctl *cs_dsp_get_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg); diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 5c28298a98be..366243ee9609 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -10,6 +10,7 @@ #define __QCOM_QSEECOM_H #include <linux/auxiliary_bus.h> +#include <linux/dma-mapping.h> #include <linux/types.h> #include <linux/firmware/qcom/qcom_scm.h> @@ -25,11 +26,56 @@ struct qseecom_client { }; /** + * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client. + * @client: The QSEECOM client device. + * + * Returns the SCM device under which the provided QSEECOM client device + * operates. This function is intended to be used for DMA allocations. + */ +static inline struct device *qseecom_scm_dev(struct qseecom_client *client) +{ + return client->aux_dev.dev.parent->parent; +} + +/** + * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client. + * @client: The QSEECOM client to allocate the memory for. + * @size: The number of bytes to allocate. + * @dma_handle: Pointer to where the DMA address should be stored. + * @gfp: Allocation flags. + * + * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for + * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details. + */ +static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size, + dma_addr_t *dma_handle, gfp_t gfp) +{ + return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp); +} + +/** + * dma_free_coherent() - Free QSEECOM DMA memory. + * @client: The QSEECOM client for which the memory has been allocated. + * @size: The number of bytes allocated. + * @cpu_addr: Virtual memory address to free. + * @dma_handle: DMA memory address to free. + * + * Wrapper function for dma_free_coherent(), freeing memory previously + * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for + * details. + */ +static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, + void *cpu_addr, dma_addr_t dma_handle) +{ + return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle); +} + +/** * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app. * @client: The QSEECOM client associated with the target app. - * @req: Request buffer sent to the app (must be DMA-mappable). + * @req: DMA address of the request buffer sent to the app. * @req_size: Size of the request buffer. - * @rsp: Response buffer, written to by the app (must be DMA-mappable). + * @rsp: DMA address of the response buffer, written to by the app. * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given client and read @@ -43,8 +89,9 @@ struct qseecom_client { * * Return: Zero on success, nonzero on failure. */ -static inline int qcom_qseecom_app_send(struct qseecom_client *client, void *req, size_t req_size, - void *rsp, size_t rsp_size) +static inline int qcom_qseecom_app_send(struct qseecom_client *client, + dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { return qcom_scm_qseecom_app_send(client->app_id, req, req_size, rsp, rsp_size); } diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index ccaf28846054..aaa19f93ac43 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -118,8 +118,8 @@ bool qcom_scm_lmh_dcvsh_available(void); #ifdef CONFIG_QCOM_QSEECOM int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id); -int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, - size_t rsp_size); +int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size); #else /* CONFIG_QCOM_QSEECOM */ @@ -128,9 +128,9 @@ static inline int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id) return -EINVAL; } -static inline int qcom_scm_qseecom_app_send(u32 app_id, void *req, - size_t req_size, void *rsp, - size_t rsp_size) +static inline int qcom_scm_qseecom_app_send(u32 app_id, + dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { return -EINVAL; } diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 9a7e52739251..1a069a56c961 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -3,6 +3,7 @@ * Xilinx Zynq MPSoC Firmware layer * * Copyright (C) 2014-2021 Xilinx + * Copyright (C) 2022 - 2023, Advanced Micro Devices, Inc. * * Michal Simek <michal.simek@amd.com> * Davorin Mista <davorin.mista@aggios.com> @@ -171,6 +172,7 @@ enum pm_api_id { PM_CLOCK_GETPARENT = 44, PM_FPGA_READ = 46, PM_SECURE_AES = 47, + PM_EFUSE_ACCESS = 53, PM_FEATURE_CHECK = 63, }; @@ -562,6 +564,7 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); int zynqmp_pm_aes_engine(const u64 address, u32 *out); +int zynqmp_pm_efuse_access(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); @@ -749,6 +752,11 @@ static inline int zynqmp_pm_aes_engine(const u64 address, u32 *out) return -ENODEV; } +static inline int zynqmp_pm_efuse_access(const u64 address, u32 *out) +{ + return -ENODEV; +} + static inline int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags) { diff --git a/include/linux/flex_proportions.h b/include/linux/flex_proportions.h index 3e378b1fb0bc..e9a72fd0bfe7 100644 --- a/include/linux/flex_proportions.h +++ b/include/linux/flex_proportions.h @@ -39,38 +39,6 @@ void fprop_global_destroy(struct fprop_global *p); bool fprop_new_period(struct fprop_global *p, int periods); /* - * ---- SINGLE ---- - */ -struct fprop_local_single { - /* the local events counter */ - unsigned long events; - /* Period in which we last updated events */ - unsigned int period; - raw_spinlock_t lock; /* Protect period and numerator */ -}; - -#define INIT_FPROP_LOCAL_SINGLE(name) \ -{ .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ -} - -int fprop_local_init_single(struct fprop_local_single *pl); -void fprop_local_destroy_single(struct fprop_local_single *pl); -void __fprop_inc_single(struct fprop_global *p, struct fprop_local_single *pl); -void fprop_fraction_single(struct fprop_global *p, - struct fprop_local_single *pl, unsigned long *numerator, - unsigned long *denominator); - -static inline -void fprop_inc_single(struct fprop_global *p, struct fprop_local_single *pl) -{ - unsigned long flags; - - local_irq_save(flags); - __fprop_inc_single(p, pl); - local_irq_restore(flags); -} - -/* * ---- PERCPU ---- */ struct fprop_local_percpu { diff --git a/include/linux/font.h b/include/linux/font.h index abf1442ce719..81caffd51bb4 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -57,7 +57,8 @@ extern const struct font_desc *find_font(const char *name); /* Get the default font for a specific screen size */ extern const struct font_desc *get_default_font(int xres, int yres, - u32 font_w, u32 font_h); + unsigned long *font_w, + unsigned long *font_h); /* Max. length for the name of a predefined font */ #define MAX_FONT_NAME 32 diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 6aeebe0a6777..85fc0e6f0f7f 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -15,10 +15,14 @@ #define FORTIFY_REASON(func, write) (FIELD_PREP(BIT(0), write) | \ FIELD_PREP(GENMASK(7, 1), func)) +/* Overridden by KUnit tests. */ #ifndef fortify_panic # define fortify_panic(func, write, avail, size, retfail) \ __fortify_panic(FORTIFY_REASON(func, write), avail, size) #endif +#ifndef fortify_warn_once +# define fortify_warn_once(x...) WARN_ONCE(x) +#endif #define FORTIFY_READ 0 #define FORTIFY_WRITE 1 @@ -609,7 +613,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ - WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \ + fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ @@ -734,7 +738,8 @@ __FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) - fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, NULL); + fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, + __real_kmemdup(p, 0, gfp)); return __real_kmemdup(p, size, gfp); } diff --git a/include/linux/framer/framer.h b/include/linux/framer/framer.h index 9a9b88962c29..2b85fe9e7f9a 100644 --- a/include/linux/framer/framer.h +++ b/include/linux/framer/framer.h @@ -181,12 +181,12 @@ static inline int framer_notifier_unregister(struct framer *framer, return -ENOSYS; } -struct framer *framer_get(struct device *dev, const char *con_id) +static inline struct framer *framer_get(struct device *dev, const char *con_id) { return ERR_PTR(-ENOSYS); } -void framer_put(struct device *dev, struct framer *framer) +static inline void framer_put(struct device *dev, struct framer *framer) { } diff --git a/include/linux/fs.h b/include/linux/fs.h index 0a22b7245982..b7b9b3b79acc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -110,21 +110,26 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, */ /* file is open for reading */ -#define FMODE_READ ((__force fmode_t)0x1) +#define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ -#define FMODE_WRITE ((__force fmode_t)0x2) +#define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ -#define FMODE_LSEEK ((__force fmode_t)0x4) +#define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ -#define FMODE_PREAD ((__force fmode_t)0x8) +#define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ -#define FMODE_PWRITE ((__force fmode_t)0x10) +#define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ -#define FMODE_EXEC ((__force fmode_t)0x20) +#define FMODE_EXEC ((__force fmode_t)(1 << 5)) +/* File writes are restricted (block device specific) */ +#define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) + +/* FMODE_* bits 7 to 8 */ + /* 32bit hashes as llseek() offset (for directories) */ -#define FMODE_32BITHASH ((__force fmode_t)0x200) +#define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ -#define FMODE_64BITHASH ((__force fmode_t)0x400) +#define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. @@ -132,60 +137,53 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ -#define FMODE_NOCMTIME ((__force fmode_t)0x800) +#define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ -#define FMODE_RANDOM ((__force fmode_t)0x1000) +#define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* File is huge (eg. /dev/mem): treat loff_t as unsigned */ -#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) +#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ -#define FMODE_PATH ((__force fmode_t)0x4000) +#define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ -#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) +#define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ -#define FMODE_WRITER ((__force fmode_t)0x10000) +#define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ -#define FMODE_CAN_READ ((__force fmode_t)0x20000) +#define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ -#define FMODE_CAN_WRITE ((__force fmode_t)0x40000) +#define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) -#define FMODE_OPENED ((__force fmode_t)0x80000) -#define FMODE_CREATED ((__force fmode_t)0x100000) +#define FMODE_OPENED ((__force fmode_t)(1 << 19)) +#define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ -#define FMODE_STREAM ((__force fmode_t)0x200000) +#define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ -#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) +#define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) -#define FMODE_NOREUSE ((__force fmode_t)0x800000) +#define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) -/* File supports non-exclusive O_DIRECT writes from multiple threads */ -#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) +/* FMODE_* bit 24 */ /* File is embedded in backing_file object */ -#define FMODE_BACKING ((__force fmode_t)0x2000000) +#define FMODE_BACKING ((__force fmode_t)(1 << 25)) /* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +#define FMODE_NONOTIFY ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ -#define FMODE_NOWAIT ((__force fmode_t)0x8000000) +#define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ -#define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000) +#define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ -#define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) - -/* File supports async buffered reads */ -#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) - -/* File supports async nowait buffered writes */ -#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000) +#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * Attribute flags. These should be or-ed together to figure out what @@ -1033,12 +1031,13 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[]; + unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { - atomic_long_inc(&f->f_count); + long prior = atomic_long_fetch_inc_relaxed(&f->f_count); + WARN_ONCE(!prior, "struct file::f_count incremented from zero; use-after-free condition present!\n"); return f; } @@ -1175,7 +1174,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 -#define SB_I_EVM_UNSUPPORTED 0x00000080 +#define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ @@ -2001,8 +2000,11 @@ struct iov_iter; struct io_uring_cmd; struct offset_ctx; +typedef unsigned int __bitwise fop_flags_t; + struct file_operations { struct module *owner; + fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); @@ -2015,7 +2017,6 @@ struct file_operations { long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); - unsigned long mmap_supported_flags; int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); @@ -2046,6 +2047,17 @@ struct file_operations { unsigned int poll_flags); } __randomize_layout; +/* Supports async buffered reads */ +#define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) +/* Supports async buffered writes */ +#define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) +/* Supports synchronous page faults for mappings */ +#define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) +/* Supports non-exclusive O_DIRECT writes from multiple threads */ +#define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) +/* Contains huge pages */ +#define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) + /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); @@ -2179,7 +2191,7 @@ struct super_operations { #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); - struct dquot **(*get_dquots)(struct inode *); + struct dquot __rcu **(*get_dquots)(struct inode *); #endif long (*nr_cached_objects)(struct super_block *, struct shrink_control *); @@ -2251,7 +2263,13 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) + +#ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) +#else +#define IS_SWAPFILE(inode) ((void)(inode), 0U) +#endif + #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) @@ -3074,6 +3092,7 @@ extern struct inode *new_inode_pseudo(struct super_block *sb); 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_flags(struct file *file, unsigned int flags); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); @@ -3337,6 +3356,8 @@ void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); int simple_offset_empty(struct dentry *dentry); +int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 01542c4b87a2..d3350979115f 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -132,4 +132,8 @@ static inline bool fs_validate_description(const char *name, #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) +/* String parameter that allows empty argument */ +#define fsparam_string_empty(NAME, OPT) \ + __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) + #endif /* _LINUX_FS_PARSER_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 6e8562cbcc43..9de27643607f 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -172,9 +172,12 @@ extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *); -extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *, - loff_t, size_t, loff_t, netfs_io_terminated_t, void *, - bool); +void __fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool using_pgpriv2, bool cond); extern void __fscache_clear_page_bits(struct address_space *, loff_t, size_t); /** @@ -597,7 +600,8 @@ static inline void fscache_clear_page_bits(struct address_space *mapping, * @i_size: The new size of the inode * @term_func: The function to call upon completion * @term_func_priv: The private data for @term_func - * @caching: If PG_fscache has been set + * @using_pgpriv2: If we're using PG_private_2 to mark in-progress write + * @caching: If we actually want to do the caching * * Helper function for a netfs to write dirty data from an inode into the cache * object that's backing it. @@ -608,19 +612,21 @@ static inline void fscache_clear_page_bits(struct address_space *mapping, * marked with PG_fscache. * * If given, @term_func will be called upon completion and supplied with - * @term_func_priv. Note that the PG_fscache flags will have been cleared by - * this point, so the netfs must retain its own pin on the mapping. + * @term_func_priv. Note that if @using_pgpriv2 is set, the PG_private_2 flags + * will have been cleared by this point, so the netfs must retain its own pin + * on the mapping. */ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, struct address_space *mapping, loff_t start, size_t len, loff_t i_size, netfs_io_terminated_t term_func, void *term_func_priv, - bool caching) + bool using_pgpriv2, bool caching) { if (caching) __fscache_write_to_cache(cookie, mapping, start, len, i_size, - term_func, term_func_priv, caching); + term_func, term_func_priv, + using_pgpriv2, caching); else if (term_func) term_func(term_func_priv, -ENOBUFS, false); diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 8300a5286988..1a9de119a0f7 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -17,6 +17,12 @@ #include <linux/slab.h> #include <linux/bug.h> +/* Are there any inode/mount/sb objects that are being watched at all? */ +static inline bool fsnotify_sb_has_watchers(struct super_block *sb) +{ + return atomic_long_read(&sb->s_fsnotify_connectors); +} + /* * Notify this @dir inode about a change in a child directory entry. * The directory entry may have turned positive or negative or its inode may @@ -30,7 +36,7 @@ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { - if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0) + if (!fsnotify_sb_has_watchers(dir->i_sb)) return 0; return fsnotify(mask, data, data_type, dir, name, NULL, cookie); @@ -44,7 +50,7 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, static inline void fsnotify_inode(struct inode *inode, __u32 mask) { - if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0) + if (!fsnotify_sb_has_watchers(inode->i_sb)) return; if (S_ISDIR(inode->i_mode)) @@ -59,7 +65,7 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, { struct inode *inode = d_inode(dentry); - if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0) + if (!fsnotify_sb_has_watchers(inode->i_sb)) return 0; if (S_ISDIR(inode->i_mode)) { diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 7f63be5ca0f1..8f40c349b228 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -31,8 +31,8 @@ #define FS_ACCESS 0x00000001 /* File was accessed */ #define FS_MODIFY 0x00000002 /* File was modified */ #define FS_ATTRIB 0x00000004 /* Metadata changed */ -#define FS_CLOSE_WRITE 0x00000008 /* Writtable file was closed */ -#define FS_CLOSE_NOWRITE 0x00000010 /* Unwrittable file closed */ +#define FS_CLOSE_WRITE 0x00000008 /* Writable file was closed */ +#define FS_CLOSE_NOWRITE 0x00000010 /* Unwritable file closed */ #define FS_OPEN 0x00000020 /* File was opened */ #define FS_MOVED_FROM 0x00000040 /* File was moved from X */ #define FS_MOVED_TO 0x00000080 /* File was moved to Y */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e8921871ef9a..54d53f345d14 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1151,7 +1151,9 @@ static inline void unpause_graph_tracing(void) { } #ifdef CONFIG_TRACING enum ftrace_dump_mode; -extern enum ftrace_dump_mode ftrace_dump_on_oops; +#define MAX_TRACER_SIZE 100 +extern char ftrace_dump_on_oops[]; +extern int ftrace_dump_on_oops_enabled(void); extern int tracepoint_printk; extern void disable_trace_on_warning(void); diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h index 95421860397a..3ff4c277296f 100644 --- a/include/linux/fw_table.h +++ b/include/linux/fw_table.h @@ -40,12 +40,14 @@ union acpi_subtable_headers { int acpi_parse_entries_array(char *id, unsigned long table_size, union fw_table_header *table_header, + unsigned long max_length, struct acpi_subtable_proc *proc, int proc_num, unsigned int max_entries); int cdat_table_parse(enum acpi_cdat_type type, acpi_tbl_entry_handler_arg handler_arg, void *arg, - struct acpi_table_cdat *table_header); + struct acpi_table_cdat *table_header, + unsigned long length); /* CXL is the only non-ACPI consumer of the FIRMWARE_TABLE library */ #if IS_ENABLED(CONFIG_ACPI) && !IS_ENABLED(CONFIG_CXL_BUS) diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 2a72f55d26eb..0d79070c5a70 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -9,10 +9,16 @@ #ifndef _LINUX_FWNODE_H_ #define _LINUX_FWNODE_H_ -#include <linux/types.h> -#include <linux/list.h> #include <linux/bits.h> #include <linux/err.h> +#include <linux/list.h> +#include <linux/types.h> + +enum dev_dma_attr { + DEV_DMA_NOT_SUPPORTED, + DEV_DMA_NON_COHERENT, + DEV_DMA_COHERENT, +}; struct fwnode_operations; struct device; @@ -53,8 +59,10 @@ struct fwnode_handle { * fwnode link flags * * CYCLE: The fwnode link is part of a cycle. Don't defer probe. + * IGNORE: Completely ignore this link, even during cycle detection. */ #define FWLINK_FLAG_CYCLE BIT(0) +#define FWLINK_FLAG_IGNORE BIT(1) struct fwnode_link { struct fwnode_handle *supplier; @@ -187,7 +195,6 @@ struct fwnode_operations { if (fwnode_has_op(fwnode, op)) \ (fwnode)->ops->op(fwnode, ## __VA_ARGS__); \ } while (false) -#define get_dev_from_fwnode(fwnode) get_device((fwnode)->dev) static inline void fwnode_init(struct fwnode_handle *fwnode, const struct fwnode_operations *ops) @@ -209,9 +216,10 @@ static inline void fwnode_dev_initialized(struct fwnode_handle *fwnode, fwnode->flags &= ~FWNODE_FLAG_INITIALIZED; } -extern bool fw_devlink_is_strict(void); -int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup); +int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup, + u8 flags); void fwnode_links_purge(struct fwnode_handle *fwnode); void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode); +bool fw_devlink_is_strict(void); #endif diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h index 847413164738..f3512fddf3d7 100644 --- a/include/linux/generic-radix-tree.h +++ b/include/linux/generic-radix-tree.h @@ -5,7 +5,7 @@ * DOC: Generic radix trees/sparse arrays * * Very simple and minimalistic, supporting arbitrary size entries up to - * PAGE_SIZE. + * GENRADIX_NODE_SIZE. * * A genradix is defined with the type it will store, like so: * @@ -45,12 +45,15 @@ struct genradix_root; +#define GENRADIX_NODE_SHIFT 9 +#define GENRADIX_NODE_SIZE (1U << GENRADIX_NODE_SHIFT) + struct __genradix { struct genradix_root *root; }; /* - * NOTE: currently, sizeof(_type) must not be larger than PAGE_SIZE: + * NOTE: currently, sizeof(_type) must not be larger than GENRADIX_NODE_SIZE: */ #define __GENRADIX_INITIALIZER \ @@ -101,14 +104,14 @@ void __genradix_free(struct __genradix *); static inline size_t __idx_to_offset(size_t idx, size_t obj_size) { if (__builtin_constant_p(obj_size)) - BUILD_BUG_ON(obj_size > PAGE_SIZE); + BUILD_BUG_ON(obj_size > GENRADIX_NODE_SIZE); else - BUG_ON(obj_size > PAGE_SIZE); + BUG_ON(obj_size > GENRADIX_NODE_SIZE); if (!is_power_of_2(obj_size)) { - size_t objs_per_page = PAGE_SIZE / obj_size; + size_t objs_per_page = GENRADIX_NODE_SIZE / obj_size; - return (idx / objs_per_page) * PAGE_SIZE + + return (idx / objs_per_page) * GENRADIX_NODE_SIZE + (idx % objs_per_page) * obj_size; } else { return idx * obj_size; @@ -118,9 +121,9 @@ static inline size_t __idx_to_offset(size_t idx, size_t obj_size) #define __genradix_cast(_radix) (typeof((_radix)->type[0]) *) #define __genradix_obj_size(_radix) sizeof((_radix)->type[0]) #define __genradix_objs_per_page(_radix) \ - (PAGE_SIZE / sizeof((_radix)->type[0])) + (GENRADIX_NODE_SIZE / sizeof((_radix)->type[0])) #define __genradix_page_remainder(_radix) \ - (PAGE_SIZE % sizeof((_radix)->type[0])) + (GENRADIX_NODE_SIZE % sizeof((_radix)->type[0])) #define __genradix_idx_to_offset(_radix, _idx) \ __idx_to_offset(_idx, __genradix_obj_size(_radix)) @@ -217,8 +220,8 @@ static inline void __genradix_iter_advance(struct genradix_iter *iter, iter->offset += obj_size; if (!is_power_of_2(obj_size) && - (iter->offset & (PAGE_SIZE - 1)) + obj_size > PAGE_SIZE) - iter->offset = round_up(iter->offset, PAGE_SIZE); + (iter->offset & (GENRADIX_NODE_SIZE - 1)) + obj_size > GENRADIX_NODE_SIZE) + iter->offset = round_up(iter->offset, GENRADIX_NODE_SIZE); iter->pos++; } @@ -235,8 +238,8 @@ static inline void __genradix_iter_rewind(struct genradix_iter *iter, return; } - if ((iter->offset & (PAGE_SIZE - 1)) == 0) - iter->offset -= PAGE_SIZE % obj_size; + if ((iter->offset & (GENRADIX_NODE_SIZE - 1)) == 0) + iter->offset -= GENRADIX_NODE_SIZE % obj_size; iter->offset -= obj_size; iter->pos--; @@ -263,7 +266,7 @@ static inline void __genradix_iter_rewind(struct genradix_iter *iter, genradix_for_each_from(_radix, _iter, _p, 0) #define genradix_last_pos(_radix) \ - (SIZE_MAX / PAGE_SIZE * __genradix_objs_per_page(_radix) - 1) + (SIZE_MAX / GENRADIX_NODE_SIZE * __genradix_objs_per_page(_radix) - 1) /** * genradix_for_each_reverse - iterate over entry in a genradix, reverse order diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h deleted file mode 100644 index c285968e437a..000000000000 --- a/include/linux/genetlink.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_GENERIC_NETLINK_H -#define __LINUX_GENERIC_NETLINK_H - -#include <uapi/linux/genetlink.h> - - -/* All generic netlink requests are serialized by a global lock. */ -extern void genl_lock(void); -extern void genl_unlock(void); - -/* for synchronisation between af_netlink and genetlink */ -extern atomic_t genl_sk_destructing_cnt; -extern wait_queue_head_t genl_sk_destructing_waitq; - -#define MODULE_ALIAS_GENL_FAMILY(family)\ - MODULE_ALIAS_NET_PF_PROTO_NAME(PF_NETLINK, NETLINK_GENERIC, "-family-" family) - -#endif /* __LINUX_GENERIC_NETLINK_H */ diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h index a419d93789ff..621b87a87d74 100644 --- a/include/linux/genl_magic_struct.h +++ b/include/linux/genl_magic_struct.h @@ -15,8 +15,8 @@ #endif #include <linux/args.h> -#include <linux/genetlink.h> #include <linux/types.h> +#include <net/genetlink.h> extern int CONCATENATE(GENL_MAGIC_FAMILY, _genl_register)(void); extern void CONCATENATE(GENL_MAGIC_FAMILY, _genl_unregister)(void); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 937c2a9b6e54..c775ea3c6015 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -342,7 +342,7 @@ void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); -void setup_pcp_cacheinfo(void); +void setup_pcp_cacheinfo(unsigned int cpu); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 1b6053da8754..13becafe41df 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -2,6 +2,8 @@ #ifndef __LINUX_GFP_TYPES_H #define __LINUX_GFP_TYPES_H +#include <linux/bits.h> + /* The typedef is in types.h but we want the documentation here */ #if 0 /** @@ -21,44 +23,78 @@ typedef unsigned int __bitwise gfp_t; * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c */ +enum { + ___GFP_DMA_BIT, + ___GFP_HIGHMEM_BIT, + ___GFP_DMA32_BIT, + ___GFP_MOVABLE_BIT, + ___GFP_RECLAIMABLE_BIT, + ___GFP_HIGH_BIT, + ___GFP_IO_BIT, + ___GFP_FS_BIT, + ___GFP_ZERO_BIT, + ___GFP_UNUSED_BIT, /* 0x200u unused */ + ___GFP_DIRECT_RECLAIM_BIT, + ___GFP_KSWAPD_RECLAIM_BIT, + ___GFP_WRITE_BIT, + ___GFP_NOWARN_BIT, + ___GFP_RETRY_MAYFAIL_BIT, + ___GFP_NOFAIL_BIT, + ___GFP_NORETRY_BIT, + ___GFP_MEMALLOC_BIT, + ___GFP_COMP_BIT, + ___GFP_NOMEMALLOC_BIT, + ___GFP_HARDWALL_BIT, + ___GFP_THISNODE_BIT, + ___GFP_ACCOUNT_BIT, + ___GFP_ZEROTAGS_BIT, +#ifdef CONFIG_KASAN_HW_TAGS + ___GFP_SKIP_ZERO_BIT, + ___GFP_SKIP_KASAN_BIT, +#endif +#ifdef CONFIG_LOCKDEP + ___GFP_NOLOCKDEP_BIT, +#endif + ___GFP_LAST_BIT +}; + /* Plain integer GFP bitmasks. Do not use this directly. */ -#define ___GFP_DMA 0x01u -#define ___GFP_HIGHMEM 0x02u -#define ___GFP_DMA32 0x04u -#define ___GFP_MOVABLE 0x08u -#define ___GFP_RECLAIMABLE 0x10u -#define ___GFP_HIGH 0x20u -#define ___GFP_IO 0x40u -#define ___GFP_FS 0x80u -#define ___GFP_ZERO 0x100u +#define ___GFP_DMA BIT(___GFP_DMA_BIT) +#define ___GFP_HIGHMEM BIT(___GFP_HIGHMEM_BIT) +#define ___GFP_DMA32 BIT(___GFP_DMA32_BIT) +#define ___GFP_MOVABLE BIT(___GFP_MOVABLE_BIT) +#define ___GFP_RECLAIMABLE BIT(___GFP_RECLAIMABLE_BIT) +#define ___GFP_HIGH BIT(___GFP_HIGH_BIT) +#define ___GFP_IO BIT(___GFP_IO_BIT) +#define ___GFP_FS BIT(___GFP_FS_BIT) +#define ___GFP_ZERO BIT(___GFP_ZERO_BIT) /* 0x200u unused */ -#define ___GFP_DIRECT_RECLAIM 0x400u -#define ___GFP_KSWAPD_RECLAIM 0x800u -#define ___GFP_WRITE 0x1000u -#define ___GFP_NOWARN 0x2000u -#define ___GFP_RETRY_MAYFAIL 0x4000u -#define ___GFP_NOFAIL 0x8000u -#define ___GFP_NORETRY 0x10000u -#define ___GFP_MEMALLOC 0x20000u -#define ___GFP_COMP 0x40000u -#define ___GFP_NOMEMALLOC 0x80000u -#define ___GFP_HARDWALL 0x100000u -#define ___GFP_THISNODE 0x200000u -#define ___GFP_ACCOUNT 0x400000u -#define ___GFP_ZEROTAGS 0x800000u +#define ___GFP_DIRECT_RECLAIM BIT(___GFP_DIRECT_RECLAIM_BIT) +#define ___GFP_KSWAPD_RECLAIM BIT(___GFP_KSWAPD_RECLAIM_BIT) +#define ___GFP_WRITE BIT(___GFP_WRITE_BIT) +#define ___GFP_NOWARN BIT(___GFP_NOWARN_BIT) +#define ___GFP_RETRY_MAYFAIL BIT(___GFP_RETRY_MAYFAIL_BIT) +#define ___GFP_NOFAIL BIT(___GFP_NOFAIL_BIT) +#define ___GFP_NORETRY BIT(___GFP_NORETRY_BIT) +#define ___GFP_MEMALLOC BIT(___GFP_MEMALLOC_BIT) +#define ___GFP_COMP BIT(___GFP_COMP_BIT) +#define ___GFP_NOMEMALLOC BIT(___GFP_NOMEMALLOC_BIT) +#define ___GFP_HARDWALL BIT(___GFP_HARDWALL_BIT) +#define ___GFP_THISNODE BIT(___GFP_THISNODE_BIT) +#define ___GFP_ACCOUNT BIT(___GFP_ACCOUNT_BIT) +#define ___GFP_ZEROTAGS BIT(___GFP_ZEROTAGS_BIT) #ifdef CONFIG_KASAN_HW_TAGS -#define ___GFP_SKIP_ZERO 0x1000000u -#define ___GFP_SKIP_KASAN 0x2000000u +#define ___GFP_SKIP_ZERO BIT(___GFP_SKIP_ZERO_BIT) +#define ___GFP_SKIP_KASAN BIT(___GFP_SKIP_KASAN_BIT) #else #define ___GFP_SKIP_ZERO 0 #define ___GFP_SKIP_KASAN 0 #endif #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x4000000u +#define ___GFP_NOLOCKDEP BIT(___GFP_NOLOCKDEP_BIT) #else #define ___GFP_NOLOCKDEP 0 #endif -/* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* * Physical address zone modifiers (see linux/mmzone.h - low four bits) @@ -249,7 +285,7 @@ typedef unsigned int __bitwise gfp_t; #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (26 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT ___GFP_LAST_BIT #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 7ecc25c543ce..56ac7e7a2889 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -74,6 +74,12 @@ static inline bool gpio_is_valid(int number) * Until they are all fixed, leave 0-512 space for them. */ #define GPIO_DYNAMIC_BASE 512 +/* + * Define the maximum of the possible GPIO in the global numberspace. + * While the GPIO base and numbers are positive, we limit it with signed + * maximum as a lot of code is using negative values for special cases. + */ +#define GPIO_DYNAMIC_MAX INT_MAX /* Always use the library code for GPIO management calls, * or when sleeping may be involved. @@ -114,8 +120,6 @@ static inline int gpio_to_irq(unsigned gpio) } 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 */ @@ -146,11 +150,6 @@ static inline int gpio_request_one(unsigned gpio, return -ENOSYS; } -static inline int gpio_request_array(const struct gpio *array, size_t num) -{ - return -ENOSYS; -} - static inline void gpio_free(unsigned gpio) { might_sleep(); @@ -159,14 +158,6 @@ static inline void gpio_free(unsigned gpio) WARN_ON(1); } -static inline void gpio_free_array(const struct gpio *array, size_t num) -{ - might_sleep(); - - /* GPIO can never have been requested */ - WARN_ON(1); -} - static inline int gpio_direction_input(unsigned gpio) { return -ENOSYS; diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 7f75c9a51874..0032bb6e7d8f 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -335,10 +335,12 @@ struct gpio_irq_chip { * (same as GPIO_LINE_DIRECTION_OUT / GPIO_LINE_DIRECTION_IN), * or negative error. It is recommended to always implement this * function, even on input-only or output-only gpio chips. - * @direction_input: configures signal "offset" as input, or returns error - * This can be omitted on input-only or output-only gpio chips. - * @direction_output: configures signal "offset" as output, or returns error - * This can be omitted on input-only or output-only gpio chips. + * @direction_input: configures signal "offset" as input, returns 0 on success + * or a negative error number. This can be omitted on input-only or + * output-only gpio chips. + * @direction_output: configures signal "offset" as output, returns 0 on + * success or a negative error number. This can be omitted on input-only + * or output-only gpio chips. * @get: returns value for signal "offset", 0=low, 1=high, or negative error * @get_multiple: reads values for multiple signals defined by "mask" and * stores them in "bits", returns 0 on success or negative error @@ -374,9 +376,7 @@ struct gpio_irq_chip { * @names: if set, must be an array of strings to use as alternative * names for the GPIOs in this chip. Any entry in the array * may be NULL if there is no alias for the GPIO, however the - * array must be @ngpio entries long. A name can include a single printk - * format specifier for an unsigned int. It is substituted by the actual - * number of the gpio. + * array must be @ngpio entries long. * @can_sleep: flag must be set iff get()/set() methods sleep, as they * must while accessing GPIO expander chips over I2C or SPI. This * implies that if the chip supports IRQs, these IRQs need to be threaded @@ -550,6 +550,21 @@ DEFINE_CLASS(_gpiochip_for_each_data, const char **label, int *i) /** + * for_each_hwgpio - Iterates over all GPIOs for given chip. + * @_chip: Chip to iterate over. + * @_i: Loop counter. + * @_label: Place to store the address of the label if the GPIO is requested. + * Set to NULL for unused GPIOs. + */ +#define for_each_hwgpio(_chip, _i, _label) \ + for (CLASS(_gpiochip_for_each_data, _data)(&_label, &_i); \ + *_data.i < _chip->ngpio; \ + (*_data.i)++, kfree(*(_data.label)), *_data.label = NULL) \ + if (IS_ERR(*_data.label = \ + gpiochip_dup_line_label(_chip, *_data.i))) {} \ + else + +/** * for_each_requested_gpio_in_range - iterates over requested GPIOs in a given range * @_chip: the chip to query * @_i: loop variable @@ -626,10 +641,9 @@ int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc, void *data, struct lock_class_key *lock_key, struct lock_class_key *request_key); -struct gpio_device *gpio_device_find(void *data, - int (*match)(struct gpio_chip *gc, void *data)); -struct gpio_device *gpio_device_find_by_label(const char *label); -struct gpio_device *gpio_device_find_by_fwnode(const struct fwnode_handle *fwnode); +struct gpio_device *gpio_device_find(const void *data, + int (*match)(struct gpio_chip *gc, + const void *data)); struct gpio_device *gpio_device_get(struct gpio_device *gdev); void gpio_device_put(struct gpio_device *gdev); @@ -704,18 +718,6 @@ int bgpio_init(struct gpio_chip *gc, struct device *dev, #define BGPIOF_NO_OUTPUT BIT(5) /* only input */ #define BGPIOF_NO_SET_ON_INPUT BIT(6) -int gpiochip_irq_map(struct irq_domain *d, unsigned int irq, - irq_hw_number_t hwirq); -void gpiochip_irq_unmap(struct irq_domain *d, unsigned int irq); - -int gpiochip_irq_domain_activate(struct irq_domain *domain, - struct irq_data *data, bool reserve); -void gpiochip_irq_domain_deactivate(struct irq_domain *domain, - struct irq_data *data); - -bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gc, - unsigned int offset); - #ifdef CONFIG_GPIOLIB_IRQCHIP int gpiochip_irqchip_add_domain(struct gpio_chip *gc, struct irq_domain *domain); @@ -808,6 +810,9 @@ struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc); int gpio_device_get_base(struct gpio_device *gdev); const char *gpio_device_get_label(struct gpio_device *gdev); +struct gpio_device *gpio_device_find_by_label(const char *label); +struct gpio_device *gpio_device_find_by_fwnode(const struct fwnode_handle *fwnode); + #else /* CONFIG_GPIOLIB */ #include <asm/bug.h> @@ -837,6 +842,18 @@ static inline const char *gpio_device_get_label(struct gpio_device *gdev) return NULL; } +static inline struct gpio_device *gpio_device_find_by_label(const char *label) +{ + WARN_ON(1); + return NULL; +} + +static inline struct gpio_device *gpio_device_find_by_fwnode(const struct fwnode_handle *fwnode) +{ + WARN_ON(1); + return NULL; +} + static inline int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset) { diff --git a/include/linux/gpio/gpio-nomadik.h b/include/linux/gpio/gpio-nomadik.h new file mode 100644 index 000000000000..b5a84864650d --- /dev/null +++ b/include/linux/gpio/gpio-nomadik.h @@ -0,0 +1,294 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_GPIO_NOMADIK_H +#define __LINUX_GPIO_NOMADIK_H + +struct fwnode_handle; + +/* Package definitions */ +#define PINCTRL_NMK_STN8815 0 +#define PINCTRL_NMK_DB8500 1 + +#define GPIO_BLOCK_SHIFT 5 +#define NMK_GPIO_PER_CHIP BIT(GPIO_BLOCK_SHIFT) +#define NMK_MAX_BANKS DIV_ROUND_UP(512, NMK_GPIO_PER_CHIP) + +/* Register in the logic block */ +#define NMK_GPIO_DAT 0x00 +#define NMK_GPIO_DATS 0x04 +#define NMK_GPIO_DATC 0x08 +#define NMK_GPIO_PDIS 0x0c +#define NMK_GPIO_DIR 0x10 +#define NMK_GPIO_DIRS 0x14 +#define NMK_GPIO_DIRC 0x18 +#define NMK_GPIO_SLPC 0x1c +#define NMK_GPIO_AFSLA 0x20 +#define NMK_GPIO_AFSLB 0x24 +#define NMK_GPIO_LOWEMI 0x28 + +#define NMK_GPIO_RIMSC 0x40 +#define NMK_GPIO_FIMSC 0x44 +#define NMK_GPIO_IS 0x48 +#define NMK_GPIO_IC 0x4c +#define NMK_GPIO_RWIMSC 0x50 +#define NMK_GPIO_FWIMSC 0x54 +#define NMK_GPIO_WKS 0x58 +/* These appear in DB8540 and later ASICs */ +#define NMK_GPIO_EDGELEVEL 0x5C +#define NMK_GPIO_LEVEL 0x60 + +/* Pull up/down values */ +enum nmk_gpio_pull { + NMK_GPIO_PULL_NONE, + NMK_GPIO_PULL_UP, + NMK_GPIO_PULL_DOWN, +}; + +/* Sleep mode */ +enum nmk_gpio_slpm { + NMK_GPIO_SLPM_INPUT, + NMK_GPIO_SLPM_WAKEUP_ENABLE = NMK_GPIO_SLPM_INPUT, + NMK_GPIO_SLPM_NOCHANGE, + NMK_GPIO_SLPM_WAKEUP_DISABLE = NMK_GPIO_SLPM_NOCHANGE, +}; + +struct nmk_gpio_chip { + struct gpio_chip chip; + void __iomem *addr; + struct clk *clk; + unsigned int bank; + void (*set_ioforce)(bool enable); + spinlock_t lock; + bool sleepmode; + bool is_mobileye_soc; + /* Keep track of configured edges */ + u32 edge_rising; + u32 edge_falling; + u32 real_wake; + u32 rwimsc; + u32 fwimsc; + u32 rimsc; + u32 fimsc; + u32 pull_up; + u32 lowemi; +}; + +/* Alternate functions: function C is set in hw by setting both A and B */ +#define NMK_GPIO_ALT_GPIO 0 +#define NMK_GPIO_ALT_A 1 +#define NMK_GPIO_ALT_B 2 +#define NMK_GPIO_ALT_C (NMK_GPIO_ALT_A | NMK_GPIO_ALT_B) + +#define NMK_GPIO_ALT_CX_SHIFT 2 +#define NMK_GPIO_ALT_C1 ((1<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C) +#define NMK_GPIO_ALT_C2 ((2<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C) +#define NMK_GPIO_ALT_C3 ((3<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C) +#define NMK_GPIO_ALT_C4 ((4<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C) + +#define PRCM_GPIOCR_ALTCX(pin_num,\ + altc1_used, altc1_ri, altc1_cb,\ + altc2_used, altc2_ri, altc2_cb,\ + altc3_used, altc3_ri, altc3_cb,\ + altc4_used, altc4_ri, altc4_cb)\ +{\ + .pin = pin_num,\ + .altcx[PRCM_IDX_GPIOCR_ALTC1] = {\ + .used = altc1_used,\ + .reg_index = altc1_ri,\ + .control_bit = altc1_cb\ + },\ + .altcx[PRCM_IDX_GPIOCR_ALTC2] = {\ + .used = altc2_used,\ + .reg_index = altc2_ri,\ + .control_bit = altc2_cb\ + },\ + .altcx[PRCM_IDX_GPIOCR_ALTC3] = {\ + .used = altc3_used,\ + .reg_index = altc3_ri,\ + .control_bit = altc3_cb\ + },\ + .altcx[PRCM_IDX_GPIOCR_ALTC4] = {\ + .used = altc4_used,\ + .reg_index = altc4_ri,\ + .control_bit = altc4_cb\ + },\ +} + +/** + * enum prcm_gpiocr_reg_index + * Used to reference an PRCM GPIOCR register address. + */ +enum prcm_gpiocr_reg_index { + PRCM_IDX_GPIOCR1, + PRCM_IDX_GPIOCR2, + PRCM_IDX_GPIOCR3 +}; +/** + * enum prcm_gpiocr_altcx_index + * Used to reference an Other alternate-C function. + */ +enum prcm_gpiocr_altcx_index { + PRCM_IDX_GPIOCR_ALTC1, + PRCM_IDX_GPIOCR_ALTC2, + PRCM_IDX_GPIOCR_ALTC3, + PRCM_IDX_GPIOCR_ALTC4, + PRCM_IDX_GPIOCR_ALTC_MAX, +}; + +/** + * struct prcm_gpio_altcx - Other alternate-C function + * @used: other alternate-C function availability + * @reg_index: PRCM GPIOCR register index used to control the function + * @control_bit: PRCM GPIOCR bit used to control the function + */ +struct prcm_gpiocr_altcx { + bool used:1; + u8 reg_index:2; + u8 control_bit:5; +} __packed; + +/** + * struct prcm_gpio_altcx_pin_desc - Other alternate-C pin + * @pin: The pin number + * @altcx: array of other alternate-C[1-4] functions + */ +struct prcm_gpiocr_altcx_pin_desc { + unsigned short pin; + struct prcm_gpiocr_altcx altcx[PRCM_IDX_GPIOCR_ALTC_MAX]; +}; + +/** + * struct nmk_function - Nomadik pinctrl mux function + * @name: The name of the function, exported to pinctrl core. + * @groups: An array of pin groups that may select this function. + * @ngroups: The number of entries in @groups. + */ +struct nmk_function { + const char *name; + const char * const *groups; + unsigned int ngroups; +}; + +/** + * struct nmk_pingroup - describes a Nomadik pin group + * @grp: Generic data of the pin group (name and pins) + * @altsetting: the altsetting to apply to all pins in this group to + * configure them to be used by a function + */ +struct nmk_pingroup { + struct pingroup grp; + int altsetting; +}; + +#define NMK_PIN_GROUP(a, b) \ + { \ + .grp = PINCTRL_PINGROUP(#a, a##_pins, ARRAY_SIZE(a##_pins)), \ + .altsetting = b, \ + } + +/** + * struct nmk_pinctrl_soc_data - Nomadik pin controller per-SoC configuration + * @pins: An array describing all pins the pin controller affects. + * All pins which are also GPIOs must be listed first within the + * array, and be numbered identically to the GPIO controller's + * numbering. + * @npins: The number of entries in @pins. + * @functions: The functions supported on this SoC. + * @nfunction: The number of entries in @functions. + * @groups: An array describing all pin groups the pin SoC supports. + * @ngroups: The number of entries in @groups. + * @altcx_pins: The pins that support Other alternate-C function on this SoC + * @npins_altcx: The number of Other alternate-C pins + * @prcm_gpiocr_registers: The array of PRCM GPIOCR registers on this SoC + */ +struct nmk_pinctrl_soc_data { + const struct pinctrl_pin_desc *pins; + unsigned int npins; + const struct nmk_function *functions; + unsigned int nfunctions; + const struct nmk_pingroup *groups; + unsigned int ngroups; + const struct prcm_gpiocr_altcx_pin_desc *altcx_pins; + unsigned int npins_altcx; + const u16 *prcm_gpiocr_registers; +}; + +#ifdef CONFIG_PINCTRL_STN8815 + +void nmk_pinctrl_stn8815_init(const struct nmk_pinctrl_soc_data **soc); + +#else + +static inline void +nmk_pinctrl_stn8815_init(const struct nmk_pinctrl_soc_data **soc) +{ +} + +#endif + +#ifdef CONFIG_PINCTRL_DB8500 + +void nmk_pinctrl_db8500_init(const struct nmk_pinctrl_soc_data **soc); + +#else + +static inline void +nmk_pinctrl_db8500_init(const struct nmk_pinctrl_soc_data **soc) +{ +} + +#endif + +#ifdef CONFIG_PINCTRL_DB8540 + +void nmk_pinctrl_db8540_init(const struct nmk_pinctrl_soc_data **soc); + +#else + +static inline void +nmk_pinctrl_db8540_init(const struct nmk_pinctrl_soc_data **soc) +{ +} + +#endif + +struct platform_device; + +#ifdef CONFIG_DEBUG_FS + +/* + * Symbols declared in gpio-nomadik used by pinctrl-nomadik. If pinctrl-nomadik + * is enabled, then gpio-nomadik is enabled as well; the reverse if not always + * true. + */ +void nmk_gpio_dbg_show_one(struct seq_file *s, struct pinctrl_dev *pctldev, + struct gpio_chip *chip, unsigned int offset, + unsigned int gpio); + +#else + +static inline void nmk_gpio_dbg_show_one(struct seq_file *s, + struct pinctrl_dev *pctldev, + struct gpio_chip *chip, + unsigned int offset, + unsigned int gpio) +{ +} + +#endif + +void __nmk_gpio_make_output(struct nmk_gpio_chip *nmk_chip, + unsigned int offset, int val); +void __nmk_gpio_set_slpm(struct nmk_gpio_chip *nmk_chip, unsigned int offset, + enum nmk_gpio_slpm mode); +struct nmk_gpio_chip *nmk_gpio_populate_chip(struct fwnode_handle *fwnode, + struct platform_device *pdev); + +/* Symbols declared in pinctrl-nomadik used by gpio-nomadik. */ +#ifdef CONFIG_PINCTRL_NOMADIK +extern struct nmk_gpio_chip *nmk_gpio_chips[NMK_MAX_BANKS]; +extern spinlock_t nmk_gpio_slpm_lock; +int __maybe_unused nmk_prcm_gpiocr_get_mode(struct pinctrl_dev *pctldev, + int gpio); +#endif + +#endif /* __LINUX_GPIO_NOMADIK_H */ diff --git a/include/linux/gpio/property.h b/include/linux/gpio/property.h index 6c75c8bd44a0..0d2209308002 100644 --- a/include/linux/gpio/property.h +++ b/include/linux/gpio/property.h @@ -2,10 +2,13 @@ #ifndef __LINUX_GPIO_PROPERTY_H #define __LINUX_GPIO_PROPERTY_H -#include <dt-bindings/gpio/gpio.h> /* for GPIO_* flags */ #include <linux/property.h> +struct software_node; + #define PROPERTY_ENTRY_GPIO(_name_, _chip_node_, _idx_, _flags_) \ PROPERTY_ENTRY_REF(_name_, _chip_node_, _idx_, _flags_) +extern const struct software_node swnode_gpio_undefined; + #endif /* __LINUX_GPIO_PROPERTY_H */ diff --git a/include/linux/greybus.h b/include/linux/greybus.h index 18c0fb958b74..634c9511cf78 100644 --- a/include/linux/greybus.h +++ b/include/linux/greybus.h @@ -104,44 +104,14 @@ void gb_debugfs_init(void); void gb_debugfs_cleanup(void); struct dentry *gb_debugfs_get(void); -extern struct bus_type greybus_bus_type; - -extern struct device_type greybus_hd_type; -extern struct device_type greybus_module_type; -extern struct device_type greybus_interface_type; -extern struct device_type greybus_control_type; -extern struct device_type greybus_bundle_type; -extern struct device_type greybus_svc_type; - -static inline int is_gb_host_device(const struct device *dev) -{ - return dev->type == &greybus_hd_type; -} - -static inline int is_gb_module(const struct device *dev) -{ - return dev->type == &greybus_module_type; -} - -static inline int is_gb_interface(const struct device *dev) -{ - return dev->type == &greybus_interface_type; -} - -static inline int is_gb_control(const struct device *dev) -{ - return dev->type == &greybus_control_type; -} - -static inline int is_gb_bundle(const struct device *dev) -{ - return dev->type == &greybus_bundle_type; -} - -static inline int is_gb_svc(const struct device *dev) -{ - return dev->type == &greybus_svc_type; -} +extern const struct bus_type greybus_bus_type; + +extern const struct device_type greybus_hd_type; +extern const struct device_type greybus_module_type; +extern const struct device_type greybus_interface_type; +extern const struct device_type greybus_control_type; +extern const struct device_type greybus_bundle_type; +extern const struct device_type greybus_svc_type; static inline bool cport_id_valid(struct gb_host_device *hd, u16 cport_id) { diff --git a/include/linux/greybus/greybus_protocols.h b/include/linux/greybus/greybus_protocols.h index aeb8f9243545..820134b0105c 100644 --- a/include/linux/greybus/greybus_protocols.h +++ b/include/linux/greybus/greybus_protocols.h @@ -232,9 +232,7 @@ struct gb_fw_download_fetch_firmware_request { __le32 size; } __packed; -struct gb_fw_download_fetch_firmware_response { - __u8 data[0]; -} __packed; +/* gb_fw_download_fetch_firmware_response contains no other data */ /* firmware download release firmware request */ struct gb_fw_download_release_firmware_request { @@ -414,9 +412,7 @@ struct gb_bootrom_get_firmware_request { __le32 size; } __packed; -struct gb_bootrom_get_firmware_response { - __u8 data[0]; -} __packed; +/* gb_bootrom_get_firmware_response contains no other data */ /* Bootrom protocol Ready to boot request */ struct gb_bootrom_ready_to_boot_request { diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h index 13b1e65fbdcc..6730ee900ee1 100644 --- a/include/linux/hid-sensor-ids.h +++ b/include/linux/hid-sensor-ids.h @@ -21,6 +21,10 @@ #define HID_USAGE_SENSOR_ALS 0x200041 #define HID_USAGE_SENSOR_DATA_LIGHT 0x2004d0 #define HID_USAGE_SENSOR_LIGHT_ILLUM 0x2004d1 +#define HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE 0x2004d2 +#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY 0x2004d3 +#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X 0x2004d4 +#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y 0x2004d5 /* PROX (200011) */ #define HID_USAGE_SENSOR_PROX 0x200011 diff --git a/include/linux/hid.h b/include/linux/hid.h index 7c26db874ff0..8e06d89698e6 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -474,9 +474,9 @@ struct hid_usage { __s8 wheel_factor; /* 120/resolution_multiplier */ __u16 code; /* input driver code */ __u8 type; /* input driver type */ - __s8 hat_min; /* hat switch fun */ - __s8 hat_max; /* ditto */ - __s8 hat_dir; /* ditto */ + __s16 hat_min; /* hat switch fun */ + __s16 hat_max; /* ditto */ + __s16 hat_dir; /* ditto */ __s16 wheel_accumulated; /* hi-res wheel */ }; @@ -683,9 +683,9 @@ struct hid_device { /* device report descriptor */ unsigned int id; /* system unique id */ -#ifdef CONFIG_BPF +#ifdef CONFIG_HID_BPF struct hid_bpf bpf; /* hid-bpf data */ -#endif /* CONFIG_BPF */ +#endif /* CONFIG_HID_BPF */ }; void hiddev_free(struct kref *ref); diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index 7118ac28d468..17b08f500098 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -103,6 +103,9 @@ struct hid_bpf_ops { unsigned char reportnum, __u8 *buf, size_t len, enum hid_report_type rtype, enum hid_class_request reqtype); + int (*hid_hw_output_report)(struct hid_device *hdev, __u8 *buf, size_t len); + int (*hid_input_report)(struct hid_device *hid, enum hid_report_type type, + u8 *data, u32 size, int interrupt); struct module *owner; const struct bus_type *bus_type; }; diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 451c1dff0e87..00341b56d291 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -439,6 +439,13 @@ static inline void memzero_page(struct page *page, size_t offset, size_t len) kunmap_local(addr); } +/** + * memcpy_from_folio - Copy a range of bytes from a folio. + * @to: The memory to copy to. + * @folio: The folio to read from. + * @offset: The first byte in the folio to read. + * @len: The number of bytes to copy. + */ static inline void memcpy_from_folio(char *to, struct folio *folio, size_t offset, size_t len) { @@ -460,6 +467,13 @@ static inline void memcpy_from_folio(char *to, struct folio *folio, } while (len > 0); } +/** + * memcpy_to_folio - Copy a range of bytes to a folio. + * @folio: The folio to write to. + * @offset: The first byte in the folio to store to. + * @from: The memory to copy from. + * @len: The number of bytes to copy. + */ static inline void memcpy_to_folio(struct folio *folio, size_t offset, const char *from, size_t len) { diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 5f4c74facf6a..9d7754ad5e9b 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -43,6 +43,7 @@ #define QM_MB_CMD_CQC_BT 0x5 #define QM_MB_CMD_SQC_VFT_V2 0x6 #define QM_MB_CMD_STOP_QP 0x8 +#define QM_MB_CMD_FLUSH_QM 0x9 #define QM_MB_CMD_SRC 0xc #define QM_MB_CMD_DST 0xd @@ -151,6 +152,7 @@ enum qm_cap_bits { QM_SUPPORT_DB_ISOLATION = 0x0, QM_SUPPORT_FUNC_QOS, QM_SUPPORT_STOP_QP, + QM_SUPPORT_STOP_FUNC, QM_SUPPORT_MB_COMMAND, QM_SUPPORT_SVA_PREFETCH, QM_SUPPORT_RPM, @@ -161,6 +163,11 @@ struct qm_dev_alg { const char *alg; }; +struct qm_dev_dfx { + u32 dev_state; + u32 dev_timeout; +}; + struct dfx_diff_registers { u32 *regs; u32 reg_offset; @@ -189,6 +196,7 @@ struct qm_debug { struct dentry *debug_root; struct dentry *qm_d; struct debugfs_file files[DEBUG_FILE_NUM]; + struct qm_dev_dfx dev_dfx; unsigned int *qm_last_words; /* ACC engines recoreding last regs */ unsigned int *last_words; @@ -523,7 +531,7 @@ void hisi_qm_uninit(struct hisi_qm *qm); int hisi_qm_start(struct hisi_qm *qm); int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); -int hisi_qm_stop_qp(struct hisi_qp *qp); +void hisi_qm_stop_qp(struct hisi_qp *qp); int hisi_qp_send(struct hisi_qp *qp, const void *msg); void hisi_qm_debug_init(struct hisi_qm *qm); void hisi_qm_debug_regs_clear(struct hisi_qm *qm); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 5adb86af35fc..de0c89105076 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -265,10 +265,11 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, void folio_prep_large_rmappable(struct folio *folio); bool can_split_folio(struct folio *folio, int *pextra_pins); -int split_huge_page_to_list(struct page *page, struct list_head *list); +int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, + unsigned int new_order); static inline int split_huge_page(struct page *page) { - return split_huge_page_to_list(page, NULL); + return split_huge_page_to_list_to_order(page, NULL, 0); } void deferred_split_folio(struct folio *folio); @@ -422,7 +423,8 @@ can_split_folio(struct folio *folio, int *pextra_pins) return false; } static inline int -split_huge_page_to_list(struct page *page, struct list_head *list) +split_huge_page_to_list_to_order(struct page *page, struct list_head *list, + unsigned int new_order) { return 0; } @@ -519,17 +521,20 @@ static inline bool thp_migration_supported(void) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline int split_folio_to_list(struct folio *folio, - struct list_head *list) +static inline int split_folio_to_list_to_order(struct folio *folio, + struct list_head *list, int new_order) { - return split_huge_page_to_list(&folio->page, list); + return split_huge_page_to_list_to_order(&folio->page, list, new_order); } -static inline int split_folio(struct folio *folio) +static inline int split_folio_to_order(struct folio *folio, int new_order) { - return split_folio_to_list(folio, NULL); + return split_folio_to_list_to_order(folio, NULL, new_order); } +#define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0) +#define split_folio(f) split_folio_to_order(f, 0) + /* * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to * limitations in the implementation like arm64 MTE can override this to diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c1ee640d87b1..b06f7c426d38 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -178,7 +178,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage); extern int sysctl_hugetlb_shm_group; -extern struct list_head huge_boot_pages; +extern struct list_head huge_boot_pages[MAX_NUMNODES]; /* arch callbacks */ @@ -554,17 +554,13 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } -extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); -static inline bool is_file_hugepages(struct file *file) +static inline bool is_file_hugepages(const struct file *file) { - if (file->f_op == &hugetlbfs_file_operations) - return true; - - return is_file_shm_hugepages(file); + return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 8cd6a6b33593..edf96f249eb5 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -141,6 +141,7 @@ enum hwmon_in_attributes { hwmon_in_rated_min, hwmon_in_rated_max, hwmon_in_beep, + hwmon_in_fault, }; #define HWMON_I_ENABLE BIT(hwmon_in_enable) @@ -162,6 +163,7 @@ enum hwmon_in_attributes { #define HWMON_I_RATED_MIN BIT(hwmon_in_rated_min) #define HWMON_I_RATED_MAX BIT(hwmon_in_rated_max) #define HWMON_I_BEEP BIT(hwmon_in_beep) +#define HWMON_I_FAULT BIT(hwmon_in_fault) enum hwmon_curr_attributes { hwmon_curr_enable, @@ -293,6 +295,8 @@ enum hwmon_humidity_attributes { hwmon_humidity_fault, hwmon_humidity_rated_min, hwmon_humidity_rated_max, + hwmon_humidity_min_alarm, + hwmon_humidity_max_alarm, }; #define HWMON_H_ENABLE BIT(hwmon_humidity_enable) @@ -306,6 +310,8 @@ enum hwmon_humidity_attributes { #define HWMON_H_FAULT BIT(hwmon_humidity_fault) #define HWMON_H_RATED_MIN BIT(hwmon_humidity_rated_min) #define HWMON_H_RATED_MAX BIT(hwmon_humidity_rated_max) +#define HWMON_H_MIN_ALARM BIT(hwmon_humidity_min_alarm) +#define HWMON_H_MAX_ALARM BIT(hwmon_humidity_max_alarm) enum hwmon_fan_attributes { hwmon_fan_enable, @@ -425,12 +431,12 @@ struct hwmon_channel_info { const u32 *config; }; -#define HWMON_CHANNEL_INFO(stype, ...) \ - (&(struct hwmon_channel_info) { \ - .type = hwmon_##stype, \ - .config = (u32 []) { \ - __VA_ARGS__, 0 \ - } \ +#define HWMON_CHANNEL_INFO(stype, ...) \ + (&(const struct hwmon_channel_info) { \ + .type = hwmon_##stype, \ + .config = (const u32 []) { \ + __VA_ARGS__, 0 \ + } \ }) /** diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6ef0557b4bff..96ceb4095425 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -832,6 +832,7 @@ struct vmbus_gpadl { u32 gpadl_handle; u32 size; void *buffer; + bool decrypted; }; struct vmbus_channel { diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 652ecb7abeda..5e6cd43a6dbd 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -24,8 +24,8 @@ #include <uapi/linux/i2c.h> extern const struct bus_type i2c_bus_type; -extern struct device_type i2c_adapter_type; -extern struct device_type i2c_client_type; +extern const struct device_type i2c_adapter_type; +extern const struct device_type i2c_client_type; /* --- General options ------------------------------------------------ */ @@ -931,7 +931,7 @@ static inline int i2c_adapter_id(struct i2c_adapter *adap) static inline u8 i2c_8bit_addr_from_msg(const struct i2c_msg *msg) { - return (msg->addr << 1) | (msg->flags & I2C_M_RD ? 1 : 0); + return (msg->addr << 1) | (msg->flags & I2C_M_RD); } u8 *i2c_get_dma_safe_msg_buf(struct i2c_msg *msg, unsigned int threshold); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 3385a2cc5b09..de2dce743ee2 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1287,6 +1287,24 @@ struct ieee80211_ttlm_elem { u8 optional[]; } __packed; +/** + * struct ieee80211_bss_load_elem - BSS Load elemen + * + * Defined in section 9.4.2.26 in IEEE 802.11-REVme D4.1 + * + * @sta_count: total number of STAs currently associated with the AP. + * @channel_util: Percentage of time that the access point sensed the channel + * was busy. This value is in range [0, 255], the highest value means + * 100% busy. + * @avail_admission_capa: remaining amount of medium time used for admission + * control. + */ +struct ieee80211_bss_load_elem { + __le16 sta_count; + u8 channel_util; + __le16 avail_admission_capa; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -2742,9 +2760,11 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 -#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 -#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 -#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 +#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 +#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 +#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP 3 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP 4 /** * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field @@ -5166,7 +5186,7 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) bool check_common_len = false; u16 control; - if (len < fixed) + if (!data || len < fixed) return false; control = le16_to_cpu(mle->control); @@ -5302,7 +5322,7 @@ static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, info_len += 1; return prof->sta_info_len >= info_len && - fixed + prof->sta_info_len <= len; + fixed + prof->sta_info_len - 1 <= len; } /** diff --git a/include/linux/iio/adc/adi-axi-adc.h b/include/linux/iio/adc/adi-axi-adc.h deleted file mode 100644 index b7904992d561..000000000000 --- a/include/linux/iio/adc/adi-axi-adc.h +++ /dev/null @@ -1,68 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Analog Devices Generic AXI ADC IP core driver/library - * Link: https://wiki.analog.com/resources/fpga/docs/axi_adc_ip - * - * Copyright 2012-2020 Analog Devices Inc. - */ -#ifndef __ADI_AXI_ADC_H__ -#define __ADI_AXI_ADC_H__ - -struct device; -struct iio_chan_spec; - -/** - * struct adi_axi_adc_chip_info - Chip specific information - * @name Chip name - * @id Chip ID (usually product ID) - * @channels Channel specifications of type @struct iio_chan_spec - * @num_channels Number of @channels - * @scale_table Supported scales by the chip; tuples of 2 ints - * @num_scales Number of scales in the table - * @max_rate Maximum sampling rate supported by the device - */ -struct adi_axi_adc_chip_info { - const char *name; - unsigned int id; - - const struct iio_chan_spec *channels; - unsigned int num_channels; - - const unsigned int (*scale_table)[2]; - int num_scales; - - unsigned long max_rate; -}; - -/** - * struct adi_axi_adc_conv - data of the ADC attached to the AXI ADC - * @chip_info chip info details for the client ADC - * @preenable_setup op to run in the client before enabling the AXI ADC - * @reg_access IIO debugfs_reg_access hook for the client ADC - * @read_raw IIO read_raw hook for the client ADC - * @write_raw IIO write_raw hook for the client ADC - * @read_avail IIO read_avail hook for the client ADC - */ -struct adi_axi_adc_conv { - const struct adi_axi_adc_chip_info *chip_info; - - int (*preenable_setup)(struct adi_axi_adc_conv *conv); - int (*reg_access)(struct adi_axi_adc_conv *conv, unsigned int reg, - unsigned int writeval, unsigned int *readval); - int (*read_raw)(struct adi_axi_adc_conv *conv, - struct iio_chan_spec const *chan, - int *val, int *val2, long mask); - int (*write_raw)(struct adi_axi_adc_conv *conv, - struct iio_chan_spec const *chan, - int val, int val2, long mask); - int (*read_avail)(struct adi_axi_adc_conv *conv, - struct iio_chan_spec const *chan, - const int **val, int *type, int *length, long mask); -}; - -struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev, - size_t sizeof_priv); - -void *adi_axi_adc_conv_priv(struct adi_axi_adc_conv *conv); - -#endif diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h new file mode 100644 index 000000000000..a6d79381866e --- /dev/null +++ b/include/linux/iio/backend.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _IIO_BACKEND_H_ +#define _IIO_BACKEND_H_ + +#include <linux/types.h> + +struct fwnode_handle; +struct iio_backend; +struct device; +struct iio_dev; + +enum iio_backend_data_type { + IIO_BACKEND_TWOS_COMPLEMENT, + IIO_BACKEND_OFFSET_BINARY, + IIO_BACKEND_DATA_TYPE_MAX +}; + +/** + * struct iio_backend_data_fmt - Backend data format + * @type: Data type. + * @sign_extend: Bool to tell if the data is sign extended. + * @enable: Enable/Disable the data format module. If disabled, + * not formatting will happen. + */ +struct iio_backend_data_fmt { + enum iio_backend_data_type type; + bool sign_extend; + bool enable; +}; + +/** + * struct iio_backend_ops - operations structure for an iio_backend + * @enable: Enable backend. + * @disable: Disable backend. + * @chan_enable: Enable one channel. + * @chan_disable: Disable one channel. + * @data_format_set: Configure the data format for a specific channel. + * @request_buffer: Request an IIO buffer. + * @free_buffer: Free an IIO buffer. + **/ +struct iio_backend_ops { + int (*enable)(struct iio_backend *back); + void (*disable)(struct iio_backend *back); + int (*chan_enable)(struct iio_backend *back, unsigned int chan); + int (*chan_disable)(struct iio_backend *back, unsigned int chan); + int (*data_format_set)(struct iio_backend *back, unsigned int chan, + const struct iio_backend_data_fmt *data); + struct iio_buffer *(*request_buffer)(struct iio_backend *back, + struct iio_dev *indio_dev); + void (*free_buffer)(struct iio_backend *back, + struct iio_buffer *buffer); +}; + +int iio_backend_chan_enable(struct iio_backend *back, unsigned int chan); +int iio_backend_chan_disable(struct iio_backend *back, unsigned int chan); +int devm_iio_backend_enable(struct device *dev, struct iio_backend *back); +int iio_backend_data_format_set(struct iio_backend *back, unsigned int chan, + const struct iio_backend_data_fmt *data); +int devm_iio_backend_request_buffer(struct device *dev, + struct iio_backend *back, + struct iio_dev *indio_dev); + +void *iio_backend_get_priv(const struct iio_backend *conv); +struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name); +struct iio_backend * +__devm_iio_backend_get_from_fwnode_lookup(struct device *dev, + struct fwnode_handle *fwnode); + +int devm_iio_backend_register(struct device *dev, + const struct iio_backend_ops *ops, void *priv); + +#endif diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h index 5c355be89814..cbb8ba957fad 100644 --- a/include/linux/iio/buffer-dmaengine.h +++ b/include/linux/iio/buffer-dmaengine.h @@ -10,6 +10,9 @@ struct iio_dev; struct device; +struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, + const char *channel); +void iio_dmaengine_buffer_free(struct iio_buffer *buffer); int devm_iio_dmaengine_buffer_setup(struct device *dev, struct iio_dev *indio_dev, const char *channel); diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index c5b36d2c1e73..e370a7bb3300 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -9,6 +9,7 @@ #include <linux/device.h> #include <linux/cdev.h> +#include <linux/cleanup.h> #include <linux/slab.h> #include <linux/iio/types.h> /* IIO TODO LIST */ @@ -638,10 +639,37 @@ int __devm_iio_device_register(struct device *dev, struct iio_dev *indio_dev, int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp); int iio_device_claim_direct_mode(struct iio_dev *indio_dev); void iio_device_release_direct_mode(struct iio_dev *indio_dev); + +/* + * This autocleanup logic is normally used via + * iio_device_claim_direct_scoped(). + */ +DEFINE_GUARD(iio_claim_direct, struct iio_dev *, iio_device_claim_direct_mode(_T), + iio_device_release_direct_mode(_T)) + +DEFINE_GUARD_COND(iio_claim_direct, _try, ({ + struct iio_dev *dev; + int d = iio_device_claim_direct_mode(_T); + + if (d < 0) + dev = NULL; + else + dev = _T; + dev; + })) + +/** + * iio_device_claim_direct_scoped() - Scoped call to iio_device_claim_direct. + * @fail: What to do on failure to claim device. + * @iio_dev: Pointer to the IIO devices structure + */ +#define iio_device_claim_direct_scoped(fail, iio_dev) \ + scoped_cond_guard(iio_claim_direct_try, fail, iio_dev) + int iio_device_claim_buffer_mode(struct iio_dev *indio_dev); void iio_device_release_buffer_mode(struct iio_dev *indio_dev); -extern struct bus_type iio_bus_type; +extern const struct bus_type iio_bus_type; /** * iio_device_put() - reference counted deallocation of struct device diff --git a/include/linux/init.h b/include/linux/init.h index 3fa3f6241350..58cef4c2e59a 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -168,12 +168,8 @@ extern initcall_entry_t __initcall_end[]; extern struct file_system_type rootfs_fs_type; -#if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX) extern bool rodata_enabled; -#endif -#ifdef CONFIG_STRICT_KERNEL_RWX void mark_rodata_ro(void); -#endif extern void (*late_time_init)(void); diff --git a/include/linux/input.h b/include/linux/input.h index de6503c0edb8..c22ac465254b 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -514,7 +514,7 @@ void input_enable_softrepeat(struct input_dev *dev, int delay, int period); bool input_device_enabled(struct input_dev *dev); -extern struct class input_class; +extern const struct class input_class; /** * struct ff_device - force-feedback part of an input device diff --git a/include/linux/input/navpoint.h b/include/linux/input/navpoint.h deleted file mode 100644 index 5192ae3f5ec1..000000000000 --- a/include/linux/input/navpoint.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 Paul Parsons <lost.distance@yahoo.com> - */ - -struct navpoint_platform_data { - int port; /* PXA SSP port for pxa_ssp_request() */ -}; diff --git a/include/linux/integrity.h b/include/linux/integrity.h index 459b79683783..f5842372359b 100644 --- a/include/linux/integrity.h +++ b/include/linux/integrity.h @@ -8,6 +8,7 @@ #define _LINUX_INTEGRITY_H #include <linux/fs.h> +#include <linux/iversion.h> enum integrity_status { INTEGRITY_PASS = 0, @@ -28,4 +29,37 @@ static inline void integrity_load_keys(void) } #endif /* CONFIG_INTEGRITY */ +/* An inode's attributes for detection of changes */ +struct integrity_inode_attributes { + u64 version; /* track inode changes */ + unsigned long ino; + dev_t dev; +}; + +/* + * On stacked filesystems the i_version alone is not enough to detect file data + * or metadata change. Additional metadata is required. + */ +static inline void +integrity_inode_attrs_store(struct integrity_inode_attributes *attrs, + u64 i_version, const struct inode *inode) +{ + attrs->version = i_version; + attrs->dev = inode->i_sb->s_dev; + attrs->ino = inode->i_ino; +} + +/* + * On stacked filesystems detect whether the inode or its content has changed. + */ +static inline bool +integrity_inode_attrs_changed(const struct integrity_inode_attributes *attrs, + const struct inode *inode) +{ + return (inode->i_sb->s_dev != attrs->dev || + inode->i_ino != attrs->ino || + !inode_eq_iversion(inode, attrs->version)); +} + + #endif /* _LINUX_INTEGRITY_H */ diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 33f21bd85dbf..c0397423d3a8 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -158,6 +158,26 @@ struct rapl_if_priv { void *rpi; }; +#ifdef CONFIG_PERF_EVENTS +/** + * struct rapl_package_pmu_data: Per package data for PMU support + * @scale: Scale of 2^-32 Joules for each energy counter increase. + * @lock: Lock to protect n_active and active_list. + * @n_active: Number of active events. + * @active_list: List of active events. + * @timer_interval: Maximum timer expiration time before counter overflow. + * @hrtimer: Periodically update the counter to prevent overflow. + */ +struct rapl_package_pmu_data { + u64 scale[RAPL_DOMAIN_MAX]; + raw_spinlock_t lock; + int n_active; + struct list_head active_list; + ktime_t timer_interval; + struct hrtimer hrtimer; +}; +#endif + /* maximum rapl package domain name: package-%d-die-%d */ #define PACKAGE_DOMAIN_NAME_LENGTH 30 @@ -176,10 +196,28 @@ struct rapl_package { struct cpumask cpumask; char name[PACKAGE_DOMAIN_NAME_LENGTH]; struct rapl_if_priv *priv; +#ifdef CONFIG_PERF_EVENTS + bool has_pmu; + struct rapl_package_pmu_data pmu_data; +#endif }; +struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_priv *priv, + bool id_is_cpu); +struct rapl_package *rapl_add_package_cpuslocked(int id, struct rapl_if_priv *priv, + bool id_is_cpu); +void rapl_remove_package_cpuslocked(struct rapl_package *rp); + struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, bool id_is_cpu); struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu); void rapl_remove_package(struct rapl_package *rp); +#ifdef CONFIG_PERF_EVENTS +int rapl_package_add_pmu(struct rapl_package *rp); +void rapl_package_remove_pmu(struct rapl_package *rp); +#else +static inline int rapl_package_add_pmu(struct rapl_package *rp) { return 0; } +static inline void rapl_package_remove_pmu(struct rapl_package *rp) { } +#endif + #endif /* __INTEL_RAPL_H__ */ diff --git a/include/linux/intel_tcc.h b/include/linux/intel_tcc.h index f422612c28d6..8ff8eabb4a98 100644 --- a/include/linux/intel_tcc.h +++ b/include/linux/intel_tcc.h @@ -13,6 +13,6 @@ int intel_tcc_get_tjmax(int cpu); int intel_tcc_get_offset(int cpu); int intel_tcc_set_offset(int cpu, int offset); -int intel_tcc_get_temp(int cpu, bool pkg); +int intel_tcc_get_temp(int cpu, int *temp, bool pkg); #endif /* __INTEL_TCC_H__ */ diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 7ba183f221f1..f5aef8784692 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -36,7 +36,7 @@ struct icc_onecell_data { struct icc_node *nodes[] __counted_by(num_nodes); }; -struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec, +struct icc_node *of_icc_xlate_onecell(const struct of_phandle_args *spec, void *data); /** @@ -65,8 +65,9 @@ struct icc_provider { u32 peak_bw, u32 *agg_avg, u32 *agg_peak); void (*pre_aggregate)(struct icc_node *node); int (*get_bw)(struct icc_node *node, u32 *avg, u32 *peak); - struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data); - struct icc_node_data* (*xlate_extended)(struct of_phandle_args *spec, void *data); + struct icc_node* (*xlate)(const struct of_phandle_args *spec, void *data); + struct icc_node_data* (*xlate_extended)(const struct of_phandle_args *spec, + void *data); struct device *dev; int users; bool inter_set; @@ -124,7 +125,7 @@ int icc_nodes_remove(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); +struct icc_node_data *of_icc_get_from_provider(const struct of_phandle_args *spec); void icc_sync_state(struct device *dev); #else @@ -171,7 +172,7 @@ static inline int icc_provider_register(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) +static inline struct icc_node_data *of_icc_get_from_provider(const struct of_phandle_args *spec) { return ERR_PTR(-ENOTSUPP); } diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 76121c2bb4f8..5c9bdd3ffccc 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -67,6 +67,8 @@ * later. * IRQF_NO_DEBUG - Exclude from runnaway detection for IPI and similar handlers, * depends on IRQF_PERCPU. + * IRQF_COND_ONESHOT - Agree to do IRQF_ONESHOT if already set for a shared + * interrupt. */ #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 @@ -82,6 +84,7 @@ #define IRQF_COND_SUSPEND 0x00040000 #define IRQF_NO_AUTOEN 0x00080000 #define IRQF_NO_DEBUG 0x00100000 +#define IRQF_COND_ONESHOT 0x00200000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 68ed6697fece..e123d5e17b52 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -11,7 +11,6 @@ void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); const char *io_uring_get_opcode(u8 opcode); -int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) @@ -45,11 +44,6 @@ static inline const char *io_uring_get_opcode(u8 opcode) { return ""; } -static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, - unsigned int issue_flags) -{ - return -EOPNOTSUPP; -} static inline bool io_is_uring_fops(struct file *file) { return false; diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index e453a997c060..447fbfd32215 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -26,12 +26,25 @@ static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); + +/* + * Completes the request, i.e. posts an io_uring CQE and deallocates @ioucmd + * and the corresponding io_uring request. + * + * Note: the caller should never hard code @issue_flags and is only allowed + * to pass the mask provided by the core io_uring code. + */ void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, unsigned issue_flags); + void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned), unsigned flags); +/* + * Note: the caller should never hard code @issue_flags and only use the + * mask provided by the core io_uring code. + */ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, unsigned int issue_flags); @@ -56,6 +69,17 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, } #endif +/* + * Polled completions must ensure they are coming from a poll queue, and + * hence are completed inside the usual poll handling loops. + */ +static inline void io_uring_cmd_iopoll_done(struct io_uring_cmd *ioucmd, + ssize_t ret, ssize_t res2) +{ + lockdep_assert(in_task()); + io_uring_cmd_done(ioucmd, ret, res2, 0); +} + /* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */ static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned)) diff --git a/include/linux/io_uring/net.h b/include/linux/io_uring/net.h new file mode 100644 index 000000000000..b58f39fed4d5 --- /dev/null +++ b/include/linux/io_uring/net.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_IO_URING_NET_H +#define _LINUX_IO_URING_NET_H + +struct io_uring_cmd; + +#if defined(CONFIG_IO_URING) +int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); + +#else +static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + return -EOPNOTSUPP; +} +#endif + +#endif diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index e24893625085..7a6b190c7da7 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -13,7 +13,7 @@ enum { * A hint to not wake right away but delay until there are enough of * tw's queued to match the number of CQEs the task is waiting for. * - * Must not be used wirh requests generating more than one CQE. + * Must not be used with requests generating more than one CQE. * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set. */ IOU_F_TWQ_LAZY_WAKE = 1, @@ -205,6 +205,7 @@ struct io_submit_state { bool plug_started; bool need_plug; + bool cq_flush; unsigned short submit_nr; unsigned int cqes_count; struct blk_plug plug; @@ -219,7 +220,7 @@ struct io_ev_fd { }; struct io_alloc_cache { - struct io_wq_work_node list; + void **entries; unsigned int nr_cached; unsigned int max_cached; size_t elem_size; @@ -294,12 +295,13 @@ struct io_ring_ctx { struct io_submit_state submit_state; - struct io_buffer_list *io_bl; struct xarray io_bl_xa; struct io_hash_table cancel_table_locked; struct io_alloc_cache apoll_cache; struct io_alloc_cache netmsg_cache; + struct io_alloc_cache rw_cache; + struct io_alloc_cache uring_cache; /* * Any cancelable uring_cmd is added to this list in @@ -342,14 +344,8 @@ struct io_ring_ctx { unsigned cq_last_tm_flush; } ____cacheline_aligned_in_smp; - struct io_uring_cqe completion_cqes[16]; - spinlock_t completion_lock; - /* IRQ completion list, under ->completion_lock */ - unsigned int locked_free_nr; - struct io_wq_work_list locked_free_list; - struct list_head io_buffers_comp; struct list_head cq_overflow_list; struct io_hash_table cancel_table; @@ -372,9 +368,6 @@ struct io_ring_ctx { struct list_head io_buffers_cache; - /* deferred free list, protected by ->uring_lock */ - struct hlist_head io_buf_list; - /* Keep this last, we don't need it for the fast path */ struct wait_queue_head poll_wq; struct io_restriction restrictions; @@ -439,8 +432,6 @@ struct io_ring_ctx { }; struct io_tw_state { - /* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */ - bool locked; }; enum { @@ -481,6 +472,7 @@ enum { REQ_F_CAN_POLL_BIT, REQ_F_BL_EMPTY_BIT, REQ_F_BL_NO_RECYCLE_BIT, + REQ_F_BUFFERS_COMMIT_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -559,6 +551,8 @@ enum { REQ_F_BL_EMPTY = IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT), /* don't recycle provided buffers for this request */ REQ_F_BL_NO_RECYCLE = IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT), + /* buffer ring head needs incrementing on put */ + REQ_F_BUFFERS_COMMIT = IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5e27cb3a3be9..2e925b5eba53 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -14,7 +14,6 @@ #include <linux/err.h> #include <linux/of.h> #include <linux/iova_bitmap.h> -#include <uapi/linux/iommu.h> #define IOMMU_READ (1 << 0) #define IOMMU_WRITE (1 << 1) @@ -41,8 +40,110 @@ struct iommu_domain_ops; struct iommu_dirty_ops; struct notifier_block; struct iommu_sva; -struct iommu_fault_event; struct iommu_dma_cookie; +struct iommu_fault_param; + +#define IOMMU_FAULT_PERM_READ (1 << 0) /* read */ +#define IOMMU_FAULT_PERM_WRITE (1 << 1) /* write */ +#define IOMMU_FAULT_PERM_EXEC (1 << 2) /* exec */ +#define IOMMU_FAULT_PERM_PRIV (1 << 3) /* privileged */ + +/* Generic fault types, can be expanded IRQ remapping fault */ +enum iommu_fault_type { + IOMMU_FAULT_PAGE_REQ = 1, /* page request fault */ +}; + +/** + * struct iommu_fault_page_request - Page Request data + * @flags: encodes whether the corresponding fields are valid and whether this + * is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values). + * When IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID is set, the page response + * must have the same PASID value as the page request. When it is clear, + * the page response should not have a PASID. + * @pasid: Process Address Space ID + * @grpid: Page Request Group Index + * @perm: requested page permissions (IOMMU_FAULT_PERM_* values) + * @addr: page address + * @private_data: device-specific private information + */ +struct iommu_fault_page_request { +#define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID (1 << 0) +#define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE (1 << 1) +#define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA (1 << 2) +#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 3) + u32 flags; + u32 pasid; + u32 grpid; + u32 perm; + u64 addr; + u64 private_data[2]; +}; + +/** + * struct iommu_fault - Generic fault data + * @type: fault type from &enum iommu_fault_type + * @prm: Page Request message, when @type is %IOMMU_FAULT_PAGE_REQ + */ +struct iommu_fault { + u32 type; + struct iommu_fault_page_request prm; +}; + +/** + * enum iommu_page_response_code - Return status of fault handlers + * @IOMMU_PAGE_RESP_SUCCESS: Fault has been handled and the page tables + * populated, retry the access. This is "Success" in PCI PRI. + * @IOMMU_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from + * this device if possible. This is "Response Failure" in PCI PRI. + * @IOMMU_PAGE_RESP_INVALID: Could not handle this fault, don't retry the + * access. This is "Invalid Request" in PCI PRI. + */ +enum iommu_page_response_code { + IOMMU_PAGE_RESP_SUCCESS = 0, + IOMMU_PAGE_RESP_INVALID, + IOMMU_PAGE_RESP_FAILURE, +}; + +/** + * struct iommu_page_response - Generic page response information + * @pasid: Process Address Space ID + * @grpid: Page Request Group Index + * @code: response code from &enum iommu_page_response_code + */ +struct iommu_page_response { + u32 pasid; + u32 grpid; + u32 code; +}; + +struct iopf_fault { + struct iommu_fault fault; + /* node for pending lists */ + struct list_head list; +}; + +struct iopf_group { + struct iopf_fault last_fault; + struct list_head faults; + /* list node for iommu_fault_param::faults */ + struct list_head pending_node; + struct work_struct work; + struct iommu_domain *domain; + /* The device's fault data parameter. */ + struct iommu_fault_param *fault_param; +}; + +/** + * struct iopf_queue - IO Page Fault queue + * @wq: the fault workqueue + * @devices: devices attached to this queue + * @lock: protects the device list + */ +struct iopf_queue { + struct workqueue_struct *wq; + struct list_head devices; + struct mutex lock; +}; /* iommu fault flags */ #define IOMMU_FAULT_READ 0x0 @@ -50,7 +151,6 @@ struct iommu_dma_cookie; typedef int (*iommu_fault_handler_t)(struct iommu_domain *, struct device *, unsigned long, int, void *); -typedef int (*iommu_dev_fault_handler_t)(struct iommu_fault *, void *); struct iommu_domain_geometry { dma_addr_t aperture_start; /* First address that can be mapped */ @@ -110,8 +210,7 @@ struct iommu_domain { unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ struct iommu_domain_geometry geometry; struct iommu_dma_cookie *iova_cookie; - enum iommu_page_response_code (*iopf_handler)(struct iommu_fault *fault, - void *data); + int (*iopf_handler)(struct iopf_group *group); void *fault_data; union { struct { @@ -468,16 +567,15 @@ struct iommu_ops { /* Request/Free a list of reserved regions for a device */ void (*get_resv_regions)(struct device *dev, struct list_head *list); - int (*of_xlate)(struct device *dev, struct of_phandle_args *args); + int (*of_xlate)(struct device *dev, const struct of_phandle_args *args); bool (*is_attach_deferred)(struct device *dev); /* Per device IOMMU features */ int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f); int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f); - int (*page_response)(struct device *dev, - struct iommu_fault_event *evt, - struct iommu_page_response *msg); + void (*page_response)(struct device *dev, struct iopf_fault *evt, + struct iommu_page_response *msg); int (*def_domain_type)(struct device *dev); void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid); @@ -487,6 +585,7 @@ struct iommu_ops { struct module *owner; struct iommu_domain *identity_domain; struct iommu_domain *blocked_domain; + struct iommu_domain *release_domain; struct iommu_domain *default_domain; }; @@ -578,38 +677,34 @@ struct iommu_device { }; /** - * struct iommu_fault_event - Generic fault event - * - * Can represent recoverable faults such as a page requests or - * unrecoverable faults such as DMA or IRQ remapping faults. - * - * @fault: fault descriptor - * @list: pending fault event list, used for tracking responses - */ -struct iommu_fault_event { - struct iommu_fault fault; - struct list_head list; -}; - -/** * struct iommu_fault_param - per-device IOMMU fault data - * @handler: Callback function to handle IOMMU faults at device level - * @data: handler private data - * @faults: holds the pending faults which needs response * @lock: protect pending faults list + * @users: user counter to manage the lifetime of the data + * @rcu: rcu head for kfree_rcu() + * @dev: the device that owns this param + * @queue: IOPF queue + * @queue_list: index into queue->devices + * @partial: faults that are part of a Page Request Group for which the last + * request hasn't been submitted yet. + * @faults: holds the pending faults which need response */ struct iommu_fault_param { - iommu_dev_fault_handler_t handler; - void *data; - struct list_head faults; struct mutex lock; + refcount_t users; + struct rcu_head rcu; + + struct device *dev; + struct iopf_queue *queue; + struct list_head queue_list; + + struct list_head partial; + struct list_head faults; }; /** * struct dev_iommu - Collection of per-device IOMMU data * * @fault_param: IOMMU detected device fault reporting data - * @iopf_param: I/O Page Fault queue and data * @fwspec: IOMMU fwspec data * @iommu_dev: IOMMU device this device is linked to * @priv: IOMMU Driver private data @@ -624,8 +719,7 @@ struct iommu_fault_param { */ struct dev_iommu { struct mutex lock; - struct iommu_fault_param *fault_param; - struct iopf_device_param *iopf_param; + struct iommu_fault_param __rcu *fault_param; struct iommu_fwspec *fwspec; struct iommu_device *iommu_dev; void *priv; @@ -654,6 +748,22 @@ static inline struct iommu_device *dev_to_iommu_device(struct device *dev) return (struct iommu_device *)dev_get_drvdata(dev); } +/** + * iommu_get_iommu_dev - Get iommu_device for a device + * @dev: an end-point device + * + * Note that this function must be called from the iommu_ops + * to retrieve the iommu_device for a device, which the core code + * guarentees it will not invoke the op without an attached iommu. + */ +static inline struct iommu_device *__iommu_get_iommu_dev(struct device *dev) +{ + return dev->iommu->iommu_dev; +} + +#define iommu_get_iommu_dev(dev, type, member) \ + container_of(__iommu_get_iommu_dev(dev), type, member) + static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) { *gather = (struct iommu_iotlb_gather) { @@ -719,16 +829,6 @@ extern int iommu_group_for_each_dev(struct iommu_group *group, void *data, extern struct iommu_group *iommu_group_get(struct device *dev); extern struct iommu_group *iommu_group_ref_get(struct iommu_group *group); extern void iommu_group_put(struct iommu_group *group); -extern int iommu_register_device_fault_handler(struct device *dev, - iommu_dev_fault_handler_t handler, - void *data); - -extern int iommu_unregister_device_fault_handler(struct device *dev); - -extern int iommu_report_device_fault(struct device *dev, - struct iommu_fault_event *evt); -extern int iommu_page_response(struct device *dev, - struct iommu_page_response *msg); extern int iommu_group_id(struct iommu_group *group); extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *); @@ -905,8 +1005,8 @@ struct iommu_mm_data { int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, const struct iommu_ops *ops); void iommu_fwspec_free(struct device *dev); -int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids); -const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode); +int iommu_fwspec_add_ids(struct device *dev, const u32 *ids, int num_ids); +const struct iommu_ops *iommu_ops_from_fwnode(const struct fwnode_handle *fwnode); static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { @@ -948,8 +1048,6 @@ bool iommu_group_dma_owner_claimed(struct iommu_group *group); int iommu_device_claim_dma_owner(struct device *dev, void *owner); void iommu_device_release_dma_owner(struct device *dev); -struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, - struct mm_struct *mm); int iommu_attach_device_pasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid); void iommu_detach_device_pasid(struct iommu_domain *domain, @@ -1138,31 +1236,6 @@ static inline void iommu_group_put(struct iommu_group *group) { } -static inline -int iommu_register_device_fault_handler(struct device *dev, - iommu_dev_fault_handler_t handler, - void *data) -{ - return -ENODEV; -} - -static inline int iommu_unregister_device_fault_handler(struct device *dev) -{ - return 0; -} - -static inline -int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt) -{ - return -ENODEV; -} - -static inline int iommu_page_response(struct device *dev, - struct iommu_page_response *msg) -{ - return -ENODEV; -} - static inline int iommu_group_id(struct iommu_group *group) { return -ENODEV; @@ -1256,7 +1329,7 @@ static inline int iommu_fwspec_add_ids(struct device *dev, u32 *ids, } static inline -const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) +const struct iommu_ops *iommu_ops_from_fwnode(const struct fwnode_handle *fwnode) { return NULL; } @@ -1311,12 +1384,6 @@ static inline int iommu_device_claim_dma_owner(struct device *dev, void *owner) return -ENODEV; } -static inline struct iommu_domain * -iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm) -{ - return NULL; -} - static inline int iommu_attach_device_pasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid) { @@ -1343,6 +1410,14 @@ static inline ioasid_t iommu_alloc_global_pasid(struct device *dev) static inline void iommu_free_global_pasid(ioasid_t pasid) {} #endif /* CONFIG_IOMMU_API */ +#if IS_ENABLED(CONFIG_LOCKDEP) && IS_ENABLED(CONFIG_IOMMU_API) +void iommu_group_mutex_assert(struct device *dev); +#else +static inline void iommu_group_mutex_assert(struct device *dev) +{ +} +#endif + /** * iommu_map_sgtable - Map the given buffer to the IOMMU domain * @domain: The IOMMU domain to perform the mapping @@ -1456,6 +1531,8 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); void iommu_sva_unbind_device(struct iommu_sva *handle); u32 iommu_sva_get_pasid(struct iommu_sva *handle); +struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, + struct mm_struct *mm); #else static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) @@ -1480,6 +1557,68 @@ static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm) } static inline void mm_pasid_drop(struct mm_struct *mm) {} + +static inline struct iommu_domain * +iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm) +{ + return NULL; +} #endif /* CONFIG_IOMMU_SVA */ +#ifdef CONFIG_IOMMU_IOPF +int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev); +void iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev); +int iopf_queue_flush_dev(struct device *dev); +struct iopf_queue *iopf_queue_alloc(const char *name); +void iopf_queue_free(struct iopf_queue *queue); +int iopf_queue_discard_partial(struct iopf_queue *queue); +void iopf_free_group(struct iopf_group *group); +void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); +void iopf_group_response(struct iopf_group *group, + enum iommu_page_response_code status); +#else +static inline int +iopf_queue_add_device(struct iopf_queue *queue, struct device *dev) +{ + return -ENODEV; +} + +static inline void +iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev) +{ +} + +static inline int iopf_queue_flush_dev(struct device *dev) +{ + return -ENODEV; +} + +static inline struct iopf_queue *iopf_queue_alloc(const char *name) +{ + return NULL; +} + +static inline void iopf_queue_free(struct iopf_queue *queue) +{ +} + +static inline int iopf_queue_discard_partial(struct iopf_queue *queue) +{ + return -ENODEV; +} + +static inline void iopf_free_group(struct iopf_group *group) +{ +} + +static inline void +iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) +{ +} + +static inline void iopf_group_response(struct iopf_group *group, + enum iommu_page_response_code status) +{ +} +#endif /* CONFIG_IOMMU_IOPF */ #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h index e3649a6563dd..4696abfd311c 100644 --- a/include/linux/iosys-map.h +++ b/include/linux/iosys-map.h @@ -34,7 +34,7 @@ * the same driver for allocation, read and write operations. * * Open-coding access to :c:type:`struct iosys_map <iosys_map>` is considered - * bad style. Rather then accessing its fields directly, use one of the provided + * bad style. Rather than accessing its fields directly, use one of the provided * helper functions, or implement your own. For example, instances of * :c:type:`struct iosys_map <iosys_map>` can be initialized statically with * IOSYS_MAP_INIT_VADDR(), or at runtime with iosys_map_set_vaddr(). These diff --git a/include/linux/irq.h b/include/linux/irq.h index 97baa937ab5b..a217e1029c1d 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -115,7 +115,7 @@ enum { * Return value for chip->irq_set_affinity() * * IRQ_SET_MASK_OK - OK, core updates irq_common_data.affinity - * IRQ_SET_MASK_NOCPY - OK, chip did update irq_common_data.affinity + * IRQ_SET_MASK_NOCOPY - OK, chip did update irq_common_data.affinity * IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to * support stacked irqchips, which indicates skipping * all descendant irqchips. diff --git a/include/linux/irqchip/riscv-aplic.h b/include/linux/irqchip/riscv-aplic.h new file mode 100644 index 000000000000..ec8f7df50583 --- /dev/null +++ b/include/linux/irqchip/riscv-aplic.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + */ +#ifndef __LINUX_IRQCHIP_RISCV_APLIC_H +#define __LINUX_IRQCHIP_RISCV_APLIC_H + +#include <linux/bitops.h> + +#define APLIC_MAX_IDC BIT(14) +#define APLIC_MAX_SOURCE 1024 + +#define APLIC_DOMAINCFG 0x0000 +#define APLIC_DOMAINCFG_RDONLY 0x80000000 +#define APLIC_DOMAINCFG_IE BIT(8) +#define APLIC_DOMAINCFG_DM BIT(2) +#define APLIC_DOMAINCFG_BE BIT(0) + +#define APLIC_SOURCECFG_BASE 0x0004 +#define APLIC_SOURCECFG_D BIT(10) +#define APLIC_SOURCECFG_CHILDIDX_MASK 0x000003ff +#define APLIC_SOURCECFG_SM_MASK 0x00000007 +#define APLIC_SOURCECFG_SM_INACTIVE 0x0 +#define APLIC_SOURCECFG_SM_DETACH 0x1 +#define APLIC_SOURCECFG_SM_EDGE_RISE 0x4 +#define APLIC_SOURCECFG_SM_EDGE_FALL 0x5 +#define APLIC_SOURCECFG_SM_LEVEL_HIGH 0x6 +#define APLIC_SOURCECFG_SM_LEVEL_LOW 0x7 + +#define APLIC_MMSICFGADDR 0x1bc0 +#define APLIC_MMSICFGADDRH 0x1bc4 +#define APLIC_SMSICFGADDR 0x1bc8 +#define APLIC_SMSICFGADDRH 0x1bcc + +#ifdef CONFIG_RISCV_M_MODE +#define APLIC_xMSICFGADDR APLIC_MMSICFGADDR +#define APLIC_xMSICFGADDRH APLIC_MMSICFGADDRH +#else +#define APLIC_xMSICFGADDR APLIC_SMSICFGADDR +#define APLIC_xMSICFGADDRH APLIC_SMSICFGADDRH +#endif + +#define APLIC_xMSICFGADDRH_L BIT(31) +#define APLIC_xMSICFGADDRH_HHXS_MASK 0x1f +#define APLIC_xMSICFGADDRH_HHXS_SHIFT 24 +#define APLIC_xMSICFGADDRH_HHXS (APLIC_xMSICFGADDRH_HHXS_MASK << \ + APLIC_xMSICFGADDRH_HHXS_SHIFT) +#define APLIC_xMSICFGADDRH_LHXS_MASK 0x7 +#define APLIC_xMSICFGADDRH_LHXS_SHIFT 20 +#define APLIC_xMSICFGADDRH_LHXS (APLIC_xMSICFGADDRH_LHXS_MASK << \ + APLIC_xMSICFGADDRH_LHXS_SHIFT) +#define APLIC_xMSICFGADDRH_HHXW_MASK 0x7 +#define APLIC_xMSICFGADDRH_HHXW_SHIFT 16 +#define APLIC_xMSICFGADDRH_HHXW (APLIC_xMSICFGADDRH_HHXW_MASK << \ + APLIC_xMSICFGADDRH_HHXW_SHIFT) +#define APLIC_xMSICFGADDRH_LHXW_MASK 0xf +#define APLIC_xMSICFGADDRH_LHXW_SHIFT 12 +#define APLIC_xMSICFGADDRH_LHXW (APLIC_xMSICFGADDRH_LHXW_MASK << \ + APLIC_xMSICFGADDRH_LHXW_SHIFT) +#define APLIC_xMSICFGADDRH_BAPPN_MASK 0xfff +#define APLIC_xMSICFGADDRH_BAPPN_SHIFT 0 +#define APLIC_xMSICFGADDRH_BAPPN (APLIC_xMSICFGADDRH_BAPPN_MASK << \ + APLIC_xMSICFGADDRH_BAPPN_SHIFT) + +#define APLIC_xMSICFGADDR_PPN_SHIFT 12 + +#define APLIC_xMSICFGADDR_PPN_HART(__lhxs) \ + (BIT(__lhxs) - 1) + +#define APLIC_xMSICFGADDR_PPN_LHX_MASK(__lhxw) \ + (BIT(__lhxw) - 1) +#define APLIC_xMSICFGADDR_PPN_LHX_SHIFT(__lhxs) \ + ((__lhxs)) +#define APLIC_xMSICFGADDR_PPN_LHX(__lhxw, __lhxs) \ + (APLIC_xMSICFGADDR_PPN_LHX_MASK(__lhxw) << \ + APLIC_xMSICFGADDR_PPN_LHX_SHIFT(__lhxs)) + +#define APLIC_xMSICFGADDR_PPN_HHX_MASK(__hhxw) \ + (BIT(__hhxw) - 1) +#define APLIC_xMSICFGADDR_PPN_HHX_SHIFT(__hhxs) \ + ((__hhxs) + APLIC_xMSICFGADDR_PPN_SHIFT) +#define APLIC_xMSICFGADDR_PPN_HHX(__hhxw, __hhxs) \ + (APLIC_xMSICFGADDR_PPN_HHX_MASK(__hhxw) << \ + APLIC_xMSICFGADDR_PPN_HHX_SHIFT(__hhxs)) + +#define APLIC_IRQBITS_PER_REG 32 + +#define APLIC_SETIP_BASE 0x1c00 +#define APLIC_SETIPNUM 0x1cdc + +#define APLIC_CLRIP_BASE 0x1d00 +#define APLIC_CLRIPNUM 0x1ddc + +#define APLIC_SETIE_BASE 0x1e00 +#define APLIC_SETIENUM 0x1edc + +#define APLIC_CLRIE_BASE 0x1f00 +#define APLIC_CLRIENUM 0x1fdc + +#define APLIC_SETIPNUM_LE 0x2000 +#define APLIC_SETIPNUM_BE 0x2004 + +#define APLIC_GENMSI 0x3000 + +#define APLIC_TARGET_BASE 0x3004 +#define APLIC_TARGET_HART_IDX_SHIFT 18 +#define APLIC_TARGET_HART_IDX_MASK 0x3fff +#define APLIC_TARGET_HART_IDX (APLIC_TARGET_HART_IDX_MASK << \ + APLIC_TARGET_HART_IDX_SHIFT) +#define APLIC_TARGET_GUEST_IDX_SHIFT 12 +#define APLIC_TARGET_GUEST_IDX_MASK 0x3f +#define APLIC_TARGET_GUEST_IDX (APLIC_TARGET_GUEST_IDX_MASK << \ + APLIC_TARGET_GUEST_IDX_SHIFT) +#define APLIC_TARGET_IPRIO_SHIFT 0 +#define APLIC_TARGET_IPRIO_MASK 0xff +#define APLIC_TARGET_IPRIO (APLIC_TARGET_IPRIO_MASK << \ + APLIC_TARGET_IPRIO_SHIFT) +#define APLIC_TARGET_EIID_SHIFT 0 +#define APLIC_TARGET_EIID_MASK 0x7ff +#define APLIC_TARGET_EIID (APLIC_TARGET_EIID_MASK << \ + APLIC_TARGET_EIID_SHIFT) + +#define APLIC_IDC_BASE 0x4000 +#define APLIC_IDC_SIZE 32 + +#define APLIC_IDC_IDELIVERY 0x00 + +#define APLIC_IDC_IFORCE 0x04 + +#define APLIC_IDC_ITHRESHOLD 0x08 + +#define APLIC_IDC_TOPI 0x18 +#define APLIC_IDC_TOPI_ID_SHIFT 16 +#define APLIC_IDC_TOPI_ID_MASK 0x3ff +#define APLIC_IDC_TOPI_ID (APLIC_IDC_TOPI_ID_MASK << \ + APLIC_IDC_TOPI_ID_SHIFT) +#define APLIC_IDC_TOPI_PRIO_SHIFT 0 +#define APLIC_IDC_TOPI_PRIO_MASK 0xff +#define APLIC_IDC_TOPI_PRIO (APLIC_IDC_TOPI_PRIO_MASK << \ + APLIC_IDC_TOPI_PRIO_SHIFT) + +#define APLIC_IDC_CLAIMI 0x1c + +#endif diff --git a/include/linux/irqchip/riscv-imsic.h b/include/linux/irqchip/riscv-imsic.h new file mode 100644 index 000000000000..faf0b800b1b0 --- /dev/null +++ b/include/linux/irqchip/riscv-imsic.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + */ +#ifndef __LINUX_IRQCHIP_RISCV_IMSIC_H +#define __LINUX_IRQCHIP_RISCV_IMSIC_H + +#include <linux/types.h> +#include <linux/bitops.h> +#include <asm/csr.h> + +#define IMSIC_MMIO_PAGE_SHIFT 12 +#define IMSIC_MMIO_PAGE_SZ BIT(IMSIC_MMIO_PAGE_SHIFT) +#define IMSIC_MMIO_PAGE_LE 0x00 +#define IMSIC_MMIO_PAGE_BE 0x04 + +#define IMSIC_MIN_ID 63 +#define IMSIC_MAX_ID 2048 + +#define IMSIC_EIDELIVERY 0x70 + +#define IMSIC_EITHRESHOLD 0x72 + +#define IMSIC_EIP0 0x80 +#define IMSIC_EIP63 0xbf +#define IMSIC_EIPx_BITS 32 + +#define IMSIC_EIE0 0xc0 +#define IMSIC_EIE63 0xff +#define IMSIC_EIEx_BITS 32 + +#define IMSIC_FIRST IMSIC_EIDELIVERY +#define IMSIC_LAST IMSIC_EIE63 + +#define IMSIC_MMIO_SETIPNUM_LE 0x00 +#define IMSIC_MMIO_SETIPNUM_BE 0x04 + +struct imsic_local_config { + phys_addr_t msi_pa; + void __iomem *msi_va; +}; + +struct imsic_global_config { + /* + * MSI Target Address Scheme + * + * XLEN-1 12 0 + * | | | + * ------------------------------------------------------------- + * |xxxxxx|Group Index|xxxxxxxxxxx|HART Index|Guest Index| 0 | + * ------------------------------------------------------------- + */ + + /* Bits representing Guest index, HART index, and Group index */ + u32 guest_index_bits; + u32 hart_index_bits; + u32 group_index_bits; + u32 group_index_shift; + + /* Global base address matching all target MSI addresses */ + phys_addr_t base_addr; + + /* Number of interrupt identities */ + u32 nr_ids; + + /* Number of guest interrupt identities */ + u32 nr_guest_ids; + + /* Per-CPU IMSIC addresses */ + struct imsic_local_config __percpu *local; +}; + +#ifdef CONFIG_RISCV_IMSIC + +const struct imsic_global_config *imsic_get_global_config(void); + +#else + +static inline const struct imsic_global_config *imsic_get_global_config(void) +{ + return NULL; +} + +#endif + +#endif diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index d9451d456a73..fd091c35d572 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -18,6 +18,18 @@ struct irq_domain; struct pt_regs; /** + * struct irqstat - interrupt statistics + * @cnt: real-time interrupt count + * @ref: snapshot of interrupt count + */ +struct irqstat { + unsigned int cnt; +#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT + unsigned int ref; +#endif +}; + +/** * struct irq_desc - interrupt descriptor * @irq_common_data: per irq and chip data passed down to chip functions * @kstat_irqs: irq stats per cpu @@ -55,7 +67,7 @@ struct pt_regs; struct irq_desc { struct irq_common_data irq_common_data; struct irq_data irq_data; - unsigned int __percpu *kstat_irqs; + struct irqstat __percpu *kstat_irqs; irq_flow_handler_t handle_irq; struct irqaction *action; /* IRQ action list */ unsigned int status_use_accessors; @@ -119,7 +131,7 @@ extern struct irq_desc irq_desc[NR_IRQS]; static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc, unsigned int cpu) { - return desc->kstat_irqs ? *per_cpu_ptr(desc->kstat_irqs, cpu) : 0; + return desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 147feebd508c..3f003d5fde53 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -114,7 +114,7 @@ do { \ # define lockdep_softirq_enter() do { } while (0) # define lockdep_softirq_exit() do { } while (0) # define lockdep_hrtimer_enter(__hrtimer) false -# define lockdep_hrtimer_exit(__context) do { } while (0) +# define lockdep_hrtimer_exit(__context) do { (void)(__context); } while (0) # define lockdep_posixtimer_enter() do { } while (0) # define lockdep_posixtimer_exit() do { } while (0) # define lockdep_irq_work_enter(__work) do { } while (0) diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index f0a949b7c973..f5a2727ca4a9 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -216,6 +216,7 @@ extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); +extern void jump_label_init_ro(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, @@ -265,6 +266,8 @@ static __always_inline void jump_label_init(void) static_key_initialized = true; } +static __always_inline void jump_label_init_ro(void) { } + static __always_inline bool static_key_false(struct static_key *key) { if (unlikely_notrace(static_key_count(key) > 0)) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d718fbec72dd..be2e8c0a187e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -215,6 +215,7 @@ enum ftrace_dump_mode { DUMP_NONE, DUMP_ALL, DUMP_ORIG, + DUMP_PARAM, }; #ifdef CONFIG_TRACING diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 9935f7ecbfb9..9c042c6384bb 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -79,6 +79,14 @@ static inline unsigned int kstat_cpu_softirqs_sum(int cpu) return sum; } +#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT +extern void kstat_snapshot_irqs(void); +extern unsigned int kstat_get_irq_since_snapshot(unsigned int irq); +#else +static inline void kstat_snapshot_irqs(void) { } +static inline unsigned int kstat_get_irq_since_snapshot(unsigned int irq) { return 0; } +#endif + /* * Number of interrupts per specific IRQ source, since bootup */ diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 99aaa050ccb7..87c79d076d6d 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -206,23 +206,25 @@ struct kernfs_node { const void *ns; /* namespace tag */ unsigned int hash; /* ns + name hash */ + unsigned short flags; + umode_t mode; + union { struct kernfs_elem_dir dir; struct kernfs_elem_symlink symlink; struct kernfs_elem_attr attr; }; - void *priv; - /* * 64bit unique ID. On 64bit ino setups, id is the ino. On 32bit, * the low 32bits are ino and upper generation. */ u64 id; - unsigned short flags; - umode_t mode; + void *priv; struct kernfs_iattrs *iattr; + + struct rcu_head rcu; }; /* diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 400cb6c02176..060835bb82d5 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -15,7 +15,8 @@ #if !defined(__ASSEMBLY__) -#include <linux/crash_core.h> +#include <linux/vmcore_info.h> +#include <linux/crash_reserve.h> #include <asm/io.h> #include <linux/range.h> @@ -31,6 +32,7 @@ extern note_buf_t __percpu *crash_notes; #include <linux/module.h> #include <linux/highmem.h> #include <asm/kexec.h> +#include <linux/crash_core.h> /* Verify architecture specific macros are defined */ @@ -378,13 +380,6 @@ extern struct page *kimage_alloc_control_pages(struct kimage *image, static inline int machine_kexec_post_load(struct kimage *image) { return 0; } #endif -extern void __crash_kexec(struct pt_regs *); -extern void crash_kexec(struct pt_regs *); -int kexec_should_crash(struct task_struct *); -int kexec_crash_loaded(void); -void crash_save_cpu(struct pt_regs *regs, int cpu); -extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); - extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; @@ -408,24 +403,6 @@ bool kexec_load_permitted(int kexec_image_type); /* flag to track if kexec reboot is in progress */ extern bool kexec_in_progress; -int crash_shrink_memory(unsigned long new_size); -ssize_t crash_get_memory_size(void); - -#ifndef arch_kexec_protect_crashkres -/* - * Protection mechanism for crashkernel reserved memory after - * the kdump kernel is loaded. - * - * Provide an empty default implementation here -- architecture - * code may override this - */ -static inline void arch_kexec_protect_crashkres(void) { } -#endif - -#ifndef arch_kexec_unprotect_crashkres -static inline void arch_kexec_unprotect_crashkres(void) { } -#endif - #ifndef page_to_boot_pfn static inline unsigned long page_to_boot_pfn(struct page *page) { @@ -482,24 +459,6 @@ static inline int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, g static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { } #endif -#ifndef arch_crash_handle_hotplug_event -static inline void arch_crash_handle_hotplug_event(struct kimage *image) { } -#endif - -int crash_check_update_elfcorehdr(void); - -#ifndef crash_hotplug_cpu_support -static inline int crash_hotplug_cpu_support(void) { return 0; } -#endif - -#ifndef crash_hotplug_memory_support -static inline int crash_hotplug_memory_support(void) { return 0; } -#endif - -#ifndef crash_get_elfcorehdr_size -static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; } -#endif - extern bool kexec_file_dbg_print; #define kexec_dprintk(fmt, ...) \ diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c30affcc43b4..c8219505a79f 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -38,7 +38,7 @@ extern char uevent_helper[]; #endif /* counter to tag the uevent, read only except for the kobject core */ -extern u64 uevent_seqnum; +extern atomic64_t uevent_seqnum; /* * The actions here must match the index to the string array diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 179df96b20f8..48f31dcd318a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -148,6 +148,11 @@ static inline bool kvm_is_error_hva(unsigned long addr) #endif +static inline bool kvm_is_error_gpa(gpa_t gpa) +{ + return gpa == INVALID_GPA; +} + #define KVM_ERR_PTR_BAD_PAGE (ERR_PTR(-ENOENT)) static inline bool is_error_page(struct page *page) @@ -238,7 +243,6 @@ struct kvm_async_pf { struct list_head link; struct list_head queue; struct kvm_vcpu *vcpu; - struct mm_struct *mm; gpa_t cr2_or_gpa; unsigned long addr; struct kvm_arch_async_pf arch; @@ -1319,21 +1323,12 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * * @gpc: struct gfn_to_pfn_cache object. * @kvm: pointer to kvm instance. - * @vcpu: vCPU to be used for marking pages dirty and to be woken on - * invalidation. - * @usage: indicates if the resulting host physical PFN is used while - * the @vcpu is IN_GUEST_MODE (in which case invalidation of - * the cache from MMU notifiers---but not for KVM memslot - * changes!---will also force @vcpu to exit the guest and - * refresh the cache); and/or if the PFN used directly - * by KVM (and thus needs a kernel virtual mapping). * * This sets up a gfn_to_pfn_cache by initializing locks and assigning the * immutable attributes. Note, the cache must be zero-allocated (or zeroed by * the caller before init). */ -void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm, - struct kvm_vcpu *vcpu, enum pfn_cache_usage usage); +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm); /** * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest @@ -1354,6 +1349,22 @@ void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm, int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len); /** + * kvm_gpc_activate_hva - prepare a cached kernel mapping and HPA for a given HVA. + * + * @gpc: struct gfn_to_pfn_cache object. + * @hva: userspace virtual address to map. + * @len: sanity check; the range being access must fit a single page. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * The semantics of this function are the same as those of kvm_gpc_activate(). It + * merely bypasses a layer of address translation. + */ +int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long hva, unsigned long len); + +/** * kvm_gpc_check - check validity of a gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. @@ -1399,6 +1410,16 @@ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len); */ void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc); +static inline bool kvm_gpc_is_gpa_active(struct gfn_to_pfn_cache *gpc) +{ + return gpc->active && !kvm_is_error_gpa(gpc->gpa); +} + +static inline bool kvm_gpc_is_hva_active(struct gfn_to_pfn_cache *gpc) +{ + return gpc->active && kvm_is_error_gpa(gpc->gpa); +} + void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); @@ -1505,9 +1526,10 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); +bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_post_init_vm(struct kvm *kvm); void kvm_arch_pre_destroy_vm(struct kvm *kvm); -int kvm_arch_create_vm_debugfs(struct kvm *kvm); +void kvm_arch_create_vm_debugfs(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* @@ -1788,11 +1810,21 @@ static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) return (hpa_t)pfn << PAGE_SHIFT; } -static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa) +static inline bool kvm_is_gpa_in_memslot(struct kvm *kvm, gpa_t gpa) { unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); - return kvm_is_error_hva(hva); + return !kvm_is_error_hva(hva); +} + +static inline void kvm_gpc_mark_dirty_in_slot(struct gfn_to_pfn_cache *gpc) +{ + lockdep_assert_held(&gpc->lock); + + if (!gpc->memslot) + return; + + mark_page_dirty_in_slot(gpc->kvm, gpc->memslot, gpa_to_gfn(gpc->gpa)); } enum kvm_stat_kind { diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 9d1f7835d8c1..d93f6522b2c3 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -49,12 +49,6 @@ typedef u64 hfn_t; typedef hfn_t kvm_pfn_t; -enum pfn_cache_usage { - KVM_GUEST_USES_PFN = BIT(0), - KVM_HOST_USES_PFN = BIT(1), - KVM_GUEST_AND_HOST_USE_PFN = KVM_GUEST_USES_PFN | KVM_HOST_USES_PFN, -}; - struct gfn_to_hva_cache { u64 generation; gpa_t gpa; @@ -69,13 +63,11 @@ struct gfn_to_pfn_cache { unsigned long uhva; struct kvm_memory_slot *memslot; struct kvm *kvm; - struct kvm_vcpu *vcpu; struct list_head list; rwlock_t lock; struct mutex refresh_lock; void *khva; kvm_pfn_t pfn; - enum pfn_cache_usage usage; bool active; bool valid; }; diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h index 612b4cab3819..36df927ec4b7 100644 --- a/include/linux/led-class-flash.h +++ b/include/linux/led-class-flash.h @@ -85,7 +85,6 @@ static inline struct led_classdev_flash *lcdev_to_flcdev( return container_of(lcdev, struct led_classdev_flash, led_cdev); } -#if IS_ENABLED(CONFIG_LEDS_CLASS_FLASH) /** * led_classdev_flash_register_ext - register a new object of LED class with * init data and with support for flash LEDs @@ -116,29 +115,6 @@ int devm_led_classdev_flash_register_ext(struct device *parent, void devm_led_classdev_flash_unregister(struct device *parent, struct led_classdev_flash *fled_cdev); -#else - -static inline int led_classdev_flash_register_ext(struct device *parent, - struct led_classdev_flash *fled_cdev, - struct led_init_data *init_data) -{ - return 0; -} - -static inline void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev) {}; -static inline int devm_led_classdev_flash_register_ext(struct device *parent, - struct led_classdev_flash *fled_cdev, - struct led_init_data *init_data) -{ - return 0; -} - -static inline void devm_led_classdev_flash_unregister(struct device *parent, - struct led_classdev_flash *fled_cdev) -{}; - -#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_FLASH) */ - static inline int led_classdev_flash_register(struct device *parent, struct led_classdev_flash *fled_cdev) { diff --git a/include/linux/led-class-multicolor.h b/include/linux/led-class-multicolor.h index 210d57bcd767..db9f34c6736e 100644 --- a/include/linux/led-class-multicolor.h +++ b/include/linux/led-class-multicolor.h @@ -30,7 +30,6 @@ static inline struct led_classdev_mc *lcdev_to_mccdev( return container_of(led_cdev, struct led_classdev_mc, led_cdev); } -#if IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) /** * led_classdev_multicolor_register_ext - register a new object of led_classdev * class with support for multicolor LEDs @@ -64,34 +63,6 @@ int devm_led_classdev_multicolor_register_ext(struct device *parent, void devm_led_classdev_multicolor_unregister(struct device *parent, struct led_classdev_mc *mcled_cdev); -#else - -static inline int led_classdev_multicolor_register_ext(struct device *parent, - struct led_classdev_mc *mcled_cdev, - struct led_init_data *init_data) -{ - return 0; -} - -static inline void led_classdev_multicolor_unregister(struct led_classdev_mc *mcled_cdev) {}; -static inline int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev, - enum led_brightness brightness) -{ - return 0; -} - -static inline int devm_led_classdev_multicolor_register_ext(struct device *parent, - struct led_classdev_mc *mcled_cdev, - struct led_init_data *init_data) -{ - return 0; -} - -static inline void devm_led_classdev_multicolor_unregister(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{}; - -#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) */ static inline int led_classdev_multicolor_register(struct device *parent, struct led_classdev_mc *mcled_cdev) diff --git a/include/linux/leds-expresswire.h b/include/linux/leds-expresswire.h new file mode 100644 index 000000000000..a422921f4159 --- /dev/null +++ b/include/linux/leds-expresswire.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Shared library for Kinetic's ExpressWire protocol. + * This protocol works by pulsing the ExpressWire IC's control GPIO. + * ktd2692 and ktd2801 are known to use this protocol. + */ + +#ifndef _LEDS_EXPRESSWIRE_H +#define _LEDS_EXPRESSWIRE_H + +#include <linux/types.h> + +struct gpio_desc; + +struct expresswire_timing { + unsigned long poweroff_us; + unsigned long detect_delay_us; + unsigned long detect_us; + unsigned long data_start_us; + unsigned long end_of_data_low_us; + unsigned long end_of_data_high_us; + unsigned long short_bitset_us; + unsigned long long_bitset_us; +}; + +struct expresswire_common_props { + struct gpio_desc *ctrl_gpio; + struct expresswire_timing timing; +}; + +void expresswire_power_off(struct expresswire_common_props *props); +void expresswire_enable(struct expresswire_common_props *props); +void expresswire_start(struct expresswire_common_props *props); +void expresswire_end(struct expresswire_common_props *props); +void expresswire_set_bit(struct expresswire_common_props *props, bool bit); +void expresswire_write_u8(struct expresswire_common_props *props, u8 val); + +#endif /* _LEDS_EXPRESSWIRE_H */ diff --git a/include/linux/leds.h b/include/linux/leds.h index 4754b02d3a2c..db6b114bb3d9 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -82,15 +82,7 @@ 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; @@ -279,20 +271,9 @@ 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) { @@ -658,7 +639,7 @@ struct gpio_led_platform_data { gpio_blink_set_t gpio_blink_set; }; -#ifdef CONFIG_NEW_LEDS +#ifdef CONFIG_LEDS_GPIO_REGISTER struct platform_device *gpio_led_register_device( int id, const struct gpio_led_platform_data *pdata); #else diff --git a/include/linux/libata.h b/include/linux/libata.h index 26d68115afb8..13fb41d25da6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -107,6 +107,7 @@ enum { ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 20), /* Priority cmds sent to dev */ ATA_DFLAG_CDL_ENABLED = (1 << 21), /* cmd duration limits is enabled */ + ATA_DFLAG_RESUMING = (1 << 22), /* Device is resuming */ ATA_DFLAG_DETACH = (1 << 24), ATA_DFLAG_DETACHED = (1 << 25), ATA_DFLAG_DA = (1 << 26), /* device supports Device Attention */ @@ -1151,12 +1152,19 @@ extern int ata_std_bios_param(struct scsi_device *sdev, sector_t capacity, int geom[]); extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev); extern int ata_scsi_slave_alloc(struct scsi_device *sdev); -extern int ata_scsi_slave_config(struct scsi_device *sdev); +int ata_scsi_device_configure(struct scsi_device *sdev, + struct queue_limits *lim); extern void ata_scsi_slave_destroy(struct scsi_device *sdev); extern int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth); extern int ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev, int queue_depth); +extern int ata_ncq_prio_supported(struct ata_port *ap, struct scsi_device *sdev, + bool *supported); +extern int ata_ncq_prio_enabled(struct ata_port *ap, struct scsi_device *sdev, + bool *enabled); +extern int ata_ncq_prio_enable(struct ata_port *ap, struct scsi_device *sdev, + bool enable); extern struct ata_device *ata_dev_pair(struct ata_device *adev); extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev); extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap); @@ -1243,7 +1251,8 @@ extern struct ata_port *ata_sas_port_alloc(struct ata_host *, extern void ata_port_probe(struct ata_port *ap); extern int ata_sas_tport_add(struct device *parent, struct ata_port *ap); extern void ata_sas_tport_delete(struct ata_port *ap); -extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *); +int ata_sas_device_configure(struct scsi_device *sdev, struct queue_limits *lim, + struct ata_port *ap); extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap); extern void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis); @@ -1409,13 +1418,13 @@ extern const struct attribute_group *ata_common_sdev_groups[]; __ATA_BASE_SHT(drv_name), \ .can_queue = ATA_DEF_QUEUE, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ - .slave_configure = ata_scsi_slave_config + .device_configure = ata_scsi_device_configure #define ATA_SUBBASE_SHT_QD(drv_name, drv_qd) \ __ATA_BASE_SHT(drv_name), \ .can_queue = drv_qd, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ - .slave_configure = ata_scsi_slave_config + .device_configure = ata_scsi_device_configure #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 287f590ed56b..d94bfd9ac8cc 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -43,29 +43,10 @@ static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) -{ - __set_bit(nr, addr); -} - -static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) -{ - __clear_bit(nr, addr); -} - -static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, - int set) -{ - if (set) - linkmode_set_bit(nr, addr); - else - linkmode_clear_bit(nr, addr); -} - -static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) -{ - return test_bit(nr, addr); -} +#define linkmode_test_bit test_bit +#define linkmode_set_bit __set_bit +#define linkmode_clear_bit __clear_bit +#define linkmode_mod_bit __assign_bit static inline void linkmode_set_bit_array(const int *array, int array_size, unsigned long *addr) diff --git a/include/linux/list.h b/include/linux/list.h index 059aa1fff41e..5f4b0a39cf46 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -766,7 +766,7 @@ static inline size_t list_count_nodes(struct list_head *head) * @member: the name of the list_head within the struct. */ #define list_entry_is_head(pos, head, member) \ - (&pos->member == (head)) + list_is_head(&pos->member, (head)) /** * list_for_each_entry - iterate over list of given type @@ -1195,4 +1195,19 @@ static inline void hlist_splice_init(struct hlist_head *from, pos && ({ n = pos->member.next; 1; }); \ pos = hlist_entry_safe(n, typeof(*pos), member)) +/** + * hlist_count_nodes - count nodes in the hlist + * @head: the head for your hlist. + */ +static inline size_t hlist_count_nodes(struct hlist_head *head) +{ + struct hlist_node *pos; + size_t count = 0; + + hlist_for_each(pos, head) + count++; + + return count; +} + #endif diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 7675a48a0701..792b67ceb631 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -24,6 +24,8 @@ enum lru_status { LRU_SKIP, /* item cannot be locked, skip */ LRU_RETRY, /* item not freeable. May drop the lock internally, but has to return locked. */ + LRU_STOP, /* stop lru list walking. May drop the lock + internally, but has to return locked. */ }; struct list_lru_one { @@ -62,8 +64,6 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, #define list_lru_init(lru) \ __list_lru_init((lru), false, NULL, NULL) -#define list_lru_init_key(lru, key) \ - __list_lru_init((lru), false, (key), NULL) #define list_lru_init_memcg(lru, shrinker) \ __list_lru_init((lru), true, NULL, shrinker) @@ -170,22 +170,6 @@ static inline unsigned long list_lru_count(struct list_lru *lru) void list_lru_isolate(struct list_lru_one *list, struct list_head *item); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head); -/** - * list_lru_putback: undo list_lru_isolate - * @lru: the lru pointer. - * @item: the item to put back. - * @nid: the node id of the sublist to put the item back to. - * @memcg: the cgroup of the sublist to put the item back to. - * - * Put back an isolated item into its original LRU. Note that unlike - * list_lru_add, this does not increment the node LRU count (as - * list_lru_isolate does not originally decrement this count). - * - * Since we might have dropped the LRU lock in between, recompute list_lru_one - * from the node's id and memcg. - */ -void list_lru_putback(struct list_lru *lru, struct list_head *item, int nid, - struct mem_cgroup *memcg); typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, struct list_lru_one *list, spinlock_t *lock, void *cb_arg); diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index a8057a3f8de6..f804b76cde44 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -176,7 +176,8 @@ LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, size_t buffer_size) LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) -LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, const char *name) +LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, struct dentry *src, + const char *name) LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, struct kernfs_node *kn) LSM_HOOK(int, 0, file_permission, struct file *file, int mask) @@ -280,9 +281,9 @@ LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb) LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry, struct inode *inode) LSM_HOOK(int, -EOPNOTSUPP, getselfattr, unsigned int attr, - struct lsm_ctx __user *ctx, size_t *size, u32 flags) + struct lsm_ctx __user *ctx, u32 *size, u32 flags) LSM_HOOK(int, -EOPNOTSUPP, setselfattr, unsigned int attr, - struct lsm_ctx *ctx, size_t size, u32 flags) + struct lsm_ctx *ctx, u32 size, u32 flags) LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 693eba9869e4..b1fbe4118414 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -7,6 +7,7 @@ /* Known PHY IDs */ #define MARVELL_PHY_ID_88E1101 0x01410c60 +#define MARVELL_PHY_ID_88E3082 0x01410c80 #define MARVELL_PHY_ID_88E1112 0x01410c90 #define MARVELL_PHY_ID_88E1111 0x01410cc0 #define MARVELL_PHY_ID_88E1118 0x01410e10 @@ -31,6 +32,8 @@ /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 +/* ID from 88E6020, assumed to be the same for the whole 6250 family */ +#define MARVELL_PHY_ID_88E6250_FAMILY 0x01410db0 /* These Ethernet switch families contain embedded PHYs, but they do * not have a model ID. So the switch driver traps reads to the ID2 * register and returns the switch family ID diff --git a/include/linux/math64.h b/include/linux/math64.h index bf74478926d4..d34def7f9a8c 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -4,8 +4,8 @@ #include <linux/types.h> #include <linux/math.h> -#include <vdso/math64.h> #include <asm/div64.h> +#include <vdso/math64.h> #if BITS_PER_LONG == 64 @@ -179,16 +179,12 @@ static __always_inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift) #ifndef mul_u64_u32_shr static __always_inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) { - u32 ah, al; + u32 ah = a >> 32, al = a; u64 ret; - al = a; - ah = a >> 32; - ret = mul_u32_u32(al, mul) >> shift; if (ah) ret += mul_u32_u32(ah, mul) << (32 - shift); - return ret; } #endif /* mul_u64_u32_shr */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 20ff87f8e001..394fd0a887ae 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -14,6 +14,7 @@ #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> +#include <linux/kernel.h> #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> @@ -712,18 +713,16 @@ static inline void mem_cgroup_uncharge(struct folio *folio) __mem_cgroup_uncharge(folio); } -void __mem_cgroup_uncharge_list(struct list_head *page_list); -static inline void mem_cgroup_uncharge_list(struct list_head *page_list) +void __mem_cgroup_uncharge_folios(struct folio_batch *folios); +static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { if (mem_cgroup_disabled()) return; - __mem_cgroup_uncharge_list(page_list); + __mem_cgroup_uncharge_folios(folios); } void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages); - void mem_cgroup_replace_folio(struct folio *old, struct folio *new); - void mem_cgroup_migrate(struct folio *old, struct folio *new); /** @@ -1162,7 +1161,7 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, rcu_read_unlock(); } -void split_page_memcg(struct page *head, unsigned int nr); +void split_page_memcg(struct page *head, int old_order, int new_order); unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, @@ -1294,7 +1293,7 @@ static inline void mem_cgroup_uncharge(struct folio *folio) { } -static inline void mem_cgroup_uncharge_list(struct list_head *page_list) +static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { } @@ -1620,7 +1619,7 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } -static inline void split_page_memcg(struct page *head, unsigned int nr) +static inline void split_page_memcg(struct page *head, int old_order, int new_order) { } @@ -1694,18 +1693,18 @@ static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio, return folio_lruvec_lock_irq(folio); } -/* Don't lock again iff page's lruvec locked */ -static inline struct lruvec *folio_lruvec_relock_irqsave(struct folio *folio, - struct lruvec *locked_lruvec, unsigned long *flags) +/* Don't lock again iff folio's lruvec locked */ +static inline void folio_lruvec_relock_irqsave(struct folio *folio, + struct lruvec **lruvecp, unsigned long *flags) { - if (locked_lruvec) { - if (folio_matches_lruvec(folio, locked_lruvec)) - return locked_lruvec; + if (*lruvecp) { + if (folio_matches_lruvec(folio, *lruvecp)) + return; - unlock_page_lruvec_irqrestore(locked_lruvec, *flags); + unlock_page_lruvec_irqrestore(*lruvecp, *flags); } - return folio_lruvec_lock_irqsave(folio, flags); + *lruvecp = folio_lruvec_lock_irqsave(folio, flags); } #ifdef CONFIG_CGROUP_WRITEBACK diff --git a/include/linux/memory.h b/include/linux/memory.h index f53cfdaaaa41..c0afee5d126e 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -96,8 +96,17 @@ int set_memory_block_size_order(unsigned int order); #define MEM_GOING_ONLINE (1<<3) #define MEM_CANCEL_ONLINE (1<<4) #define MEM_CANCEL_OFFLINE (1<<5) +#define MEM_PREPARE_ONLINE (1<<6) +#define MEM_FINISH_OFFLINE (1<<7) struct memory_notify { + /* + * The altmap_start_pfn and altmap_nr_pages fields are designated for + * specifying the altmap range and are exclusively intended for use in + * MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers. + */ + unsigned long altmap_start_pfn; + unsigned long altmap_nr_pages; unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; @@ -114,6 +123,7 @@ struct mem_section; #define DEFAULT_CALLBACK_PRI 0 #define SLAB_CALLBACK_PRI 1 #define HMAT_CALLBACK_PRI 2 +#define CXL_CALLBACK_PRI 5 #define MM_COMPUTE_BATCH_PRI 10 #define CPUSET_CALLBACK_PRI 10 #define MEMTIER_HOTPLUG_PRI 100 diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7d2076583494..7a9ff464608d 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -106,6 +106,22 @@ typedef int __bitwise mhp_t; * implies the node id (nid). */ #define MHP_NID_IS_MGID ((__force mhp_t)BIT(2)) +/* + * The hotplugged memory is completely inaccessible while the memory is + * offline. The memory provider will handle MEM_PREPARE_ONLINE / + * MEM_FINISH_OFFLINE notifications and make the memory accessible. + * + * This flag is only relevant when used along with MHP_MEMMAP_ON_MEMORY, + * because the altmap cannot be written (e.g., poisoned) when adding + * memory -- before it is set online. + * + * This allows for adding memory with an altmap that is not currently + * made available by a hypervisor. When onlining that memory, the + * hypervisor can be instructed to make that memory available, and + * the onlining phase will not require any memory allocations, which is + * helpful in low-memory situations. + */ +#define MHP_OFFLINE_INACCESSIBLE ((__force mhp_t)BIT(3)) /* * Extended parameters for memory hotplug: @@ -121,6 +137,7 @@ struct mhp_params { bool mhp_range_allowed(u64 start, u64 size, bool need_mapping); struct range mhp_get_pluggable_range(bool need_mapping); +bool mhp_supports_memmap_on_memory(void); /* * Zone resizing functions @@ -154,7 +171,7 @@ extern void adjust_present_page_count(struct page *page, long nr_pages); /* VM interface that may be used by firmware interface */ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, - struct zone *zone); + struct zone *zone, bool mhp_off_inaccessible); extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); @@ -262,6 +279,11 @@ static inline bool movable_node_is_enabled(void) return false; } +static inline bool mhp_supports_memmap_on_memory(void) +{ + return false; +} + static inline void pgdat_kswapd_lock(pg_data_t *pgdat) {} static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) {} static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) {} diff --git a/include/linux/mempool.h b/include/linux/mempool.h index 7be1e32e6d42..16c5cc807ff6 100644 --- a/include/linux/mempool.h +++ b/include/linux/mempool.h @@ -95,6 +95,19 @@ static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size) (void *) size); } +void *mempool_kvmalloc(gfp_t gfp_mask, void *pool_data); +void mempool_kvfree(void *element, void *pool_data); + +static inline int mempool_init_kvmalloc_pool(mempool_t *pool, int min_nr, size_t size) +{ + return mempool_init(pool, min_nr, mempool_kvmalloc, mempool_kvfree, (void *) size); +} + +static inline mempool_t *mempool_create_kvmalloc_pool(int min_nr, size_t size) +{ + return mempool_create(min_nr, mempool_kvmalloc, mempool_kvfree, (void *) size); +} + /* * A mempool_alloc_t and mempool_free_t for a simple page allocator that * allocates pages of the order specified by pool_data diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 744c830f4b13..3f7143ade32c 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -25,6 +25,7 @@ struct vmem_altmap { unsigned long free; unsigned long align; unsigned long alloc; + bool inaccessible; }; /* @@ -108,7 +109,7 @@ struct dev_pagemap_ops { * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping * @done: completion for @ref - * @type: memory type: see MEMORY_* in memory_hotplug.h + * @type: memory type: see MEMORY_* above in memremap.h * @flags: PGMAP_* flags to specify defailed behavior * @vmemmap_shift: structural definition of how the vmemmap page metadata * is populated, specifically the metadata page order. diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index f1755163dd9f..8c0a33a2e9ce 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -19,6 +19,7 @@ enum axp20x_variants { AXP223_ID, AXP288_ID, AXP313A_ID, + AXP717_ID, AXP803_ID, AXP806_ID, AXP809_ID, @@ -104,15 +105,47 @@ enum axp20x_variants { #define AXP313A_ON_INDICATE 0x00 #define AXP313A_OUTPUT_CONTROL 0x10 -#define AXP313A_DCDC1_CONRTOL 0x13 -#define AXP313A_DCDC2_CONRTOL 0x14 -#define AXP313A_DCDC3_CONRTOL 0x15 -#define AXP313A_ALDO1_CONRTOL 0x16 -#define AXP313A_DLDO1_CONRTOL 0x17 +#define AXP313A_DCDC1_CONTROL 0x13 +#define AXP313A_DCDC2_CONTROL 0x14 +#define AXP313A_DCDC3_CONTROL 0x15 +#define AXP313A_ALDO1_CONTROL 0x16 +#define AXP313A_DLDO1_CONTROL 0x17 #define AXP313A_SHUTDOWN_CTRL 0x1a #define AXP313A_IRQ_EN 0x20 #define AXP313A_IRQ_STATE 0x21 +#define AXP717_ON_INDICATE 0x00 +#define AXP717_IRQ0_EN 0x40 +#define AXP717_IRQ1_EN 0x41 +#define AXP717_IRQ2_EN 0x42 +#define AXP717_IRQ3_EN 0x43 +#define AXP717_IRQ4_EN 0x44 +#define AXP717_IRQ0_STATE 0x48 +#define AXP717_IRQ1_STATE 0x49 +#define AXP717_IRQ2_STATE 0x4a +#define AXP717_IRQ3_STATE 0x4b +#define AXP717_IRQ4_STATE 0x4c +#define AXP717_DCDC_OUTPUT_CONTROL 0x80 +#define AXP717_DCDC1_CONTROL 0x83 +#define AXP717_DCDC2_CONTROL 0x84 +#define AXP717_DCDC3_CONTROL 0x85 +#define AXP717_DCDC4_CONTROL 0x86 +#define AXP717_LDO0_OUTPUT_CONTROL 0x90 +#define AXP717_LDO1_OUTPUT_CONTROL 0x91 +#define AXP717_ALDO1_CONTROL 0x93 +#define AXP717_ALDO2_CONTROL 0x94 +#define AXP717_ALDO3_CONTROL 0x95 +#define AXP717_ALDO4_CONTROL 0x96 +#define AXP717_BLDO1_CONTROL 0x97 +#define AXP717_BLDO2_CONTROL 0x98 +#define AXP717_BLDO3_CONTROL 0x99 +#define AXP717_BLDO4_CONTROL 0x9a +#define AXP717_CLDO1_CONTROL 0x9b +#define AXP717_CLDO2_CONTROL 0x9c +#define AXP717_CLDO3_CONTROL 0x9d +#define AXP717_CLDO4_CONTROL 0x9e +#define AXP717_CPUSLDO_CONTROL 0x9f + #define AXP806_STARTUP_SRC 0x00 #define AXP806_CHIP_ID 0x03 #define AXP806_PWR_OUT_CTRL1 0x10 @@ -434,6 +467,27 @@ enum { }; enum { + AXP717_DCDC1 = 0, + AXP717_DCDC2, + AXP717_DCDC3, + AXP717_DCDC4, + AXP717_ALDO1, + AXP717_ALDO2, + AXP717_ALDO3, + AXP717_ALDO4, + AXP717_BLDO1, + AXP717_BLDO2, + AXP717_BLDO3, + AXP717_BLDO4, + AXP717_CLDO1, + AXP717_CLDO2, + AXP717_CLDO3, + AXP717_CLDO4, + AXP717_CPUSLDO, + AXP717_REG_ID_MAX, +}; + +enum { AXP806_DCDCA = 0, AXP806_DCDCB, AXP806_DCDCC, @@ -732,6 +786,40 @@ enum axp313a_irqs { AXP313A_IRQ_PEK_RIS_EDGE, }; +enum axp717_irqs { + AXP717_IRQ_VBUS_FAULT, + AXP717_IRQ_VBUS_OVER_V, + AXP717_IRQ_BOOST_OVER_V, + AXP717_IRQ_GAUGE_NEW_SOC = 4, + AXP717_IRQ_SOC_DROP_LVL1 = 6, + AXP717_IRQ_SOC_DROP_LVL2, + AXP717_IRQ_PEK_RIS_EDGE, + AXP717_IRQ_PEK_FAL_EDGE, + AXP717_IRQ_PEK_LONG, + AXP717_IRQ_PEK_SHORT, + AXP717_IRQ_BATT_REMOVAL, + AXP717_IRQ_BATT_PLUGIN, + AXP717_IRQ_VBUS_REMOVAL, + AXP717_IRQ_VBUS_PLUGIN, + AXP717_IRQ_BATT_OVER_V, + AXP717_IRQ_CHARG_TIMER, + AXP717_IRQ_DIE_TEMP_HIGH, + AXP717_IRQ_CHARG, + AXP717_IRQ_CHARG_DONE, + AXP717_IRQ_BATT_OVER_CURR, + AXP717_IRQ_LDO_OVER_CURR, + AXP717_IRQ_WDOG_EXPIRE, + AXP717_IRQ_BATT_ACT_TEMP_LOW, + AXP717_IRQ_BATT_ACT_TEMP_HIGH, + AXP717_IRQ_BATT_CHG_TEMP_LOW, + AXP717_IRQ_BATT_CHG_TEMP_HIGH, + AXP717_IRQ_BATT_QUIT_TEMP_HIGH, + AXP717_IRQ_BC_USB_CHNG = 30, + AXP717_IRQ_BC_USB_DONE, + AXP717_IRQ_TYPEC_PLUGIN = 37, + AXP717_IRQ_TYPEC_REMOVE, +}; + enum axp803_irqs { AXP803_IRQ_ACIN_OVER_V = 1, AXP803_IRQ_ACIN_PLUGIN, diff --git a/include/linux/mfd/cs42l43.h b/include/linux/mfd/cs42l43.h index cf8263aab41b..2239d8585e78 100644 --- a/include/linux/mfd/cs42l43.h +++ b/include/linux/mfd/cs42l43.h @@ -6,20 +6,21 @@ * Cirrus Logic International Semiconductor Ltd. */ +#ifndef CS42L43_CORE_EXT_H +#define CS42L43_CORE_EXT_H + #include <linux/completion.h> -#include <linux/device.h> -#include <linux/gpio/consumer.h> #include <linux/mutex.h> #include <linux/regmap.h> #include <linux/regulator/consumer.h> -#include <linux/soundwire/sdw.h> #include <linux/workqueue.h> -#ifndef CS42L43_CORE_EXT_H -#define CS42L43_CORE_EXT_H - #define CS42L43_N_SUPPLIES 3 +struct device; +struct gpio_desc; +struct sdw_slave; + enum cs42l43_irq_numbers { CS42L43_PLL_LOST_LOCK, CS42L43_PLL_READY, diff --git a/include/linux/mfd/da9055/pdata.h b/include/linux/mfd/da9055/pdata.h index d3f126990ad0..137a2b067512 100644 --- a/include/linux/mfd/da9055/pdata.h +++ b/include/linux/mfd/da9055/pdata.h @@ -7,7 +7,6 @@ #define DA9055_MAX_REGULATORS 8 struct da9055; -struct gpio_desc; enum gpio_select { NO_GPIO = 0, @@ -24,16 +23,6 @@ struct da9055_pdata { /* Enable RTC in RESET Mode */ bool reset_enable; /* - * GPI muxed pin to control - * regulator state A/B, 0 if not available. - */ - int *gpio_ren; - /* - * GPI muxed pin to control - * regulator set, 0 if not available. - */ - int *gpio_rsel; - /* * Regulator mode control bits value (GPI offset) that * controls the regulator state, 0 if not available. */ @@ -43,7 +32,5 @@ struct da9055_pdata { * controls the regulator set A/B, 0 if not available. */ enum gpio_select *reg_rsel; - /* GPIO descriptors to enable regulator, NULL if not available */ - struct gpio_desc **ena_gpiods; }; #endif /* __DA9055_PDATA_H */ diff --git a/include/linux/mfd/lp8788.h b/include/linux/mfd/lp8788.h index 3d5c480d58ea..51b47966a04d 100644 --- a/include/linux/mfd/lp8788.h +++ b/include/linux/mfd/lp8788.h @@ -10,7 +10,6 @@ #ifndef __MFD_LP8788_H__ #define __MFD_LP8788_H__ -#include <linux/gpio.h> #include <linux/irqdomain.h> #include <linux/pwm.h> #include <linux/regmap.h> @@ -159,21 +158,17 @@ struct lp8788; /* * lp8788_buck1_dvs - * @gpio : gpio pin number for dvs control * @vsel : dvs selector for buck v1 register */ struct lp8788_buck1_dvs { - int gpio; enum lp8788_dvs_sel vsel; }; /* * lp8788_buck2_dvs - * @gpio : two gpio pin numbers are used for dvs * @vsel : dvs selector for buck v2 register */ struct lp8788_buck2_dvs { - int gpio[LP8788_NUM_BUCK2_DVS]; enum lp8788_dvs_sel vsel; }; @@ -268,8 +263,8 @@ struct lp8788_vib_platform_data { * @buck_data : regulator initial data for buck * @dldo_data : regulator initial data for digital ldo * @aldo_data : regulator initial data for analog ldo - * @buck1_dvs : gpio configurations for buck1 dvs - * @buck2_dvs : gpio configurations for buck2 dvs + * @buck1_dvs : configurations for buck1 dvs + * @buck2_dvs : configurations for buck2 dvs * @chg_pdata : platform data for charger driver * @alarm_sel : rtc alarm selection (1 or 2) * @bl_pdata : configurable data for backlight driver diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h index 6193905abbb5..5c2cc1103437 100644 --- a/include/linux/mfd/max8997.h +++ b/include/linux/mfd/max8997.h @@ -178,7 +178,6 @@ struct max8997_platform_data { * */ bool ignore_gpiodvs_side_effect; - int buck125_gpios[3]; /* GPIO of [0]SET1, [1]SET2, [2]SET3 */ int buck125_default_idx; /* Default value of SET1, 2, 3 */ unsigned int buck1_voltage[8]; /* buckx_voltage in uV */ bool buck1_gpiodvs; diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index 79c020bd0c70..a054e55c8646 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -65,10 +65,7 @@ struct max8998_regulator_data { * be other than the preset values. * @buck1_voltage: BUCK1 DVS mode 1 voltage registers * @buck2_voltage: BUCK2 DVS mode 2 voltage registers - * @buck1_set1: BUCK1 gpio pin 1 to set output voltage - * @buck1_set2: BUCK1 gpio pin 2 to set output voltage * @buck1_default_idx: Default for BUCK1 gpio pin 1, 2 - * @buck2_set3: BUCK2 gpio pin to set output voltage * @buck2_default_idx: Default for BUCK2 gpio pin. * @wakeup: Allow to wake up from suspend * @rtc_delay: LP3974 RTC chip bug that requires delay after a register @@ -91,10 +88,7 @@ struct max8998_platform_data { bool buck_voltage_lock; int buck1_voltage[4]; int buck2_voltage[2]; - int buck1_set1; - int buck1_set2; int buck1_default_idx; - int buck2_set3; int buck2_default_idx; bool wakeup; bool rtc_delay; diff --git a/include/linux/mfd/sun4i-gpadc.h b/include/linux/mfd/sun4i-gpadc.h index ea0ccf33a459..021f820f9d52 100644 --- a/include/linux/mfd/sun4i-gpadc.h +++ b/include/linux/mfd/sun4i-gpadc.h @@ -81,8 +81,8 @@ #define SUN4I_GPADC_TEMP_DATA 0x20 #define SUN4I_GPADC_DATA 0x24 -#define SUN4I_GPADC_IRQ_FIFO_DATA 0 -#define SUN4I_GPADC_IRQ_TEMP_DATA 1 +#define SUN4I_GPADC_IRQ_FIFO_DATA 1 +#define SUN4I_GPADC_IRQ_TEMP_DATA 2 /* 10s delay before suspending the IP */ #define SUN4I_GPADC_AUTOSUSPEND_DELAY 10000 diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h index fecc2fa2a364..c315903f6dab 100644 --- a/include/linux/mfd/syscon.h +++ b/include/linux/mfd/syscon.h @@ -17,20 +17,17 @@ struct device_node; #ifdef CONFIG_MFD_SYSCON -extern struct regmap *device_node_to_regmap(struct device_node *np); -extern struct regmap *syscon_node_to_regmap(struct device_node *np); -extern struct regmap *syscon_regmap_lookup_by_compatible(const char *s); -extern struct regmap *syscon_regmap_lookup_by_phandle( - struct device_node *np, - const char *property); -extern struct regmap *syscon_regmap_lookup_by_phandle_args( - struct device_node *np, - const char *property, - int arg_count, - unsigned int *out_args); -extern struct regmap *syscon_regmap_lookup_by_phandle_optional( - struct device_node *np, - const char *property); +struct regmap *device_node_to_regmap(struct device_node *np); +struct regmap *syscon_node_to_regmap(struct device_node *np); +struct regmap *syscon_regmap_lookup_by_compatible(const char *s); +struct regmap *syscon_regmap_lookup_by_phandle(struct device_node *np, + const char *property); +struct regmap *syscon_regmap_lookup_by_phandle_args(struct device_node *np, + const char *property, + int arg_count, + unsigned int *out_args); +struct regmap *syscon_regmap_lookup_by_phandle_optional(struct device_node *np, + const char *property); #else static inline struct regmap *device_node_to_regmap(struct device_node *np) { diff --git a/include/linux/mfd/twl.h b/include/linux/mfd/twl.h index c062d91a67d9..85dc406173db 100644 --- a/include/linux/mfd/twl.h +++ b/include/linux/mfd/twl.h @@ -461,6 +461,7 @@ static inline int twl6030_mmc_card_detect(struct device *dev, int slot) #define TWL4030_PM_MASTER_GLOBAL_TST 0xb6 +#define TWL6030_PHOENIX_DEV_ON 0x06 /*----------------------------------------------------------------------*/ /* Power bus message definitions */ diff --git a/include/linux/mhi.h b/include/linux/mhi.h index d0f9b522f328..cde01e133a1b 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -320,12 +320,7 @@ struct mhi_controller_config { * @hw_ev_rings: Number of hardware event rings * @sw_ev_rings: Number of software event rings * @nr_irqs: Number of IRQ allocated by bus master (required) - * @family_number: MHI controller family number - * @device_number: MHI controller device number - * @major_version: MHI controller major revision number - * @minor_version: MHI controller minor revision number * @serial_number: MHI controller serial number obtained from BHI - * @oem_pk_hash: MHI controller OEM PK Hash obtained from BHI * @mhi_event: MHI event ring configurations table * @mhi_cmd: MHI command ring configurations table * @mhi_ctxt: MHI device context, shared memory between host and device @@ -369,15 +364,6 @@ struct mhi_controller_config { * Fields marked as (required) need to be populated by the controller driver * before calling mhi_register_controller(). For the fields marked as (optional) * they can be populated depending on the usecase. - * - * The following fields are present for the purpose of implementing any device - * specific quirks or customizations for specific MHI revisions used in device - * by the controller drivers. The MHI stack will just populate these fields - * during mhi_register_controller(): - * family_number - * device_number - * major_version - * minor_version */ struct mhi_controller { struct device *cntrl_dev; @@ -408,12 +394,7 @@ struct mhi_controller { u32 hw_ev_rings; u32 sw_ev_rings; u32 nr_irqs; - u32 family_number; - u32 device_number; - u32 major_version; - u32 minor_version; u32 serial_number; - u32 oem_pk_hash[MHI_MAX_OEM_PK_HASH_SEGMENTS]; struct mhi_event *mhi_event; struct mhi_cmd *mhi_cmd; @@ -649,13 +630,29 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl); int mhi_sync_power_up(struct mhi_controller *mhi_cntrl); /** - * mhi_power_down - Start MHI power down sequence + * mhi_power_down - Power down the MHI device and also destroy the + * 'struct device' for the channels associated with it. + * See also mhi_power_down_keep_dev() which is a variant + * of this API that keeps the 'struct device' for channels + * (useful during suspend/hibernation). * @mhi_cntrl: MHI controller * @graceful: Link is still accessible, so do a graceful shutdown process */ void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful); /** + * mhi_power_down_keep_dev - Power down the MHI device but keep the 'struct + * device' for the channels associated with it. + * This is a variant of 'mhi_power_down()' and + * useful in scenarios such as suspend/hibernation + * where destroying of the 'struct device' is not + * needed. + * @mhi_cntrl: MHI controller + * @graceful: Link is still accessible, so do a graceful shutdown process + */ +void mhi_power_down_keep_dev(struct mhi_controller *mhi_cntrl, bool graceful); + +/** * mhi_unprepare_after_power_down - Free any allocated memory after power down * @mhi_cntrl: MHI controller */ diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h index 44077837385f..d52daf45861b 100644 --- a/include/linux/min_heap.h +++ b/include/linux/min_heap.h @@ -35,31 +35,33 @@ static __always_inline void min_heapify(struct min_heap *heap, int pos, const struct min_heap_callbacks *func) { - void *left, *right, *parent, *smallest; + void *left, *right; void *data = heap->data; + void *root = data + pos * func->elem_size; + int i = pos, j; + /* Find the sift-down path all the way to the leaves. */ for (;;) { - if (pos * 2 + 1 >= heap->nr) + if (i * 2 + 2 >= heap->nr) break; + left = data + (i * 2 + 1) * func->elem_size; + right = data + (i * 2 + 2) * func->elem_size; + i = func->less(left, right) ? i * 2 + 1 : i * 2 + 2; + } - left = data + ((pos * 2 + 1) * func->elem_size); - parent = data + (pos * func->elem_size); - smallest = parent; - if (func->less(left, smallest)) - smallest = left; - - if (pos * 2 + 2 < heap->nr) { - right = data + ((pos * 2 + 2) * func->elem_size); - if (func->less(right, smallest)) - smallest = right; - } - if (smallest == parent) - break; - func->swp(smallest, parent); - if (smallest == left) - pos = (pos * 2) + 1; - else - pos = (pos * 2) + 2; + /* Special case for the last leaf with no sibling. */ + if (i * 2 + 2 == heap->nr) + i = i * 2 + 1; + + /* Backtrack to the correct location. */ + while (i != pos && func->less(root, data + i * func->elem_size)) + i = (i - 1) / 2; + + /* Shift the element into its correct place. */ + j = i; + while (i != pos) { + i = (i - 1) / 2; + func->swp(data + i * func->elem_size, data + j * func->elem_size); } } @@ -70,7 +72,7 @@ void min_heapify_all(struct min_heap *heap, { int i; - for (i = heap->nr / 2; i >= 0; i--) + for (i = heap->nr / 2 - 1; i >= 0; i--) min_heapify(heap, i, func); } diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index cb15308b5cb0..991526039ccb 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -95,9 +95,10 @@ enum { }; enum { - MLX5_CQ_MODIFY_PERIOD = 1 << 0, - MLX5_CQ_MODIFY_COUNT = 1 << 1, - MLX5_CQ_MODIFY_OVERRUN = 1 << 2, + MLX5_CQ_MODIFY_PERIOD = BIT(0), + MLX5_CQ_MODIFY_COUNT = BIT(1), + MLX5_CQ_MODIFY_OVERRUN = BIT(2), + MLX5_CQ_MODIFY_PERIOD_MODE = BIT(4), }; enum { diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 01275c6e8468..d7bb31d9a446 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -68,7 +68,7 @@ #define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8) #define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32) #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8) -#define MLX5_ADDR_OF(typ, p, fld) ((void *)((uint8_t *)(p) + MLX5_BYTE_OFF(typ, fld))) +#define MLX5_ADDR_OF(typ, p, fld) ((void *)((u8 *)(p) + MLX5_BYTE_OFF(typ, fld))) /* insert a value to a struct */ #define MLX5_SET(typ, p, fld, v) do { \ @@ -1336,6 +1336,9 @@ enum mlx5_qcam_feature_groups { #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_NIC_RX_FT_FIELD_SUPPORT_2(mdev, cap) \ + MLX5_CAP_FLOWTABLE(mdev, ft_field_support_2_nic_receive.cap) + #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) @@ -1359,6 +1362,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) +#define MLX5_CAP_PORT_SELECTION_FT_FIELD_SUPPORT_2(mdev, cap) \ + MLX5_CAP_PORT_SELECTION(mdev, ft_field_support_2_port_selection.cap) + #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index bf9324a31ae9..779cfdf2e9d6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -85,7 +85,7 @@ enum mlx5_sqp_t { }; enum { - MLX5_MAX_PORTS = 4, + MLX5_MAX_PORTS = 8, }; enum { @@ -862,6 +862,7 @@ struct mlx5_cmd_work_ent { void *context; int idx; struct completion handling; + struct completion slotted; struct completion done; struct mlx5_cmd *cmd; struct work_struct work; @@ -1374,11 +1375,4 @@ static inline bool mlx5_is_macsec_roce_supported(struct mlx5_core_dev *mdev) 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 49f660563e49..f468763478ae 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -416,7 +416,10 @@ struct mlx5_ifc_flow_table_fields_supported_bits { /* Table 2170 - Flow Table Fields Supported 2 Format */ struct mlx5_ifc_flow_table_fields_supported_2_bits { - u8 reserved_at_0[0xe]; + u8 reserved_at_0[0x2]; + u8 inner_l4_type[0x1]; + u8 outer_l4_type[0x1]; + u8 reserved_at_4[0xa]; u8 bth_opcode[0x1]; u8 reserved_at_f[0x1]; u8 tunnel_header_0_1[0x1]; @@ -525,6 +528,12 @@ union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { u8 reserved_at_0[0x80]; }; +enum { + MLX5_PACKET_L4_TYPE_NONE, + MLX5_PACKET_L4_TYPE_TCP, + MLX5_PACKET_L4_TYPE_UDP, +}; + struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 smac_47_16[0x20]; @@ -550,7 +559,8 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_at_c0[0x10]; + u8 l4_type[0x2]; + u8 reserved_at_c2[0xe]; u8 ipv4_ihl[0x4]; u8 reserved_at_c4[0x4]; @@ -846,7 +856,11 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; - u8 reserved_at_e00[0x700]; + u8 reserved_at_e00[0x600]; + + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive; + + u8 reserved_at_1480[0x80]; struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive_rdma; @@ -876,7 +890,9 @@ struct mlx5_ifc_port_selection_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_port_selection; - u8 reserved_at_400[0x7c00]; + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_port_selection; + + u8 reserved_at_480[0x7b80]; }; enum { @@ -1469,7 +1485,9 @@ enum { }; struct mlx5_ifc_cmd_hca_cap_bits { - u8 reserved_at_0[0x10]; + u8 reserved_at_0[0x6]; + u8 page_request_disable[0x1]; + u8 reserved_at_7[0x9]; u8 shared_object_to_user_object_allowed[0x1]; u8 reserved_at_13[0xe]; u8 vhca_resource_manager[0x1]; @@ -1668,7 +1686,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cq_oi[0x1]; u8 cq_resize[0x1]; u8 cq_moderation[0x1]; - u8 reserved_at_223[0x3]; + u8 cq_period_mode_modify[0x1]; + u8 reserved_at_224[0x2]; u8 cq_eq_remap[0x1]; u8 pg[0x1]; u8 block_lb_mc[0x1]; @@ -2004,7 +2023,13 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_3a0[0x10]; u8 max_rqt_vhca_id[0x10]; - u8 reserved_at_3c0[0x440]; + u8 reserved_at_3c0[0x20]; + + u8 reserved_at_3e0[0x10]; + u8 pcc_ifa2[0x1]; + u8 reserved_at_3f1[0xf]; + + u8 reserved_at_400[0x400]; }; enum mlx5_ifc_flow_destination_type { @@ -4361,10 +4386,10 @@ enum { MLX5_CQC_ST_FIRED = 0xa, }; -enum { +enum mlx5_cq_period_mode { MLX5_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, MLX5_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, - MLX5_CQ_PERIOD_NUM_MODES + MLX5_CQ_PERIOD_NUM_MODES, }; struct mlx5_ifc_cqc_bits { @@ -9793,7 +9818,21 @@ struct mlx5_ifc_pplm_reg_bits { u8 fec_override_admin_100g_2x[0x10]; u8 fec_override_admin_50g_1x[0x10]; - u8 reserved_at_140[0x140]; + u8 fec_override_cap_800g_8x[0x10]; + u8 fec_override_cap_400g_4x[0x10]; + + u8 fec_override_cap_200g_2x[0x10]; + u8 fec_override_cap_100g_1x[0x10]; + + u8 reserved_at_180[0xa0]; + + u8 fec_override_admin_800g_8x[0x10]; + u8 fec_override_admin_400g_4x[0x10]; + + u8 fec_override_admin_200g_2x[0x10]; + u8 fec_override_admin_100g_1x[0x10]; + + u8 reserved_at_260[0x20]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -10165,7 +10204,9 @@ struct mlx5_ifc_mtutc_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x68]; + u8 reserved_at_0[0x48]; + u8 fec_100G_per_lane_in_pplm[0x1]; + u8 reserved_at_49[0x1f]; u8 fec_50G_per_lane_in_pplm[0x1]; u8 reserved_at_69[0x4]; u8 rx_icrc_encapsulated_counter[0x1]; @@ -12677,6 +12718,11 @@ struct mlx5_ifc_modify_page_track_obj_in_bits { struct mlx5_ifc_page_track_bits obj_context; }; +struct mlx5_ifc_query_page_track_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_page_track_bits obj_context; +}; + struct mlx5_ifc_msecq_reg_bits { u8 reserved_at_0[0x20]; diff --git a/include/linux/mm.h b/include/linux/mm.h index f5a97dec5169..b6bdaa18b9e9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -36,6 +36,7 @@ struct anon_vma; struct anon_vma_chain; struct user_struct; struct pt_regs; +struct folio_batch; extern int sysctl_page_lock_unfairness; @@ -86,7 +87,7 @@ extern int sysctl_legacy_va_layout; #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; -extern const int mmap_rnd_bits_max; +extern int mmap_rnd_bits_max __ro_after_init; extern int mmap_rnd_bits __read_mostly; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS @@ -226,7 +227,6 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) -#define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) static inline struct folio *lru_to_folio(struct list_head *head) { return list_entry((head)->prev, struct folio, lru); @@ -391,6 +391,20 @@ extern unsigned int kobjsize(const void *objp); # define VM_UFFD_MINOR VM_NONE #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ +/* + * This flag is used to connect VFIO to arch specific KVM code. It + * indicates that the memory under this VMA is safe for use with any + * non-cachable memory type inside KVM. Some VFIO devices, on some + * platforms, are thought to be unsafe and can cause machine crashes + * if KVM does not lock down the memory type. + */ +#ifdef CONFIG_64BIT +#define VM_ALLOW_ANY_UNCACHED_BIT 39 +#define VM_ALLOW_ANY_UNCACHED BIT(VM_ALLOW_ANY_UNCACHED_BIT) +#else +#define VM_ALLOW_ANY_UNCACHED VM_NONE +#endif + /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) @@ -781,6 +795,11 @@ static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, return NULL; } +static inline void vma_assert_locked(struct vm_area_struct *vma) +{ + mmap_assert_locked(vma->vm_mm); +} + static inline void release_fault_lock(struct vm_fault *vmf) { mmap_read_unlock(vmf->vma->vm_mm); @@ -1178,7 +1197,7 @@ static inline int is_vmalloc_or_module_addr(const void *x) * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for * debugging purposes - it does not include PTE-mapped sub-pages; look - * at folio_mapcount() or page_mapcount() or total_mapcount() instead. + * at folio_mapcount() or page_mapcount() instead. */ static inline int folio_entire_mapcount(struct folio *folio) { @@ -1204,14 +1223,16 @@ static inline void page_mapcount_reset(struct page *page) * a large folio, it includes the number of times this page is mapped * as part of that folio. * - * The result is undefined for pages which cannot be mapped into userspace. - * For example SLAB or special types of pages. See function page_has_type(). - * They use this field in struct page differently. + * Will report 0 for pages which cannot be mapped into userspace, eg + * slab, page tables and similar. */ static inline int page_mapcount(struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; + /* Handle page_has_type() pages */ + if (mapcount < 0) + mapcount = 0; if (unlikely(PageCompound(page))) mapcount += folio_entire_mapcount(page_folio(page)); @@ -1238,13 +1259,6 @@ static inline int folio_mapcount(struct folio *folio) return folio_total_mapcount(folio); } -static inline int total_mapcount(struct page *page) -{ - if (likely(!PageCompound(page))) - return atomic_read(&page->_mapcount) + 1; - return folio_total_mapcount(page_folio(page)); -} - static inline bool folio_large_is_mapped(struct folio *folio) { /* @@ -1514,6 +1528,8 @@ static inline void folio_put_refs(struct folio *folio, int refs) __folio_put(folio); } +void folios_put_refs(struct folio_batch *folios, unsigned int *refs); + /* * union release_pages_arg - an array of pages or folios * @@ -1536,18 +1552,19 @@ void release_pages(release_pages_arg, int nr); /** * folios_put - Decrement the reference count on an array of folios. * @folios: The folios. - * @nr: How many folios there are. * - * Like folio_put(), but for an array of folios. This is more efficient - * than writing the loop yourself as it will optimise the locks which - * need to be taken if the folios are freed. + * Like folio_put(), but for a batch of folios. This is more efficient + * than writing the loop yourself as it will optimise the locks which need + * to be taken if the folios are freed. The folios batch is returned + * empty and ready to be reused for another batch; there is no need to + * reinitialise it. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ -static inline void folios_put(struct folio **folios, unsigned int nr) +static inline void folios_put(struct folio_batch *folios) { - release_pages(folios, nr); + folios_put_refs(folios, NULL); } static inline void put_page(struct page *page) @@ -1640,13 +1657,11 @@ static inline int page_zone_id(struct page *page) } #ifdef NODE_NOT_IN_PAGE_FLAGS -extern int page_to_nid(const struct page *page); +int page_to_nid(const struct page *page); #else static inline int page_to_nid(const struct page *page) { - struct page *p = (struct page *)page; - - return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK; + return (PF_POISONED_CHECK(page)->flags >> NODES_PGSHIFT) & NODES_MASK; } #endif @@ -2065,6 +2080,13 @@ static inline long folio_nr_pages(struct folio *folio) #endif } +/* Only hugetlbfs can allocate folios larger than MAX_ORDER */ +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE +#define MAX_FOLIO_NR_PAGES (1UL << PUD_ORDER) +#else +#define MAX_FOLIO_NR_PAGES MAX_ORDER_NR_PAGES +#endif + /* * compound_nr() returns the number of pages in this potentially compound * page. compound_nr() can be called on a tail page, and is defined to @@ -2187,11 +2209,6 @@ static inline int arch_make_folio_accessible(struct folio *folio) */ #include <linux/vmstat.h> -static __always_inline void *lowmem_page_address(const struct page *page) -{ - return page_to_virt(page); -} - #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif @@ -2214,6 +2231,11 @@ void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif +static __always_inline void *lowmem_page_address(const struct page *page) +{ + return page_to_virt(page); +} + #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) @@ -2595,19 +2617,19 @@ static inline void dec_mm_counter(struct mm_struct *mm, int member) mm_trace_rss_stat(mm, member); } -/* Optimized variant when page is already known not to be PageAnon */ -static inline int mm_counter_file(struct page *page) +/* Optimized variant when folio is already known not to be anon */ +static inline int mm_counter_file(struct folio *folio) { - if (PageSwapBacked(page)) + if (folio_test_swapbacked(folio)) return MM_SHMEMPAGES; return MM_FILEPAGES; } -static inline int mm_counter(struct page *page) +static inline int mm_counter(struct folio *folio) { - if (PageAnon(page)) + if (folio_test_anon(folio)) return MM_ANONPAGES; - return mm_counter_file(page); + return mm_counter_file(folio); } static inline unsigned long get_mm_rss(struct mm_struct *mm) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8b611e13153e..5240bd7bca33 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -210,8 +210,8 @@ struct page { * * An 'encoded_page' pointer is a pointer to a regular 'struct page', but * with the low bits of the pointer indicating extra context-dependent - * information. Not super-common, but happens in mmu_gather and mlock - * handling, and this acts as a type system check on that use. + * information. Only used in mmu_gather handling, and this acts as a type + * system check on that use. * * We only really have two guaranteed bits in general, although you could * play with 'struct page' alignment (see CONFIG_HAVE_ALIGNED_STRUCT_PAGE) @@ -220,21 +220,46 @@ struct page { * Use the supplied helper functions to endcode/decode the pointer and bits. */ struct encoded_page; -#define ENCODE_PAGE_BITS 3ul + +#define ENCODED_PAGE_BITS 3ul + +/* Perform rmap removal after we have flushed the TLB. */ +#define ENCODED_PAGE_BIT_DELAY_RMAP 1ul + +/* + * The next item in an encoded_page array is the "nr_pages" argument, specifying + * the number of consecutive pages starting from this page, that all belong to + * the same folio. For example, "nr_pages" corresponds to the number of folio + * references that must be dropped. If this bit is not set, "nr_pages" is + * implicitly 1. + */ +#define ENCODED_PAGE_BIT_NR_PAGES_NEXT 2ul + static __always_inline struct encoded_page *encode_page(struct page *page, unsigned long flags) { - BUILD_BUG_ON(flags > ENCODE_PAGE_BITS); + BUILD_BUG_ON(flags > ENCODED_PAGE_BITS); return (struct encoded_page *)(flags | (unsigned long)page); } static inline unsigned long encoded_page_flags(struct encoded_page *page) { - return ENCODE_PAGE_BITS & (unsigned long)page; + return ENCODED_PAGE_BITS & (unsigned long)page; } static inline struct page *encoded_page_ptr(struct encoded_page *page) { - return (struct page *)(~ENCODE_PAGE_BITS & (unsigned long)page); + return (struct page *)(~ENCODED_PAGE_BITS & (unsigned long)page); +} + +static __always_inline struct encoded_page *encode_nr_pages(unsigned long nr) +{ + VM_WARN_ON_ONCE((nr << 2) >> 2 != nr); + return (struct encoded_page *)(nr << 2); +} + +static __always_inline unsigned long encoded_nr_pages(struct encoded_page *page) +{ + return ((unsigned long)page) >> 2; } /* @@ -394,12 +419,13 @@ FOLIO_MATCH(compound_head, _head_2a); /** * struct ptdesc - Memory descriptor for page tables. - * @__page_flags: Same as page flags. Unused for page tables. + * @__page_flags: Same as page flags. Powerpc only. * @pt_rcu_head: For freeing page table pages. * @pt_list: List of used page tables. Used for s390 and x86. * @_pt_pad_1: Padding that aliases with page's compound head. * @pmd_huge_pte: Protected by ptdesc->ptl, used for THPs. * @__page_mapping: Aliases with page->mapping. Unused for page tables. + * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. * @_pt_pad_2: Padding to ensure proper alignment. @@ -425,6 +451,7 @@ struct ptdesc { unsigned long __page_mapping; union { + pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; }; @@ -450,6 +477,7 @@ TABLE_MATCH(flags, __page_flags); TABLE_MATCH(compound_head, pt_list); TABLE_MATCH(compound_head, _pt_pad_1); TABLE_MATCH(mapping, __page_mapping); +TABLE_MATCH(index, pt_index); TABLE_MATCH(rcu_head, pt_rcu_head); TABLE_MATCH(page_type, __page_type); TABLE_MATCH(_refcount, __page_refcount); diff --git a/include/linux/mman.h b/include/linux/mman.h index dc7048824be8..bcb201ab7a41 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -162,6 +162,14 @@ calc_vm_flag_bits(unsigned long flags) unsigned long vm_commit_limit(void); +#ifndef arch_memory_deny_write_exec_supported +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return true; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported +#endif + /* * Denies creating a writable executable mapping or gaining executable permissions. * diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 2f445c651742..88c6a76042ee 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -433,8 +433,8 @@ struct mmc_host { mmc_pm_flag_t pm_caps; /* supported pm features */ /* host specific block data */ - unsigned int max_seg_size; /* see blk_queue_max_segment_size */ - unsigned short max_segs; /* see blk_queue_max_segments */ + unsigned int max_seg_size; /* lim->max_segment_size */ + unsigned short max_segs; /* lim->max_segments */ unsigned short unused; unsigned int max_req_size; /* maximum number of bytes in one req */ unsigned int max_blk_size; /* maximum size of one mmc block */ @@ -539,7 +539,7 @@ struct mmc_host *devm_mmc_alloc_host(struct device *dev, int extra); int mmc_add_host(struct mmc_host *); void mmc_remove_host(struct mmc_host *); void mmc_free_host(struct mmc_host *); -void mmc_of_parse_clk_phase(struct mmc_host *host, +void mmc_of_parse_clk_phase(struct device *dev, struct mmc_clk_phase_map *map); int mmc_of_parse(struct mmc_host *host); int mmc_of_parse_voltage(struct mmc_host *host, u32 *mask); diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 7fada7a714fe..7cddfdac2f57 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -124,6 +124,7 @@ #define SDIO_DEVICE_ID_REALTEK_RTW8723DS_2ANT 0xd723 #define SDIO_DEVICE_ID_REALTEK_RTW8723DS_1ANT 0xd724 #define SDIO_DEVICE_ID_REALTEK_RTW8821DS 0xd821 +#define SDIO_DEVICE_ID_REALTEK_RTW8723CS 0xb703 #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 7c3e7b0b0e8f..39a7714605a7 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -10,7 +10,7 @@ struct vm_area_struct; struct mm_struct; struct vma_iterator; -void dump_page(struct page *page, const char *reason); +void dump_page(const struct page *page, const char *reason); void dump_vma(const struct vm_area_struct *vma); void dump_mm(const struct mm_struct *mm); void vma_iter_dump_tree(const struct vma_iterator *vmi); diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index f2b7a3f04099..bbaec80c78c5 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -11,7 +11,7 @@ #endif #ifndef leave_mm -static inline void leave_mm(int cpu) { } +static inline void leave_mm(void) { } #endif /* diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index a497f189d988..c11b7cde81ef 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -76,9 +76,12 @@ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) +# define is_migrate_cma_folio(folio, pfn) (MIGRATE_CMA == \ + get_pfnblock_flags_mask(&folio->page, pfn, MIGRATETYPE_MASK)) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false +# define is_migrate_cma_folio(folio, pfn) false #endif static inline bool is_migrate_movable(int mt) @@ -464,7 +467,7 @@ enum { #define NR_BLOOM_FILTERS 2 struct lru_gen_mm_state { - /* set to max_seq after each iteration */ + /* synced with max_seq after each iteration */ unsigned long seq; /* where the current iteration continues after */ struct list_head *head; @@ -479,8 +482,8 @@ struct lru_gen_mm_state { struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; - /* unstable max_seq from lru_gen_folio */ - unsigned long max_seq; + /* max_seq from lru_gen_folio: can be out of date */ + unsigned long seq; /* the next address within an mm to scan */ unsigned long next_addr; /* to batch promoted pages */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index f458469c5ce5..7a9a07ea451b 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -960,4 +960,14 @@ struct vchiq_device_id { char name[32]; }; +/** + * struct coreboot_device_id - Identifies a coreboot table entry + * @tag: tag ID + * @driver_data: driver specific data + */ +struct coreboot_device_id { + __u32 tag; + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 001b2ce83832..89b1e0ed9811 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -115,6 +115,14 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod); +#ifdef CONFIG_MODULES +void flush_module_init_free_work(void); +#else +static inline void flush_module_init_free_work(void) +{ +} +#endif + /* Any cleanup needed when module leaves. */ void module_arch_cleanup(struct module *mod); diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index c04f690871ca..9798c1a1d3b6 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -13,6 +13,7 @@ */ #include <linux/sched.h> #include <linux/mutex.h> +#include <linux/wait.h> typedef enum { FL_READY, diff --git a/include/linux/mtd/lpc32xx_mlc.h b/include/linux/mtd/lpc32xx_mlc.h index d168c628c0d5..35e971be0950 100644 --- a/include/linux/mtd/lpc32xx_mlc.h +++ b/include/linux/mtd/lpc32xx_mlc.h @@ -11,7 +11,7 @@ #include <linux/dmaengine.h> struct lpc32xx_mlc_platform_data { - bool (*dma_filter)(struct dma_chan *chan, void *filter_param); + dma_filter_fn dma_filter; }; #endif /* __LINUX_MTD_LPC32XX_MLC_H */ diff --git a/include/linux/mtd/lpc32xx_slc.h b/include/linux/mtd/lpc32xx_slc.h index cf54a9f80460..a044b806566b 100644 --- a/include/linux/mtd/lpc32xx_slc.h +++ b/include/linux/mtd/lpc32xx_slc.h @@ -11,7 +11,7 @@ #include <linux/dmaengine.h> struct lpc32xx_slc_platform_data { - bool (*dma_filter)(struct dma_chan *chan, void *filter_param); + dma_filter_fn dma_filter; }; #endif /* __LINUX_MTD_LPC32XX_SLC_H */ diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 914a9f974baa..8d10d9d2e830 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -223,7 +223,7 @@ struct mtd_part { * @partitions_lock: lock protecting accesses to the partition list. Protects * not only the master partition list, but also all * sub-partitions. - * @suspended: et to 1 when the device is suspended, 0 otherwise + * @suspended: set to 1 when the device is suspended, 0 otherwise * * This struct is embedded in mtd_info and contains master-specific * properties/fields. The master is the root MTD device from the MTD partition diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index badb4c1ac079..5c19ead60499 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -169,7 +169,7 @@ struct spinand_op; struct spinand_device; -#define SPINAND_MAX_ID_LEN 4 +#define SPINAND_MAX_ID_LEN 5 /* * For erase, write and read operation, we got the following timings : * tBERS (erase) 1ms to 4ms diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index a529347fd75b..562f92504f2b 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -192,6 +192,7 @@ struct ubi_device_info { * or a volume was removed) * @UBI_VOLUME_RESIZED: a volume has been re-sized * @UBI_VOLUME_RENAMED: a volume has been re-named + * @UBI_VOLUME_SHUTDOWN: a volume is going to removed, shutdown users * @UBI_VOLUME_UPDATED: data has been written to a volume * * These constants define which type of event has happened when a volume @@ -202,6 +203,7 @@ enum { UBI_VOLUME_REMOVED, UBI_VOLUME_RESIZED, UBI_VOLUME_RENAMED, + UBI_VOLUME_SHUTDOWN, UBI_VOLUME_UPDATED, }; diff --git a/include/linux/namei.h b/include/linux/namei.h index 74e0cc14ebf8..967aa9ea9f96 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -44,6 +44,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ +#define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) diff --git a/include/linux/net/intel/libie/rx.h b/include/linux/net/intel/libie/rx.h new file mode 100644 index 000000000000..8e97775f1d66 --- /dev/null +++ b/include/linux/net/intel/libie/rx.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBIE_RX_H +#define __LIBIE_RX_H + +#include <net/libeth/rx.h> + +/* Rx buffer management */ + +/* The largest size for a single descriptor as per HW */ +#define LIBIE_MAX_RX_BUF_LEN 9728U +/* "True" HW-writeable space: minimum from SW and HW values */ +#define LIBIE_RX_BUF_LEN(hr) min_t(u32, LIBETH_RX_PAGE_LEN(hr), \ + LIBIE_MAX_RX_BUF_LEN) + +/* The maximum frame size as per HW (S/G) */ +#define __LIBIE_MAX_RX_FRM_LEN 16382U +/* ATST, HW can chain up to 5 Rx descriptors */ +#define LIBIE_MAX_RX_FRM_LEN(hr) \ + min_t(u32, __LIBIE_MAX_RX_FRM_LEN, LIBIE_RX_BUF_LEN(hr) * 5) +/* Maximum frame size minus LL overhead */ +#define LIBIE_MAX_MTU \ + (LIBIE_MAX_RX_FRM_LEN(LIBETH_MAX_HEADROOM) - LIBETH_RX_LL_LEN) + +/* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed + * bitfield struct. + */ + +#define LIBIE_RX_PT_NUM 154 + +extern const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM]; + +/** + * libie_rx_pt_parse - convert HW packet type to software bitfield structure + * @pt: 10-bit hardware packet type value from the descriptor + * + * ```libie_rx_pt_lut``` must be accessed only using this wrapper. + * + * Return: parsed bitfield struct corresponding to the provided ptype. + */ +static inline struct libeth_rx_pt libie_rx_pt_parse(u32 pt) +{ + if (unlikely(pt >= LIBIE_RX_PT_NUM)) + pt = 0; + + return libie_rx_pt_lut[pt]; +} + +#endif /* __LIBIE_RX_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c6f6ac779b34..d20c6c99eb88 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -59,7 +59,7 @@ struct ethtool_ops; struct kernel_hwtstamp_config; struct phy_device; struct dsa_port; -struct ip_tunnel_parm; +struct ip_tunnel_parm_kern; struct macsec_context; struct macsec_ops; struct netdev_name_node; @@ -1327,7 +1327,7 @@ struct netdev_net_notifier { * queue id bound to an AF_XDP socket. The flags field specifies if * only RX, only Tx, or both should be woken up using the flags * XDP_WAKEUP_RX and XDP_WAKEUP_TX. - * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, + * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); @@ -1583,7 +1583,8 @@ struct net_device_ops { int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); int (*ndo_tunnel_ctl)(struct net_device *dev, - struct ip_tunnel_parm *p, int cmd); + struct ip_tunnel_parm_kern *p, + int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); @@ -1956,6 +1957,7 @@ enum netdev_reg_state { * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops * @stat_ops: Optional ops for queue-aware statistics + * @queue_mgmt_ops: Optional ops for queue management * * @gso_max_size: Maximum size of generic segmentation offload * @tso_max_size: Device (as in HW) limit on the max TSO request size @@ -2072,6 +2074,7 @@ struct net_device { struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; }; + unsigned long state; unsigned int flags; unsigned short hard_header_len; netdev_features_t features; @@ -2117,7 +2120,6 @@ struct net_device { * part of the usual set specified in Space.c. */ - unsigned long state; struct list_head dev_list; struct list_head napi_list; @@ -2338,6 +2340,8 @@ struct net_device { const struct netdev_stat_ops *stat_ops; + const struct netdev_queue_mgmt_ops *queue_mgmt_ops; + /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u @@ -2367,8 +2371,8 @@ struct net_device { struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; bool proto_down; + bool threaded; unsigned wol_enabled:1; - unsigned threaded:1; struct list_head net_notifier_list; @@ -3133,6 +3137,7 @@ struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); +void netdev_copy_name(struct net_device *dev, char *name); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -3203,6 +3208,7 @@ struct softnet_data { struct softnet_data *rps_ipi_list; #endif + unsigned int received_rps; bool in_net_rx_action; bool in_napi_threaded_poll; @@ -3235,11 +3241,11 @@ struct softnet_data { unsigned int cpu; unsigned int input_queue_tail; #endif - unsigned int received_rps; - unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + atomic_t dropped ____cacheline_aligned_in_smp; + /* Another possibly contended cache line */ spinlock_t defer_lock ____cacheline_aligned_in_smp; int defer_count; @@ -3248,21 +3254,6 @@ struct softnet_data { call_single_data_t defer_csd; }; -static inline void input_queue_head_incr(struct softnet_data *sd) -{ -#ifdef CONFIG_RPS - sd->input_queue_head++; -#endif -} - -static inline void input_queue_tail_incr_save(struct softnet_data *sd, - unsigned int *qtail) -{ -#ifdef CONFIG_RPS - *qtail = ++sd->input_queue_tail; -#endif -} - DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); static inline int dev_recursion_level(void) @@ -3270,23 +3261,6 @@ static inline int dev_recursion_level(void) return this_cpu_read(softnet_data.xmit.recursion); } -#define XMIT_RECURSION_LIMIT 8 -static inline bool dev_xmit_recursion(void) -{ - return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > - XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) -{ - __this_cpu_inc(softnet_data.xmit.recursion); -} - -static inline void dev_xmit_recursion_dec(void) -{ - __this_cpu_dec(softnet_data.xmit.recursion); -} - void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); @@ -4127,6 +4101,8 @@ static inline void dev_put(struct net_device *dev) netdev_put(dev, NULL); } +DEFINE_FREE(dev_put, struct net_device *, if (_T) dev_put(_T)) + static inline void netdev_ref_replace(struct net_device *odev, struct net_device *ndev, netdevice_tracker *tracker, @@ -4545,6 +4521,9 @@ static inline void netif_addr_unlock_bh(struct net_device *dev) void ether_setup(struct net_device *dev); +/* Allocate dummy net_device */ +struct net_device *alloc_netdev_dummy(int sizeof_priv); + /* Support for loadable net-drivers */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 100cbb261269..ca56a4428043 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -20,95 +20,24 @@ #include <linux/uio.h> enum netfs_sreq_ref_trace; - -/* - * Overload PG_private_2 to give us PG_fscache - this is used to indicate that - * a page is currently backed by a local disk cache - */ -#define folio_test_fscache(folio) folio_test_private_2(folio) -#define PageFsCache(page) PagePrivate2((page)) -#define SetPageFsCache(page) SetPagePrivate2((page)) -#define ClearPageFsCache(page) ClearPagePrivate2((page)) -#define TestSetPageFsCache(page) TestSetPagePrivate2((page)) -#define TestClearPageFsCache(page) TestClearPagePrivate2((page)) +typedef struct mempool_s mempool_t; /** - * folio_start_fscache - Start an fscache write on a folio. + * folio_start_private_2 - Start an fscache write on a folio. [DEPRECATED] * @folio: The folio. * * Call this function before writing a folio to a local cache. Starting a * second write before the first one finishes is not allowed. + * + * Note that this should no longer be used. */ -static inline void folio_start_fscache(struct folio *folio) +static inline void folio_start_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_private_2(folio), folio); folio_get(folio); folio_set_private_2(folio); } -/** - * folio_end_fscache - End an fscache write on a folio. - * @folio: The folio. - * - * Call this function after the folio has been written to the local cache. - * This will wake any sleepers waiting on this folio. - */ -static inline void folio_end_fscache(struct folio *folio) -{ - folio_end_private_2(folio); -} - -/** - * folio_wait_fscache - Wait for an fscache write on this folio to end. - * @folio: The folio. - * - * If this folio is currently being written to a local cache, wait for - * the write to finish. Another write may start after this one finishes, - * unless the caller holds the folio lock. - */ -static inline void folio_wait_fscache(struct folio *folio) -{ - folio_wait_private_2(folio); -} - -/** - * folio_wait_fscache_killable - Wait for an fscache write on this folio to end. - * @folio: The folio. - * - * If this folio is currently being written to a local cache, wait - * for the write to finish or for a fatal signal to be received. - * Another write may start after this one finishes, unless the caller - * holds the folio lock. - * - * Return: - * - 0 if successful. - * - -EINTR if a fatal signal was encountered. - */ -static inline int folio_wait_fscache_killable(struct folio *folio) -{ - return folio_wait_private_2_killable(folio); -} - -static inline void set_page_fscache(struct page *page) -{ - folio_start_fscache(page_folio(page)); -} - -static inline void end_page_fscache(struct page *page) -{ - folio_end_private_2(page_folio(page)); -} - -static inline void wait_on_page_fscache(struct page *page) -{ - folio_wait_private_2(page_folio(page)); -} - -static inline int wait_on_page_fscache_killable(struct page *page) -{ - return folio_wait_private_2_killable(page_folio(page)); -} - /* Marks used on xarray-based buffers */ #define NETFS_BUF_PUT_MARK XA_MARK_0 /* - Page needs putting */ #define NETFS_BUF_PAGECACHE_MARK XA_MARK_1 /* - Page needs wb/dirty flag wrangling */ @@ -135,6 +64,7 @@ struct netfs_inode { #if IS_ENABLED(CONFIG_FSCACHE) struct fscache_cookie *cache; #endif + struct mutex wb_lock; /* Writeback serialisation */ loff_t remote_i_size; /* Size of the remote file */ loff_t zero_point; /* Size after which we assume there's no data * on the server */ @@ -142,7 +72,8 @@ struct netfs_inode { #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ -#define NETFS_ICTX_NO_WRITE_STREAMING 3 /* Don't engage in write-streaming */ +#define NETFS_ICTX_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark + * write to cache on read */ }; /* @@ -165,16 +96,25 @@ struct netfs_folio { unsigned int dirty_len; /* Write-streaming dirty data length */ }; #define NETFS_FOLIO_INFO 0x1UL /* OR'd with folio->private. */ +#define NETFS_FOLIO_COPY_TO_CACHE ((struct netfs_group *)0x356UL) /* Write to the cache only */ -static inline struct netfs_folio *netfs_folio_info(struct folio *folio) +static inline bool netfs_is_folio_info(const void *priv) { - void *priv = folio_get_private(folio); + return (unsigned long)priv & NETFS_FOLIO_INFO; +} - if ((unsigned long)priv & NETFS_FOLIO_INFO) +static inline struct netfs_folio *__netfs_folio_info(const void *priv) +{ + if (netfs_is_folio_info(priv)) return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO); return NULL; } +static inline struct netfs_folio *netfs_folio_info(struct folio *folio) +{ + return __netfs_folio_info(folio_get_private(folio)); +} + static inline struct netfs_group *netfs_folio_group(struct folio *folio) { struct netfs_folio *finfo; @@ -187,6 +127,33 @@ static inline struct netfs_group *netfs_folio_group(struct folio *folio) } /* + * Stream of I/O subrequests going to a particular destination, such as the + * server or the local cache. This is mainly intended for writing where we may + * have to write to multiple destinations concurrently. + */ +struct netfs_io_stream { + /* Submission tracking */ + struct netfs_io_subrequest *construct; /* Op being constructed */ + unsigned int submit_off; /* Folio offset we're submitting from */ + unsigned int submit_len; /* Amount of data left to submit */ + unsigned int submit_max_len; /* Amount I/O can be rounded up to */ + void (*prepare_write)(struct netfs_io_subrequest *subreq); + void (*issue_write)(struct netfs_io_subrequest *subreq); + /* Collection tracking */ + struct list_head subrequests; /* Contributory I/O operations */ + struct netfs_io_subrequest *front; /* Op being collected */ + unsigned long long collected_to; /* Position we've collected results to */ + size_t transferred; /* The amount transferred from this stream */ + enum netfs_io_source source; /* Where to read from/write to */ + unsigned short error; /* Aggregate error for the stream */ + unsigned char stream_nr; /* Index of stream in parent table */ + bool avail; /* T if stream is available */ + bool active; /* T if stream is active */ + bool need_retry; /* T if this stream needs retrying */ + bool failed; /* T if this stream failed */ +}; + +/* * Resources required to do operations on a cache. */ struct netfs_cache_resources { @@ -209,14 +176,17 @@ struct netfs_io_subrequest { struct work_struct work; struct list_head rreq_link; /* Link in rreq->subrequests */ struct iov_iter io_iter; /* Iterator for this subrequest */ - loff_t start; /* Where to start the I/O */ + unsigned long long start; /* Where to start the I/O */ + size_t max_len; /* Maximum size of the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ + unsigned int nr_segs; /* Number of segs in io_iter */ unsigned int max_nr_segs; /* 0 or max number of segments in an iterator */ enum netfs_io_source source; /* Where to read from/write to */ + unsigned char stream_nr; /* I/O stream this belongs to */ unsigned long flags; #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ @@ -224,15 +194,20 @@ struct netfs_io_subrequest { #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ #define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ +#define NETFS_SREQ_BOUNDARY 6 /* Set if ends on hard boundary (eg. ceph object) */ +#define NETFS_SREQ_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ +#define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ +#define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ +#define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */ }; enum netfs_io_origin { NETFS_READAHEAD, /* This read was triggered by readahead */ NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ + NETFS_COPY_TO_CACHE, /* This write is to copy a read to the cache */ NETFS_WRITEBACK, /* This write was triggered by writepages */ NETFS_WRITETHROUGH, /* This write was made by netfs_perform_write() */ - NETFS_LAUNDER_WRITE, /* This is triggered by ->launder_folio() */ NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_DIO_WRITE, /* This is a direct I/O write */ @@ -254,26 +229,36 @@ struct netfs_io_request { struct netfs_cache_resources cache_resources; struct list_head proc_link; /* Link in netfs_iorequests */ struct list_head subrequests; /* Contributory I/O operations */ + struct netfs_io_stream io_streams[2]; /* Streams of parallel I/O operations */ +#define NR_IO_STREAMS 2 //wreq->nr_io_streams + struct netfs_group *group; /* Writeback group being written back */ struct iov_iter iter; /* Unencrypted-side iterator */ struct iov_iter io_iter; /* I/O (Encrypted-side) iterator */ void *netfs_priv; /* Private data for the netfs */ + void *netfs_priv2; /* Private data for the netfs */ struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; unsigned int rsize; /* Maximum read size (0 for none) */ unsigned int wsize; /* Maximum write size (0 for none) */ - unsigned int subreq_counter; /* Next subreq->debug_index */ + atomic_t subreq_counter; /* Next subreq->debug_index */ + unsigned int nr_group_rel; /* Number of refs to release on ->group */ + spinlock_t lock; /* Lock for queuing subreqs */ atomic_t nr_outstanding; /* Number of ops in progress */ atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ - size_t submitted; /* Amount submitted for I/O so far */ - size_t len; /* Length of the request */ size_t upper_len; /* Length can be extended to here */ + unsigned long long submitted; /* Amount submitted for I/O so far */ + unsigned long long len; /* Length of the request */ size_t transferred; /* Amount to be indicated as transferred */ short error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ - loff_t i_size; /* Size of the file */ - loff_t start; /* Start position */ + unsigned long long i_size; /* Size of the file */ + unsigned long long start; /* Start position */ + atomic64_t issued_to; /* Write issuer folio cursor */ + unsigned long long contiguity; /* Tracking for gaps in the writeback sequence */ + unsigned long long collected_to; /* Point we've collected to */ + unsigned long long cleaned_to; /* Position we've cleaned folios to */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ refcount_t ref; unsigned long flags; @@ -287,6 +272,11 @@ struct netfs_io_request { #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ +#define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ +#define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ +#define NETFS_RREQ_ALL_QUEUED 13 /* All subreqs are now queued */ +#define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark + * write to cache on read */ const struct netfs_request_ops *netfs_ops; void (*cleanup)(struct netfs_io_request *req); }; @@ -295,8 +285,8 @@ struct netfs_io_request { * Operations the network filesystem can/must provide to the helpers. */ struct netfs_request_ops { - unsigned int io_request_size; /* Alloc size for netfs_io_request struct */ - unsigned int io_subrequest_size; /* Alloc size for netfs_io_subrequest struct */ + mempool_t *request_pool; + mempool_t *subrequest_pool; int (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); void (*free_subrequest)(struct netfs_io_subrequest *rreq); @@ -312,10 +302,13 @@ struct netfs_request_ops { /* Modification handling */ void (*update_i_size)(struct inode *inode, loff_t i_size); + void (*post_modify)(struct inode *inode); /* Write request handling */ - void (*create_write_requests)(struct netfs_io_request *wreq, - loff_t start, size_t len); + void (*begin_writeback)(struct netfs_io_request *wreq); + void (*prepare_write)(struct netfs_io_subrequest *subreq); + void (*issue_write)(struct netfs_io_subrequest *subreq); + void (*retry_request)(struct netfs_io_request *wreq, struct netfs_io_stream *stream); void (*invalidate_cache)(struct netfs_io_request *wreq); }; @@ -350,15 +343,27 @@ struct netfs_cache_ops { netfs_io_terminated_t term_func, void *term_func_priv); + /* Write data to the cache from a netfs subrequest. */ + void (*issue_write)(struct netfs_io_subrequest *subreq); + /* Expand readahead request */ void (*expand_readahead)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size); + unsigned long long *_start, + unsigned long long *_len, + unsigned long long i_size); /* Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, - loff_t i_size); + unsigned long long i_size); + + /* Prepare a write subrequest, working out if we're allowed to do it + * and finding out the maximum amount of data to gather before + * attempting to submit. If we're not permitted to do it, the + * subrequest should be marked failed. + */ + void (*prepare_write_subreq)(struct netfs_io_subrequest *subreq); /* Prepare a write operation, working out what part of the write we can * actually do. @@ -384,6 +389,7 @@ struct netfs_cache_ops { }; /* High-level read API. */ +ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); @@ -410,7 +416,6 @@ int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); void netfs_clear_inode_writeback(struct inode *inode, const void *aux); void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length); bool netfs_release_folio(struct folio *folio, gfp_t gfp); -int netfs_launder_folio(struct folio *folio); /* VMA operations API. */ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); @@ -426,9 +431,7 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, iov_iter_extraction_t extraction_flags); size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, size_t max_size, size_t max_segs); -struct netfs_io_subrequest *netfs_create_write_request( - struct netfs_io_request *wreq, enum netfs_io_source dest, - loff_t start, size_t len, work_func_t worker); +void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq); void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, bool was_async); void netfs_queue_write_request(struct netfs_io_subrequest *subreq); @@ -472,6 +475,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif + mutex_init(&ctx->wb_lock); /* ->releasepage() drives zero_point */ if (use_zero_point) { ctx->zero_point = ctx->remote_i_size; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f5ce7b101146..d59116ac8209 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -611,6 +611,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline bool nfs_have_writebacks(const struct inode *inode) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 539b57fbf3ce..d09b9773b20c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1821,13 +1821,6 @@ struct nfs_rpc_ops { }; /* - * NFS_CALL(getattr, inode, (fattr)); - * into - * NFS_PROTO(inode)->getattr(fattr); - */ -#define NFS_CALL(op, inode, args) NFS_PROTO(inode)->op args - -/* * Function vectors etc. for the NFS client */ extern const struct nfs_rpc_ops nfs_v2_clientops; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index e92e378df000..f53438eae815 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -216,13 +216,6 @@ void watchdog_update_hrtimer_threshold(u64 period); static inline void watchdog_update_hrtimer_threshold(u64 period) { } #endif -struct ctl_table; -int proc_watchdog(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_nmi_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *); -int proc_soft_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *); -int proc_watchdog_thresh(struct ctl_table *, int , void *, size_t *, loff_t *); -int proc_watchdog_cpumask(struct ctl_table *, int, void *, size_t *, loff_t *); - #ifdef CONFIG_HAVE_ACPI_APEI_NMI #include <asm/nmi.h> #endif diff --git a/include/linux/node.h b/include/linux/node.h index 25b66d705ee2..dfc004e4bee7 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -34,6 +34,18 @@ struct access_coordinate { unsigned int write_latency; }; +/* + * ACCESS_COORDINATE_LOCAL correlates to ACCESS CLASS 0 + * - access_coordinate between target node and nearest initiator node + * ACCESS_COORDINATE_CPU correlates to ACCESS CLASS 1 + * - access_coordinate between target node and nearest CPU node + */ +enum access_coordinate_class { + ACCESS_COORDINATE_LOCAL, + ACCESS_COORDINATE_CPU, + ACCESS_COORDINATE_MAX +}; + enum cache_indexing { NODE_CACHE_DIRECT_MAP, NODE_CACHE_INDEXED, @@ -66,7 +78,7 @@ struct node_cache_attrs { #ifdef CONFIG_HMEM_REPORTING void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs); void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord, - unsigned access); + enum access_coordinate_class access); #else static inline void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs) @@ -75,7 +87,7 @@ static inline void node_add_cache(unsigned int nid, static inline void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord, - unsigned access) + enum access_coordinate_class access) { } #endif @@ -137,7 +149,7 @@ extern void unregister_memory_block_under_nodes(struct memory_block *mem_blk); extern int register_memory_node_under_compute_node(unsigned int mem_nid, unsigned int cpu_nid, - unsigned access); + enum access_coordinate_class access); #else static inline void node_dev_init(void) { diff --git a/include/linux/numa.h b/include/linux/numa.h index 915033a75731..1d43371fafd2 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -36,12 +36,7 @@ int memory_add_physaddr_to_nid(u64 start); int phys_to_target_node(u64 start); #endif -#ifndef numa_fill_memblks -static inline int __init numa_fill_memblks(u64 start, u64 end) -{ - return NUMA_NO_MEMBLK; -} -#endif +int numa_fill_memblks(u64 start, u64 end); #else /* !CONFIG_NUMA */ static inline int numa_nearest_node(int node, unsigned int state) diff --git a/include/linux/of.h b/include/linux/of.h index 6a9ddf20e79a..a0bedd038a05 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -13,6 +13,7 @@ */ #include <linux/types.h> #include <linux/bitops.h> +#include <linux/cleanup.h> #include <linux/errno.h> #include <linux/kobject.h> #include <linux/mod_devicetable.h> @@ -134,6 +135,7 @@ static inline struct device_node *of_node_get(struct device_node *node) } static inline void of_node_put(struct device_node *node) { } #endif /* !CONFIG_OF_DYNAMIC */ +DEFINE_FREE(device_node, struct device_node *, if (_T) of_node_put(_T)) /* Pointer for first entry in chain of all nodes. */ extern struct device_node *of_root; @@ -180,11 +182,6 @@ static inline bool is_of_node(const struct fwnode_handle *fwnode) &__of_fwnode_handle_node->fwnode : NULL; \ }) -static inline bool of_have_populated_dt(void) -{ - return of_root != NULL; -} - static inline bool of_node_is_root(const struct device_node *node) { return node && (node->parent == NULL); @@ -294,6 +291,8 @@ extern struct device_node *of_get_next_child(const struct device_node *node, struct device_node *prev); extern struct device_node *of_get_next_available_child( const struct device_node *node, struct device_node *prev); +extern struct device_node *of_get_next_reserved_child( + const struct device_node *node, struct device_node *prev); extern struct device_node *of_get_compatible_child(const struct device_node *parent, const char *compatible); @@ -362,9 +361,6 @@ extern struct device_node *of_get_cpu_state_node(struct device_node *cpu_node, int index); extern u64 of_get_cpu_hwid(struct device_node *cpun, unsigned int thread); -#define for_each_property_of_node(dn, pp) \ - for (pp = dn->properties; pp != NULL; pp = pp->next) - 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( @@ -402,7 +398,20 @@ extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)); extern int of_alias_get_id(struct device_node *np, const char *stem); extern int of_alias_get_highest_id(const char *stem); -extern int of_machine_is_compatible(const char *compat); +bool of_machine_compatible_match(const char *const *compats); + +/** + * of_machine_is_compatible - Test root of device tree for a given compatible value + * @compat: compatible string to look for in root node's compatible property. + * + * Return: true if the root node has the given value in its compatible property. + */ +static inline bool of_machine_is_compatible(const char *compat) +{ + const char *compats[] = { compat, NULL }; + + return of_machine_compatible_match(compats); +} extern int of_add_property(struct device_node *np, struct property *prop); extern int of_remove_property(struct device_node *np, struct property *prop); @@ -541,6 +550,12 @@ static inline struct device_node *of_get_next_available_child( return NULL; } +static inline struct device_node *of_get_next_reserved_child( + const struct device_node *node, struct device_node *prev) +{ + return NULL; +} + static inline struct device_node *of_find_node_with_property( struct device_node *from, const char *prop_name) { @@ -549,11 +564,6 @@ static inline struct device_node *of_find_node_with_property( #define of_fwnode_handle(node) NULL -static inline bool of_have_populated_dt(void) -{ - return false; -} - static inline struct device_node *of_get_compatible_child(const struct device_node *parent, const char *compatible) { @@ -808,6 +818,11 @@ static inline int of_remove_property(struct device_node *np, struct property *pr return 0; } +static inline bool of_machine_compatible_match(const char *const *compats) +{ + return false; +} + static inline bool of_console_check(const struct device_node *dn, const char *name, int index) { return false; @@ -892,6 +907,9 @@ static inline int of_prop_val_eq(struct property *p1, struct property *p2) !memcmp(p1->value, p2->value, (size_t)p1->length); } +#define for_each_property_of_node(dn, pp) \ + for (pp = dn->properties; pp != NULL; pp = pp->next) + #if defined(CONFIG_OF) && defined(CONFIG_NUMA) extern int of_node_to_nid(struct device_node *np); #else @@ -1066,6 +1084,22 @@ static inline int of_parse_phandle_with_optional_args(const struct device_node * } /** + * of_phandle_args_equal() - Compare two of_phandle_args + * @a1: First of_phandle_args to compare + * @a2: Second of_phandle_args to compare + * + * Return: True if a1 and a2 are the same (same node pointer, same phandle + * args), false otherwise. + */ +static inline bool of_phandle_args_equal(const struct of_phandle_args *a1, + const struct of_phandle_args *a2) +{ + return a1->np == a2->np && + a1->args_count == a2->args_count && + !memcmp(a1->args, a2->args, sizeof(a1->args[0]) * a1->args_count); +} + +/** * of_property_count_u8_elems - Count the number of u8 elements in a property * * @np: device node from which the property value is to be read. @@ -1428,9 +1462,25 @@ static inline int of_property_read_s32(const struct device_node *np, #define for_each_child_of_node(parent, child) \ for (child = of_get_next_child(parent, NULL); child != NULL; \ child = of_get_next_child(parent, child)) + +#define for_each_child_of_node_scoped(parent, child) \ + for (struct device_node *child __free(device_node) = \ + of_get_next_child(parent, NULL); \ + child != NULL; \ + child = of_get_next_child(parent, child)) + #define for_each_available_child_of_node(parent, child) \ for (child = of_get_next_available_child(parent, NULL); child != NULL; \ child = of_get_next_available_child(parent, child)) +#define for_each_reserved_child_of_node(parent, child) \ + for (child = of_get_next_reserved_child(parent, NULL); child != NULL; \ + child = of_get_next_reserved_child(parent, child)) + +#define for_each_available_child_of_node_scoped(parent, child) \ + for (struct device_node *child __free(device_node) = \ + of_get_next_available_child(parent, NULL); \ + child != NULL; \ + child = of_get_next_available_child(parent, child)) #define for_each_of_cpu_node(cpu) \ for (cpu = of_get_next_cpu_node(NULL); cpu != NULL; \ @@ -1634,6 +1684,21 @@ static inline bool of_device_is_system_power_controller(const struct device_node return of_property_read_bool(np, "system-power-controller"); } +/** + * of_have_populated_dt() - Has DT been populated by bootloader + * + * Return: True if a DTB has been populated by the bootloader and it isn't the + * empty builtin one. False otherwise. + */ +static inline bool of_have_populated_dt(void) +{ +#ifdef CONFIG_OF + return of_property_present(of_root, "compatible"); +#else + return false; +#endif +} + /* * Overlay support */ diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h index 4d7756087b6b..a4bea62bfa29 100644 --- a/include/linux/of_graph.h +++ b/include/linux/of_graph.h @@ -41,7 +41,7 @@ struct of_endpoint { bool of_graph_is_present(const struct device_node *node); int of_graph_parse_endpoint(const struct device_node *node, struct of_endpoint *endpoint); -int of_graph_get_endpoint_count(const struct device_node *np); +unsigned int of_graph_get_endpoint_count(const struct device_node *np); struct device_node *of_graph_get_port_by_id(struct device_node *node, u32 id); struct device_node *of_graph_get_next_endpoint(const struct device_node *parent, struct device_node *previous); @@ -68,7 +68,7 @@ static inline int of_graph_parse_endpoint(const struct device_node *node, return -ENOSYS; } -static inline int of_graph_get_endpoint_count(const struct device_node *np) +static inline unsigned int of_graph_get_endpoint_count(const struct device_node *np) { return 0; } diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 3921fbed0b28..6f9242259edc 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -17,10 +17,12 @@ * build_OID_registry.pl to generate the data for look_up_OID(). */ enum OID { + OID_id_dsa_with_sha1, /* 1.2.840.10030.4.3 */ OID_id_dsa, /* 1.2.840.10040.4.1 */ OID_id_ecPublicKey, /* 1.2.840.10045.2.1 */ OID_id_prime192v1, /* 1.2.840.10045.3.1.1 */ OID_id_prime256v1, /* 1.2.840.10045.3.1.7 */ + OID_id_ecdsa_with_sha1, /* 1.2.840.10045.4.1 */ OID_id_ecdsa_with_sha224, /* 1.2.840.10045.4.3.1 */ OID_id_ecdsa_with_sha256, /* 1.2.840.10045.4.3.2 */ OID_id_ecdsa_with_sha384, /* 1.2.840.10045.4.3.3 */ @@ -28,6 +30,7 @@ enum OID { /* PKCS#1 {iso(1) member-body(2) us(840) rsadsi(113549) pkcs(1) pkcs-1(1)} */ OID_rsaEncryption, /* 1.2.840.113549.1.1.1 */ + OID_sha1WithRSAEncryption, /* 1.2.840.113549.1.1.5 */ OID_sha256WithRSAEncryption, /* 1.2.840.113549.1.1.11 */ OID_sha384WithRSAEncryption, /* 1.2.840.113549.1.1.12 */ OID_sha512WithRSAEncryption, /* 1.2.840.113549.1.1.13 */ @@ -64,7 +67,9 @@ enum OID { OID_PKU2U, /* 1.3.5.1.5.2.7 */ OID_Scram, /* 1.3.6.1.5.5.14 */ OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ + OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ + OID_id_ansip521r1, /* 1.3.132.0.35 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ OID_sha512, /* 2.16.840.1.101.3.4.2.3 */ diff --git a/include/linux/overflow.h b/include/linux/overflow.h index aa691f2119b0..0c7e3dcfe867 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -398,7 +398,7 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) * @count: Number of elements in the array; must be compile-time const. * @initializer: initializer expression (could be empty for no init). */ -#define _DEFINE_FLEX(type, name, member, count, initializer) \ +#define _DEFINE_FLEX(type, name, member, count, initializer...) \ _Static_assert(__builtin_constant_p(count), \ "onstack flex array members require compile-time const count"); \ union { \ @@ -408,8 +408,8 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) type *name = (type *)&name##_u /** - * DEFINE_FLEX() - Define an on-stack instance of structure with a trailing - * flexible array member. + * DEFINE_RAW_FLEX() - Define an on-stack instance of structure with a trailing + * flexible array member, when it does not have a __counted_by annotation. * * @type: structure type name, including "struct" keyword. * @name: Name for a variable to define. @@ -420,7 +420,24 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) * flexible array member. * Use __struct_size(@name) to get compile-time size of it afterwards. */ -#define DEFINE_FLEX(type, name, member, count) \ +#define DEFINE_RAW_FLEX(type, name, member, count) \ _DEFINE_FLEX(type, name, member, count, = {}) +/** + * DEFINE_FLEX() - Define an on-stack instance of structure with a trailing + * flexible array member. + * + * @TYPE: structure type name, including "struct" keyword. + * @NAME: Name for a variable to define. + * @MEMBER: Name of the array member. + * @COUNTER: Name of the __counted_by member. + * @COUNT: Number of elements in the array; must be compile-time const. + * + * Define a zeroed, on-stack, instance of @TYPE structure with a trailing + * flexible array member. + * Use __struct_size(@NAME) to get compile-time size of it afterwards. + */ +#define DEFINE_FLEX(TYPE, NAME, MEMBER, COUNTER, COUNT) \ + _DEFINE_FLEX(TYPE, NAME, MEMBER, COUNT, = { .obj.COUNTER = COUNT, }) + #endif /* __LINUX_OVERFLOW_H */ diff --git a/include/linux/padata.h b/include/linux/padata.h index 495b16b6b4d7..0146daf34430 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -137,6 +137,7 @@ struct padata_shell { * appropriate for one worker thread to do at once. * @max_threads: Max threads to use for the job, actual number may be less * depending on task size and minimum chunk size. + * @numa_aware: Distribute jobs to different nodes with CPU in a round robin fashion. */ struct padata_mt_job { void (*thread_fn)(unsigned long start, unsigned long end, void *arg); @@ -146,6 +147,7 @@ struct padata_mt_job { unsigned long align; unsigned long min_chunk; int max_threads; + bool numa_aware; }; /** @@ -178,10 +180,6 @@ struct padata_instance { #ifdef CONFIG_PADATA extern void __init padata_init(void); -#else -static inline void __init padata_init(void) {} -#endif - extern struct padata_instance *padata_alloc(const char *name); extern void padata_free(struct padata_instance *pinst); extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst); @@ -192,4 +190,12 @@ extern void padata_do_serial(struct padata_priv *padata); extern void __init padata_do_multithreaded(struct padata_mt_job *job); extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask); +#else +static inline void __init padata_init(void) {} +static inline void __init padata_do_multithreaded(struct padata_mt_job *job) +{ + job->thread_fn(job->start, job->start + job->size, job->fn_arg); +} +#endif + #endif diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 735cddc13d20..4bf1c25fd1dc 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -190,7 +190,6 @@ enum pageflags { /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_error, - PG_hugetlb = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ }; @@ -237,7 +236,7 @@ static inline const struct page *page_fixed_fake_head(const struct page *page) } #endif -static __always_inline int page_is_fake_head(struct page *page) +static __always_inline int page_is_fake_head(const struct page *page) { return page_fixed_fake_head(page) != page; } @@ -281,12 +280,12 @@ static inline unsigned long _compound_head(const struct page *page) */ #define folio_page(folio, n) nth_page(&(folio)->page, n) -static __always_inline int PageTail(struct page *page) +static __always_inline int PageTail(const struct page *page) { return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page); } -static __always_inline int PageCompound(struct page *page) +static __always_inline int PageCompound(const struct page *page) { return test_bit(PG_head, &page->flags) || READ_ONCE(page->compound_head) & 1; @@ -306,6 +305,16 @@ static inline void page_init_poison(struct page *page, size_t size) } #endif +static const unsigned long *const_folio_flags(const struct folio *folio, + unsigned n) +{ + const struct page *page = &folio->page; + + VM_BUG_ON_PGFLAGS(PageTail(page), page); + VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); + return &page[n].flags; +} + static unsigned long *folio_flags(struct folio *folio, unsigned n) { struct page *page = &folio->page; @@ -328,9 +337,6 @@ static unsigned long *folio_flags(struct folio *folio, unsigned n) * for compound page all operations related to the page flag applied to * head page. * - * PF_ONLY_HEAD: - * for compound page, callers only ever operate on the head page. - * * PF_NO_TAIL: * modifications of the page flag must be done on small or head pages, * checks can be done on tail pages too. @@ -346,9 +352,6 @@ static unsigned long *folio_flags(struct folio *folio, unsigned n) page; }) #define PF_ANY(page, enforce) PF_POISONED_CHECK(page) #define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page)) -#define PF_ONLY_HEAD(page, enforce) ({ \ - VM_BUG_ON_PGFLAGS(PageTail(page), page); \ - PF_POISONED_CHECK(page); }) #define PF_NO_TAIL(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ PF_POISONED_CHECK(compound_head(page)); }) @@ -362,59 +365,81 @@ static unsigned long *folio_flags(struct folio *folio, unsigned n) /* Which page is the flag stored in */ #define FOLIO_PF_ANY 0 #define FOLIO_PF_HEAD 0 -#define FOLIO_PF_ONLY_HEAD 0 #define FOLIO_PF_NO_TAIL 0 #define FOLIO_PF_NO_COMPOUND 0 #define FOLIO_PF_SECOND 1 +#define FOLIO_HEAD_PAGE 0 +#define FOLIO_SECOND_PAGE 1 + /* * Macros to create function definitions for page flags */ +#define FOLIO_TEST_FLAG(name, page) \ +static __always_inline bool folio_test_##name(const struct folio *folio) \ +{ return test_bit(PG_##name, const_folio_flags(folio, page)); } + +#define FOLIO_SET_FLAG(name, page) \ +static __always_inline void folio_set_##name(struct folio *folio) \ +{ set_bit(PG_##name, folio_flags(folio, page)); } + +#define FOLIO_CLEAR_FLAG(name, page) \ +static __always_inline void folio_clear_##name(struct folio *folio) \ +{ clear_bit(PG_##name, folio_flags(folio, page)); } + +#define __FOLIO_SET_FLAG(name, page) \ +static __always_inline void __folio_set_##name(struct folio *folio) \ +{ __set_bit(PG_##name, folio_flags(folio, page)); } + +#define __FOLIO_CLEAR_FLAG(name, page) \ +static __always_inline void __folio_clear_##name(struct folio *folio) \ +{ __clear_bit(PG_##name, folio_flags(folio, page)); } + +#define FOLIO_TEST_SET_FLAG(name, page) \ +static __always_inline bool folio_test_set_##name(struct folio *folio) \ +{ return test_and_set_bit(PG_##name, folio_flags(folio, page)); } + +#define FOLIO_TEST_CLEAR_FLAG(name, page) \ +static __always_inline bool folio_test_clear_##name(struct folio *folio) \ +{ return test_and_clear_bit(PG_##name, folio_flags(folio, page)); } + +#define FOLIO_FLAG(name, page) \ +FOLIO_TEST_FLAG(name, page) \ +FOLIO_SET_FLAG(name, page) \ +FOLIO_CLEAR_FLAG(name, page) + #define TESTPAGEFLAG(uname, lname, policy) \ -static __always_inline bool folio_test_##lname(struct folio *folio) \ -{ return test_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ -static __always_inline int Page##uname(struct page *page) \ +FOLIO_TEST_FLAG(lname, FOLIO_##policy) \ +static __always_inline int Page##uname(const struct page *page) \ { return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ -static __always_inline \ -void folio_set_##lname(struct folio *folio) \ -{ set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ +FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void SetPage##uname(struct page *page) \ { set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ -static __always_inline \ -void folio_clear_##lname(struct folio *folio) \ -{ clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ +FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void ClearPage##uname(struct page *page) \ { clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ -static __always_inline \ -void __folio_set_##lname(struct folio *folio) \ -{ __set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ +__FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void __SetPage##uname(struct page *page) \ { __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ -static __always_inline \ -void __folio_clear_##lname(struct folio *folio) \ -{ __clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ +__FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void __ClearPage##uname(struct page *page) \ { __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ -static __always_inline \ -bool folio_test_set_##lname(struct folio *folio) \ -{ return test_and_set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ +FOLIO_TEST_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestSetPage##uname(struct page *page) \ { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ -static __always_inline \ -bool folio_test_clear_##lname(struct folio *folio) \ -{ return test_and_clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ +FOLIO_TEST_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestClearPage##uname(struct page *page) \ { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } @@ -432,30 +457,51 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) +#define FOLIO_TEST_FLAG_FALSE(name) \ +static inline bool folio_test_##name(const struct folio *folio) \ +{ return false; } +#define FOLIO_SET_FLAG_NOOP(name) \ +static inline void folio_set_##name(struct folio *folio) { } +#define FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void folio_clear_##name(struct folio *folio) { } +#define __FOLIO_SET_FLAG_NOOP(name) \ +static inline void __folio_set_##name(struct folio *folio) { } +#define __FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void __folio_clear_##name(struct folio *folio) { } +#define FOLIO_TEST_SET_FLAG_FALSE(name) \ +static inline bool folio_test_set_##name(struct folio *folio) \ +{ return false; } +#define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ +static inline bool folio_test_clear_##name(struct folio *folio) \ +{ return false; } + +#define FOLIO_FLAG_FALSE(name) \ +FOLIO_TEST_FLAG_FALSE(name) \ +FOLIO_SET_FLAG_NOOP(name) \ +FOLIO_CLEAR_FLAG_NOOP(name) + #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ +FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_set_##lname(struct folio *folio) { } \ +FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_clear_##lname(struct folio *folio) { } \ +FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void __folio_clear_##lname(struct folio *folio) { } \ +__FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ -static inline bool folio_test_set_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ -static inline bool folio_test_clear_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ @@ -465,7 +511,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) -PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) +FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE) PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) @@ -532,13 +578,13 @@ PAGEFLAG_FALSE(HighMem, highmem) #endif #ifdef CONFIG_SWAP -static __always_inline bool folio_test_swapcache(struct folio *folio) +static __always_inline bool folio_test_swapcache(const struct folio *folio) { return folio_test_swapbacked(folio) && - test_bit(PG_swapcache, folio_flags(folio, 0)); + test_bit(PG_swapcache, const_folio_flags(folio, 0)); } -static __always_inline bool PageSwapCache(struct page *page) +static __always_inline bool PageSwapCache(const struct page *page) { return folio_test_swapcache(page_folio(page)); } @@ -583,10 +629,10 @@ PAGEFLAG_FALSE(HWPoison, hwpoison) #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) -TESTPAGEFLAG(Young, young, PF_ANY) -SETPAGEFLAG(Young, young, PF_ANY) -TESTCLEARFLAG(Young, young, PF_ANY) -PAGEFLAG(Idle, idle, PF_ANY) +FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE) +FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE) +FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE) +FOLIO_FLAG(idle, FOLIO_HEAD_PAGE) #endif /* @@ -637,22 +683,22 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) */ #define PAGE_MAPPING_DAX_SHARED ((void *)0x1) -static __always_inline bool folio_mapping_flags(struct folio *folio) +static __always_inline bool folio_mapping_flags(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; } -static __always_inline int PageMappingFlags(struct page *page) +static __always_inline int PageMappingFlags(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } -static __always_inline bool folio_test_anon(struct folio *folio) +static __always_inline bool folio_test_anon(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0; } -static __always_inline bool PageAnon(struct page *page) +static __always_inline bool PageAnon(const struct page *page) { return folio_test_anon(page_folio(page)); } @@ -663,7 +709,7 @@ static __always_inline bool __folio_test_movable(const struct folio *folio) PAGE_MAPPING_MOVABLE; } -static __always_inline int __PageMovable(struct page *page) +static __always_inline int __PageMovable(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; @@ -676,13 +722,13 @@ static __always_inline int __PageMovable(struct page *page) * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ -static __always_inline bool folio_test_ksm(struct folio *folio) +static __always_inline bool folio_test_ksm(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } -static __always_inline bool PageKsm(struct page *page) +static __always_inline bool PageKsm(const struct page *page) { return folio_test_ksm(page_folio(page)); } @@ -721,9 +767,9 @@ static inline bool folio_xor_flags_has_waiters(struct folio *folio, * some of the bytes in it may be; see the is_partially_uptodate() * address_space operation. */ -static inline bool folio_test_uptodate(struct folio *folio) +static inline bool folio_test_uptodate(const struct folio *folio) { - bool ret = test_bit(PG_uptodate, folio_flags(folio, 0)); + bool ret = test_bit(PG_uptodate, const_folio_flags(folio, 0)); /* * Must ensure that the data we read out of the folio is loaded * _after_ we've loaded folio->flags to check the uptodate bit. @@ -738,7 +784,7 @@ static inline bool folio_test_uptodate(struct folio *folio) return ret; } -static inline int PageUptodate(struct page *page) +static inline int PageUptodate(const struct page *page) { return folio_test_uptodate(page_folio(page)); } @@ -780,12 +826,12 @@ void set_page_writeback(struct page *page); #define folio_start_writeback_keepwrite(folio) \ __folio_start_writeback(folio, true) -static __always_inline bool folio_test_head(struct folio *folio) +static __always_inline bool folio_test_head(const struct folio *folio) { - return test_bit(PG_head, folio_flags(folio, FOLIO_PF_ANY)); + return test_bit(PG_head, const_folio_flags(folio, FOLIO_PF_ANY)); } -static __always_inline int PageHead(struct page *page) +static __always_inline int PageHead(const struct page *page) { PF_POISONED_CHECK(page); return test_bit(PG_head, &page->flags) && !page_is_fake_head(page); @@ -801,7 +847,7 @@ CLEARPAGEFLAG(Head, head, PF_ANY) * * Return: True if the folio is larger than one page. */ -static inline bool folio_test_large(struct folio *folio) +static inline bool folio_test_large(const struct folio *folio) { return folio_test_head(folio); } @@ -829,29 +875,6 @@ TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) #define PG_head_mask ((1UL << PG_head)) -#ifdef CONFIG_HUGETLB_PAGE -int PageHuge(struct page *page); -SETPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) -CLEARPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) - -/** - * folio_test_hugetlb - Determine if the folio belongs to hugetlbfs - * @folio: The folio to test. - * - * Context: Any context. Caller should have a reference on the folio to - * prevent it from being turned into a tail page. - * Return: True for hugetlbfs folios, false for anon folios or folios - * belonging to other filesystems. - */ -static inline bool folio_test_hugetlb(struct folio *folio) -{ - return folio_test_large(folio) && - test_bit(PG_hugetlb, folio_flags(folio, 1)); -} -#else -TESTPAGEFLAG_FALSE(Huge, hugetlb) -#endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for @@ -861,7 +884,7 @@ TESTPAGEFLAG_FALSE(Huge, hugetlb) * hugetlbfs pages, but not normal pages. PageTransHuge() can only be * called only in the core VM paths where hugetlbfs pages can't exist. */ -static inline int PageTransHuge(struct page *page) +static inline int PageTransHuge(const struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); return PageHead(page); @@ -872,7 +895,7 @@ static inline int PageTransHuge(struct page *page) * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ -static inline int PageTransCompound(struct page *page) +static inline int PageTransCompound(const struct page *page) { return PageCompound(page); } @@ -882,7 +905,7 @@ static inline int PageTransCompound(struct page *page) * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ -static inline int PageTransTail(struct page *page) +static inline int PageTransTail(const struct page *page) { return PageTail(page); } @@ -908,33 +931,22 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif /* - * Check if a page is currently marked HWPoisoned. Note that this check is - * best effort only and inherently racy: there is no way to synchronize with - * failing hardware. - */ -static inline bool is_page_hwpoison(struct page *page) -{ - if (PageHWPoison(page)) - return true; - return PageHuge(page) && PageHWPoison(compound_head(page)); -} - -/* * For pages that are never mapped to userspace (and aren't PageSlab), * page_type may be used. Because it is initialised to -1, we invert the * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and - * low bits so that an underflow or overflow of page_mapcount() won't be + * low bits so that an underflow or overflow of _mapcount won't be * mistaken for a page type value. */ #define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of page_mapcount */ +/* Reserve 0x0000007f to catch underflows of _mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 #define PG_offline 0x00000100 #define PG_table 0x00000200 #define PG_guard 0x00000400 +#define PG_hugetlb 0x00000800 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) @@ -946,40 +958,43 @@ 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) +static inline int page_has_type(const struct page *page) { return page_type_has_type(page->page_type); } +#define FOLIO_TYPE_OPS(lname, fname) \ +static __always_inline bool folio_test_##fname(const struct folio *folio)\ +{ \ + return folio_test_type(folio, PG_##lname); \ +} \ +static __always_inline void __folio_set_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ + folio->page.page_type &= ~PG_##lname; \ +} \ +static __always_inline void __folio_clear_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ + folio->page.page_type |= PG_##lname; \ +} + #define PAGE_TYPE_OPS(uname, lname, fname) \ +FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ return PageType(page, PG_##lname); \ } \ -static __always_inline int folio_test_##fname(const struct folio *folio)\ -{ \ - return folio_test_type(folio, PG_##lname); \ -} \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!PageType(page, 0), page); \ page->page_type &= ~PG_##lname; \ } \ -static __always_inline void __folio_set_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ - folio->page.page_type &= ~PG_##lname; \ -} \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type |= PG_##lname; \ -} \ -static __always_inline void __folio_clear_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ - folio->page.page_type |= PG_##lname; \ -} \ +} /* * PageBuddy() indicates that the page is free and in the buddy system @@ -1026,11 +1041,42 @@ PAGE_TYPE_OPS(Table, table, pgtable) */ PAGE_TYPE_OPS(Guard, guard, guard) +#ifdef CONFIG_HUGETLB_PAGE +FOLIO_TYPE_OPS(hugetlb, hugetlb) +#else +FOLIO_TEST_FLAG_FALSE(hugetlb) +#endif + +/** + * PageHuge - Determine if the page belongs to hugetlbfs + * @page: The page to test. + * + * Context: Any context. + * Return: True for hugetlbfs pages, false for anon pages or pages + * belonging to other filesystems. + */ +static inline bool PageHuge(const struct page *page) +{ + return folio_test_hugetlb(page_folio(page)); +} + +/* + * Check if a page is currently marked HWPoisoned. Note that this check is + * best effort only and inherently racy: there is no way to synchronize with + * failing hardware. + */ +static inline bool is_page_hwpoison(struct page *page) +{ + if (PageHWPoison(page)) + return true; + return PageHuge(page) && PageHWPoison(compound_head(page)); +} + extern bool is_free_buddy_page(struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); -static __always_inline int PageAnonExclusive(struct page *page) +static __always_inline int PageAnonExclusive(const struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); @@ -1092,7 +1138,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ - 1UL << PG_hugetlb | 1UL << PG_large_rmappable) + 1UL << PG_large_rmappable) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) @@ -1103,19 +1149,18 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) * Determine if a page has private stuff, indicating that release routines * should be invoked upon it. */ -static inline int page_has_private(struct page *page) +static inline int page_has_private(const struct page *page) { return !!(page->flags & PAGE_FLAGS_PRIVATE); } -static inline bool folio_has_private(struct folio *folio) +static inline bool folio_has_private(const struct folio *folio) { return page_has_private(&folio->page); } #undef PF_ANY #undef PF_HEAD -#undef PF_ONLY_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND #undef PF_SECOND diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index c141ea9a95ef..8cd858d912c4 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -4,7 +4,7 @@ #include <linux/atomic.h> #include <linux/cache.h> -#include <linux/kernel.h> +#include <linux/limits.h> #include <asm/page.h> struct page_counter { diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 119a0c9d2a8b..debdc25f08b9 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -11,7 +11,8 @@ extern struct page_ext_operations page_owner_ops; extern void __reset_page_owner(struct page *page, unsigned short order); extern void __set_page_owner(struct page *page, unsigned short order, gfp_t gfp_mask); -extern void __split_page_owner(struct page *page, unsigned int nr); +extern void __split_page_owner(struct page *page, int old_order, + int new_order); extern void __folio_copy_owner(struct folio *newfolio, struct folio *old); extern void __set_page_owner_migrate_reason(struct page *page, int reason); extern void __dump_page_owner(const struct page *page); @@ -31,10 +32,11 @@ static inline void set_page_owner(struct page *page, __set_page_owner(page, order, gfp_mask); } -static inline void split_page_owner(struct page *page, unsigned int nr) +static inline void split_page_owner(struct page *page, int old_order, + int new_order) { if (static_branch_unlikely(&page_owner_inited)) - __split_page_owner(page, nr); + __split_page_owner(page, old_order, new_order); } static inline void folio_copy_owner(struct folio *newfolio, struct folio *old) { @@ -56,11 +58,11 @@ static inline void reset_page_owner(struct page *page, unsigned short order) { } static inline void set_page_owner(struct page *page, - unsigned int order, gfp_t gfp_mask) + unsigned short order, gfp_t gfp_mask) { } -static inline void split_page_owner(struct page *page, - unsigned short order) +static inline void split_page_owner(struct page *page, int old_order, + int new_order) { } static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2df35e65557d..c5e33e2ca48a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -40,6 +40,8 @@ int filemap_fdatawait_keep_errors(struct address_space *mapping); int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte); +int filemap_invalidate_inode(struct inode *inode, bool flush, + loff_t start, loff_t end); static inline int filemap_fdatawait(struct address_space *mapping) { diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 87cc678adc85..5d3a0cccc6bf 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -11,8 +11,8 @@ #include <linux/types.h> -/* 15 pointers + header align the folio_batch structure to a power of two */ -#define PAGEVEC_SIZE 15 +/* 31 pointers + header align the folio_batch structure to a power of two */ +#define PAGEVEC_SIZE 31 struct folio; @@ -27,6 +27,7 @@ struct folio; */ struct folio_batch { unsigned char nr; + unsigned char i; bool percpu_pvec_drained; struct folio *folios[PAGEVEC_SIZE]; }; @@ -40,12 +41,14 @@ struct folio_batch { static inline void folio_batch_init(struct folio_batch *fbatch) { fbatch->nr = 0; + fbatch->i = 0; fbatch->percpu_pvec_drained = false; } static inline void folio_batch_reinit(struct folio_batch *fbatch) { fbatch->nr = 0; + fbatch->i = 0; } static inline unsigned int folio_batch_count(struct folio_batch *fbatch) @@ -75,6 +78,21 @@ static inline unsigned folio_batch_add(struct folio_batch *fbatch, return folio_batch_space(fbatch); } +/** + * folio_batch_next - Return the next folio to process. + * @fbatch: The folio batch being processed. + * + * Use this function to implement a queue of folios. + * + * Return: The next folio in the queue, or NULL if the queue is empty. + */ +static inline struct folio *folio_batch_next(struct folio_batch *fbatch) +{ + if (fbatch->i == fbatch->nr) + return NULL; + return fbatch->folios[fbatch->i++]; +} + void __folio_batch_release(struct folio_batch *pvec); static inline void folio_batch_release(struct folio_batch *fbatch) diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 40ea18f5aa02..cc2f70d061c8 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -146,15 +146,44 @@ struct pci_epc { }; /** + * @BAR_PROGRAMMABLE: The BAR mask can be configured by the EPC. + * @BAR_FIXED: The BAR mask is fixed by the hardware. + * @BAR_RESERVED: The BAR should not be touched by an EPF driver. + */ +enum pci_epc_bar_type { + BAR_PROGRAMMABLE = 0, + BAR_FIXED, + BAR_RESERVED, +}; + +/** + * struct pci_epc_bar_desc - hardware description for a BAR + * @type: the type of the BAR + * @fixed_size: the fixed size, only applicable if type is BAR_FIXED_MASK. + * @only_64bit: if true, an EPF driver is not allowed to choose if this BAR + * should be configured as 32-bit or 64-bit, the EPF driver must + * configure this BAR as 64-bit. Additionally, the BAR succeeding + * this BAR must be set to type BAR_RESERVED. + * + * only_64bit should not be set on a BAR of type BAR_RESERVED. + * (If BARx is a 64-bit BAR that an EPF driver is not allowed to + * touch, then both BARx and BARx+1 must be set to type + * BAR_RESERVED.) + */ +struct pci_epc_bar_desc { + enum pci_epc_bar_type type; + u64 fixed_size; + bool only_64bit; +}; + +/** * struct pci_epc_features - features supported by a EPC device per function * @linkup_notifier: indicate if the EPC device can notify EPF driver on link up * @core_init_notifier: indicate cores that can notify about their availability * for initialization * @msi_capable: indicate if the endpoint function has MSI capability * @msix_capable: indicate if the endpoint function has MSI-X capability - * @reserved_bar: bitmap to indicate reserved BAR unavailable to function driver - * @bar_fixed_64bit: bitmap to indicate fixed 64bit BARs - * @bar_fixed_size: Array specifying the size supported by each BAR + * @bar: array specifying the hardware description for each BAR * @align: alignment size required for BAR buffer allocation */ struct pci_epc_features { @@ -162,9 +191,7 @@ struct pci_epc_features { unsigned int core_init_notifier : 1; unsigned int msi_capable : 1; unsigned int msix_capable : 1; - u8 reserved_bar; - u8 bar_fixed_64bit; - u64 bar_fixed_size[PCI_STD_NUM_BARS]; + struct pci_epc_bar_desc bar[PCI_STD_NUM_BARS]; size_t align; }; diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 77b146e0f672..adee6a1b35db 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -15,6 +15,7 @@ #include <linux/pci.h> struct pci_epf; +struct pci_epc_features; enum pci_epc_interface_type; enum pci_barno { @@ -216,7 +217,8 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver, struct module *owner); void pci_epf_unregister_driver(struct pci_epf_driver *driver); void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, - size_t align, enum pci_epc_interface_type type); + const struct pci_epc_features *epc_features, + enum pci_epc_interface_type type); void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar, enum pci_epc_interface_type type); int pci_epf_bind(struct pci_epf *epf); diff --git a/include/linux/pci.h b/include/linux/pci.h index 7ab0d13672da..16493426a04f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -390,9 +390,9 @@ struct pci_dev { unsigned int d3hot_delay; /* D3hot->D0 transition time in ms */ unsigned int d3cold_delay; /* D3cold->D0 transition time in ms */ + u16 l1ss; /* L1SS Capability pointer */ #ifdef CONFIG_PCIEASPM struct pcie_link_state *link_state; /* ASPM link state */ - u16 l1ss; /* L1SS Capability pointer */ unsigned int ltr_path:1; /* Latency Tolerance Reporting supported from root to here */ #endif @@ -2517,6 +2517,11 @@ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) return NULL; } +static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) +{ + return dev->error_state == pci_channel_io_perm_failure; +} + void pci_request_acs(void); bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags); bool pci_acs_path_enabled(struct pci_dev *start, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a0c75e467df3..7a099e1282d2 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -580,6 +580,7 @@ #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F3 0x12fb #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3 0x12c3 #define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3 0x16fb +#define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3 0x12bb #define PCI_DEVICE_ID_AMD_MI200_DF_F3 0x14d3 #define PCI_DEVICE_ID_AMD_MI300_DF_F3 0x152b #define PCI_DEVICE_ID_AMD_VANGOGH_USB 0x163a @@ -2686,8 +2687,10 @@ #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_HDA_HSW_0 0x0a0c +#define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 #define PCI_DEVICE_ID_INTEL_HDA_HSW_2 0x0c0c #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 +#define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe #define PCI_DEVICE_ID_INTEL_HDA_HSW_3 0x0d0c #define PCI_DEVICE_ID_INTEL_HDA_BYT 0x0f04 #define PCI_DEVICE_ID_INTEL_SST_BYT 0x0f28 @@ -3106,6 +3109,7 @@ #define PCI_DEVICE_ID_INTEL_HDA_CML_S 0xa3f0 #define PCI_DEVICE_ID_INTEL_HDA_LNL_P 0xa828 #define PCI_DEVICE_ID_INTEL_S21152BB 0xb152 +#define PCI_DEVICE_ID_INTEL_HDA_BMG 0xe2f7 #define PCI_DEVICE_ID_INTEL_HDA_CML_R 0xf0c8 #define PCI_DEVICE_ID_INTEL_HDA_RKL_S 0xf1c8 diff --git a/include/linux/peci.h b/include/linux/peci.h index 9b3d36aff431..90e241458ef6 100644 --- a/include/linux/peci.h +++ b/include/linux/peci.h @@ -58,7 +58,6 @@ static inline struct peci_controller *to_peci_controller(void *d) /** * struct peci_device - PECI device * @dev: device object to register PECI device to the device model - * @controller: manages the bus segment hosting this PECI device * @info: PECI device characteristics * @info.family: device family * @info.model: device model diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d2a15c0c6f8a..a5304ae8c654 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -809,11 +809,8 @@ struct perf_event { u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; -#ifdef CONFIG_BPF_SYSCALL - perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; u64 bpf_cookie; -#endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; @@ -883,6 +880,7 @@ struct perf_event_pmu_context { unsigned int nr_events; unsigned int nr_cgroups; + unsigned int nr_freq; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; @@ -897,6 +895,11 @@ struct perf_event_pmu_context { int rotate_necessary; }; +static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc) +{ + return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active); +} + struct perf_event_groups { struct rb_root tree; u64 index; @@ -1342,8 +1345,10 @@ extern int perf_event_output(struct perf_event *event, struct pt_regs *regs); static inline bool -__is_default_overflow_handler(perf_overflow_handler_t overflow_handler) +is_default_overflow_handler(struct perf_event *event) { + perf_overflow_handler_t overflow_handler = event->overflow_handler; + if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) @@ -1351,22 +1356,6 @@ __is_default_overflow_handler(perf_overflow_handler_t overflow_handler) return false; } -#define is_default_overflow_handler(event) \ - __is_default_overflow_handler((event)->overflow_handler) - -#ifdef CONFIG_BPF_SYSCALL -static inline bool uses_default_overflow_handler(struct perf_event *event) -{ - if (likely(is_default_overflow_handler(event))) - return true; - - return __is_default_overflow_handler(event->orig_overflow_handler); -} -#else -#define uses_default_overflow_handler(event) \ - is_default_overflow_handler(event) -#endif - extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, @@ -1697,6 +1686,14 @@ perf_event_addr_filters(struct perf_event *event) return ifh; } +static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) +{ + /* Only the parent has fasync state */ + if (event->parent) + event = event->parent; + return &event->fasync; +} + extern void perf_event_addr_filters_sync(struct perf_event *event); extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index f6d0e3513948..85fc7554cd52 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -212,15 +212,37 @@ static inline int pmd_dirty(pmd_t pmd) #define arch_flush_lazy_mmu_mode() do {} while (0) #endif -#ifndef set_ptes +#ifndef pte_batch_hint +/** + * pte_batch_hint - Number of pages that can be added to batch without scanning. + * @ptep: Page table pointer for the entry. + * @pte: Page table entry. + * + * Some architectures know that a set of contiguous ptes all map the same + * contiguous memory with the same permissions. In this case, it can provide a + * hint to aid pte batching without the core code needing to scan every pte. + * + * An architecture implementation may ignore the PTE accessed state. Further, + * the dirty state must apply atomically to all the PTEs described by the hint. + * + * May be overridden by the architecture, else pte_batch_hint is always 1. + */ +static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte) +{ + return 1; +} +#endif -#ifndef pte_next_pfn -static inline pte_t pte_next_pfn(pte_t pte) +#ifndef pte_advance_pfn +static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { - return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); + return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); } #endif +#define pte_next_pfn(pte) pte_advance_pfn(pte, 1) + +#ifndef set_ptes /** * set_ptes - Map consecutive pages to a contiguous range of addresses. * @mm: Address space to map the pages into. @@ -229,6 +251,10 @@ static inline pte_t pte_next_pfn(pte_t pte) * @pte: Page table entry for the first page. * @nr: Number of pages to map. * + * When nr==1, initial state of pte may be present or not present, and new state + * may be present or not present. When nr>1, initial state of all ptes must be + * not present, and new state must be present. + * * May be overridden by the architecture, or the architecture can define * set_pte() and PFN_PTE_SHIFT. * @@ -580,6 +606,76 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, } #endif +#ifndef get_and_clear_full_ptes +/** + * get_and_clear_full_ptes - Clear present PTEs that map consecutive pages of + * the same folio, collecting dirty/accessed bits. + * @mm: Address space the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to clear. + * @full: Whether we are clearing a full mm. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over ptep_get_and_clear_full(), merging dirty/accessed bits into the + * returned PTE. + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, unsigned int nr, int full) +{ + pte_t pte, tmp_pte; + + pte = ptep_get_and_clear_full(mm, addr, ptep, full); + while (--nr) { + ptep++; + addr += PAGE_SIZE; + tmp_pte = ptep_get_and_clear_full(mm, addr, ptep, full); + if (pte_dirty(tmp_pte)) + pte = pte_mkdirty(pte); + if (pte_young(tmp_pte)) + pte = pte_mkyoung(pte); + } + return pte; +} +#endif + +#ifndef clear_full_ptes +/** + * clear_full_ptes - Clear present PTEs that map consecutive pages of the same + * folio. + * @mm: Address space the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to clear. + * @full: Whether we are clearing a full mm. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over ptep_get_and_clear_full(). + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned int nr, int full) +{ + for (;;) { + ptep_get_and_clear_full(mm, addr, ptep, full); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif /* * If two threads concurrently fault at the same page, the thread that @@ -650,6 +746,37 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres } #endif +#ifndef wrprotect_ptes +/** + * wrprotect_ptes - Write-protect PTEs that map consecutive pages of the same + * folio. + * @mm: Address space the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to write-protect. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over ptep_set_wrprotect(). + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned int nr) +{ + for (;;) { + ptep_set_wrprotect(mm, addr, ptep); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + /* * On some architectures hardware does not set page access bit when accessing * memory page, it is responsibility of software setting this bit. It brings @@ -1650,16 +1777,16 @@ typedef unsigned int pgtbl_mod_mask; * Only meaningful when called on a valid entry. */ #ifndef pgd_leaf -#define pgd_leaf(x) 0 +#define pgd_leaf(x) false #endif #ifndef p4d_leaf -#define p4d_leaf(x) 0 +#define p4d_leaf(x) false #endif #ifndef pud_leaf -#define pud_leaf(x) 0 +#define pud_leaf(x) false #endif #ifndef pmd_leaf -#define pmd_leaf(x) 0 +#define pmd_leaf(x) false #endif #ifndef pgd_leaf_size diff --git a/include/linux/phy.h b/include/linux/phy.h index 3f68b8239bb1..e6e83304558e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -778,6 +778,7 @@ struct phy_device { /* Generic phy_device::dev_flags */ #define PHY_F_NO_IRQ 0x80000000 +#define PHY_F_RXC_ALWAYS_ON 0x40000000 static inline struct phy_device *to_phy_device(const struct device *dev) { diff --git a/include/linux/phy/phy-dp.h b/include/linux/phy/phy-dp.h index 18cad23642cd..9cce5766bc0b 100644 --- a/include/linux/phy/phy-dp.h +++ b/include/linux/phy/phy-dp.h @@ -8,6 +8,9 @@ #include <linux/types.h> +#define PHY_SUBMODE_DP 0 +#define PHY_SUBMODE_EDP 1 + /** * struct phy_configure_opts_dp - DisplayPort PHY configuration set * diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index f6d607ef0e80..03cd5bae92d3 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -122,6 +122,11 @@ struct phy_ops { union phy_configure_opts *opts); int (*reset)(struct phy *phy); int (*calibrate)(struct phy *phy); + + /* notify phy connect status change */ + int (*connect)(struct phy *phy, int port); + int (*disconnect)(struct phy *phy, int port); + void (*release)(struct phy *phy); struct module *owner; }; @@ -176,7 +181,7 @@ struct phy_provider { struct module *owner; struct list_head list; struct phy * (*of_xlate)(struct device *dev, - struct of_phandle_args *args); + const struct of_phandle_args *args); }; /** @@ -243,6 +248,8 @@ static inline enum phy_mode phy_get_mode(struct phy *phy) } int phy_reset(struct phy *phy); int phy_calibrate(struct phy *phy); +int phy_notify_connect(struct phy *phy, int port); +int phy_notify_disconnect(struct phy *phy, int port); static inline int phy_get_bus_width(struct phy *phy) { return phy->attrs.bus_width; @@ -265,7 +272,7 @@ void phy_put(struct device *dev, struct phy *phy); void devm_phy_put(struct device *dev, struct phy *phy); struct phy *of_phy_get(struct device_node *np, const char *con_id); struct phy *of_phy_simple_xlate(struct device *dev, - struct of_phandle_args *args); + const struct of_phandle_args *args); struct phy *phy_create(struct device *dev, struct device_node *node, const struct phy_ops *ops); struct phy *devm_phy_create(struct device *dev, struct device_node *node, @@ -275,11 +282,11 @@ void devm_phy_destroy(struct device *dev, struct phy *phy); struct phy_provider *__of_phy_provider_register(struct device *dev, struct device_node *children, struct module *owner, struct phy * (*of_xlate)(struct device *dev, - struct of_phandle_args *args)); + const struct of_phandle_args *args)); struct phy_provider *__devm_of_phy_provider_register(struct device *dev, struct device_node *children, struct module *owner, struct phy * (*of_xlate)(struct device *dev, - struct of_phandle_args *args)); + const struct of_phandle_args *args)); void of_phy_provider_unregister(struct phy_provider *phy_provider); void devm_of_phy_provider_unregister(struct device *dev, struct phy_provider *phy_provider); @@ -396,6 +403,20 @@ static inline int phy_calibrate(struct phy *phy) return -ENOSYS; } +static inline int phy_notify_connect(struct phy *phy, int index) +{ + if (!phy) + return 0; + return -ENOSYS; +} + +static inline int phy_notify_disconnect(struct phy *phy, int index) +{ + if (!phy) + return 0; + return -ENOSYS; +} + static inline int phy_configure(struct phy *phy, union phy_configure_opts *opts) { @@ -479,7 +500,7 @@ static inline struct phy *of_phy_get(struct device_node *np, const char *con_id) } static inline struct phy *of_phy_simple_xlate(struct device *dev, - struct of_phandle_args *args) + const struct of_phandle_args *args) { return ERR_PTR(-ENOSYS); } @@ -509,7 +530,7 @@ static inline void devm_phy_destroy(struct device *dev, struct phy *phy) static inline struct phy_provider *__of_phy_provider_register( struct device *dev, struct device_node *children, struct module *owner, struct phy * (*of_xlate)(struct device *dev, - struct of_phandle_args *args)) + const struct of_phandle_args *args)) { return ERR_PTR(-ENOSYS); } @@ -517,7 +538,7 @@ static inline struct phy_provider *__of_phy_provider_register( static inline struct phy_provider *__devm_of_phy_provider_register(struct device *dev, struct device_node *children, struct module *owner, struct phy * (*of_xlate)(struct device *dev, - struct of_phandle_args *args)) + const struct of_phandle_args *args)) { return ERR_PTR(-ENOSYS); } diff --git a/include/linux/phy/tegra/xusb.h b/include/linux/phy/tegra/xusb.h index 70998e6dd6fd..6ca51e0080ec 100644 --- a/include/linux/phy/tegra/xusb.h +++ b/include/linux/phy/tegra/xusb.h @@ -26,6 +26,7 @@ void tegra_phy_xusb_utmi_pad_power_down(struct phy *phy); int tegra_phy_xusb_utmi_port_reset(struct phy *phy); int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, unsigned int port); +int tegra_xusb_padctl_get_port_number(struct phy *phy); int tegra_xusb_padctl_enable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy, enum usb_device_speed speed); int tegra_xusb_padctl_disable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 9a57deefcb07..5ea6b2ad2396 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -138,6 +138,9 @@ enum phylink_op_type { * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. + * @mac_requires_rxc: if true, the MAC always requires a receive clock from PHY. + * The PHY driver should start the clock signal as soon as + * possible and avoid stopping it during suspend events. * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. @@ -150,6 +153,7 @@ struct phylink_config { enum phylink_op_type type; bool poll_fixed_state; bool mac_managed_pm; + bool mac_requires_rxc; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); @@ -392,6 +396,10 @@ struct phylink_pcs_ops; * @phylink: pointer to &struct phylink_config * @neg_mode: provide PCS neg mode via "mode" argument * @poll: poll the PCS for link changes + * @rxc_always_on: The MAC driver requires the reference clock + * to always be on. Standalone PCS drivers which + * do not have access to a PHY device can check + * this instead of PHY_F_RXC_ALWAYS_ON. * * This structure is designed to be embedded within the PCS private data, * and will be passed between phylink and the PCS. @@ -404,6 +412,7 @@ struct phylink_pcs { struct phylink *phylink; bool neg_mode; bool poll; + bool rxc_always_on; }; /** @@ -418,6 +427,8 @@ struct phylink_pcs { * @pcs_an_restart: restart 802.3z BaseX autonegotiation. * @pcs_link_up: program the PCS for the resolved link configuration * (where necessary). + * @pcs_pre_init: configure PCS components necessary for MAC hardware + * initialization e.g. RX clock for stmmac. */ struct phylink_pcs_ops { int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, @@ -437,6 +448,7 @@ struct phylink_pcs_ops { void (*pcs_an_restart)(struct phylink_pcs *pcs); void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); + int (*pcs_pre_init)(struct phylink_pcs *pcs); }; #if 0 /* For kernel-doc purposes only. */ @@ -542,6 +554,34 @@ void pcs_an_restart(struct phylink_pcs *pcs); */ void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); + +/** + * pcs_pre_init() - Configure PCS components necessary for MAC initialization + * @pcs: a pointer to a &struct phylink_pcs. + * + * This function can be called by MAC drivers through the + * phylink_pcs_pre_init() wrapper, before their hardware is initialized. It + * should not be called after the link is brought up, as reconfiguring the PCS + * at this point could break the link. + * + * Some MAC devices require specific hardware initialization to be performed by + * their associated PCS device before they can properly initialize their own + * hardware. An example of this is the initialization of stmmac controllers, + * which requires an active REF_CLK signal to be provided by the PHY/PCS. + * + * By calling phylink_pcs_pre_init(), MAC drivers can ensure that the PCS is + * setup in a way that allows for successful hardware initialization. + * + * The specific configuration performed by pcs_pre_init() is dependent on the + * model of PCS and the requirements of the MAC device attached to it. PCS + * driver authors should consider whether their target device is to be used in + * conjunction with a MAC device whose driver calls phylink_pcs_pre_init(). MAC + * driver authors should document their requirements for the PCS + * pre-initialization. + * + */ +int pcs_pre_init(struct phylink_pcs *pcs); + #endif struct phylink *phylink_create(struct phylink_config *, @@ -561,6 +601,8 @@ void phylink_disconnect_phy(struct phylink *); void phylink_mac_change(struct phylink *, bool up); void phylink_pcs_change(struct phylink_pcs *, bool up); +int phylink_pcs_pre_init(struct phylink *pl, struct phylink_pcs *pcs); + void phylink_start(struct phylink *); void phylink_stop(struct phylink *); diff --git a/include/linux/pid.h b/include/linux/pid.h index c79a0efd0258..a3aad9b4074c 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -45,6 +45,8 @@ * find_pid_ns() using the int nr and struct pid_namespace *ns. */ +#define RESERVED_PIDS 300 + struct upid { int nr; struct pid_namespace *ns; @@ -55,10 +57,8 @@ struct pid refcount_t count; unsigned int level; spinlock_t lock; -#ifdef CONFIG_FS_PID struct dentry *stashed; - unsigned long ino; -#endif + u64 ino; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 40dd325a32a6..75bdf9807802 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -4,6 +4,5 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); -bool is_pidfs_sb(const struct super_block *sb); #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 7dae17b62a4d..ecc47d5fe239 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -3961,60 +3961,52 @@ struct ec_response_i2c_passthru { } __ec_align1; /*****************************************************************************/ -/* Power button hang detect */ - +/* AP hang detect */ #define EC_CMD_HANG_DETECT 0x009F -/* Reasons to start hang detection timer */ -/* Power button pressed */ -#define EC_HANG_START_ON_POWER_PRESS BIT(0) - -/* Lid closed */ -#define EC_HANG_START_ON_LID_CLOSE BIT(1) - - /* Lid opened */ -#define EC_HANG_START_ON_LID_OPEN BIT(2) - -/* Start of AP S3->S0 transition (booting or resuming from suspend) */ -#define EC_HANG_START_ON_RESUME BIT(3) - -/* Reasons to cancel hang detection */ +#define EC_HANG_DETECT_MIN_TIMEOUT 5 +#define EC_HANG_DETECT_MAX_TIMEOUT 65535 -/* Power button released */ -#define EC_HANG_STOP_ON_POWER_RELEASE BIT(8) +/* EC hang detect commands */ +enum ec_hang_detect_cmds { + /* Reload AP hang detect timer. */ + EC_HANG_DETECT_CMD_RELOAD = 0x0, -/* Any host command from AP received */ -#define EC_HANG_STOP_ON_HOST_COMMAND BIT(9) + /* Stop AP hang detect timer. */ + EC_HANG_DETECT_CMD_CANCEL = 0x1, -/* Stop on end of AP S0->S3 transition (suspending or shutting down) */ -#define EC_HANG_STOP_ON_SUSPEND BIT(10) + /* Configure watchdog with given reboot timeout and + * cancel currently running AP hang detect timer. + */ + EC_HANG_DETECT_CMD_SET_TIMEOUT = 0x2, -/* - * If this flag is set, all the other fields are ignored, and the hang detect - * timer is started. This provides the AP a way to start the hang timer - * without reconfiguring any of the other hang detect settings. Note that - * you must previously have configured the timeouts. - */ -#define EC_HANG_START_NOW BIT(30) + /* Get last hang status - whether the AP boot was clear or not */ + EC_HANG_DETECT_CMD_GET_STATUS = 0x3, -/* - * If this flag is set, all the other fields are ignored (including - * EC_HANG_START_NOW). This provides the AP a way to stop the hang timer - * without reconfiguring any of the other hang detect settings. - */ -#define EC_HANG_STOP_NOW BIT(31) + /* Clear last hang status. Called when AP is rebooting/shutting down + * gracefully. + */ + EC_HANG_DETECT_CMD_CLEAR_STATUS = 0x4 +}; struct ec_params_hang_detect { - /* Flags; see EC_HANG_* */ - uint32_t flags; - - /* Timeout in msec before generating host event, if enabled */ - uint16_t host_event_timeout_msec; + uint16_t command; /* enum ec_hang_detect_cmds */ + /* Timeout in seconds before generating reboot */ + uint16_t reboot_timeout_sec; +} __ec_align2; - /* Timeout in msec before generating warm reboot, if enabled */ - uint16_t warm_reboot_timeout_msec; -} __ec_align4; +/* Status codes that describe whether AP has boot normally or the hang has been + * detected and EC has reset AP + */ +enum ec_hang_detect_status { + EC_HANG_DETECT_AP_BOOT_NORMAL = 0x0, + EC_HANG_DETECT_AP_BOOT_EC_WDT = 0x1, + EC_HANG_DETECT_AP_BOOT_COUNT, +}; +struct ec_response_hang_detect { + uint8_t status; /* enum ec_hang_detect_status */ +} __ec_align1; /*****************************************************************************/ /* Commands for battery charging */ diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h index c8645b2ed3c0..b9c8520b4bd3 100644 --- a/include/linux/platform_data/davinci_asp.h +++ b/include/linux/platform_data/davinci_asp.h @@ -26,16 +26,6 @@ struct davinci_mcasp_pdata { struct gen_pool *sram_pool; /* - * If McBSP peripheral gets the clock from an external pin, - * there are three chooses, that are MCBSP_CLKX, MCBSP_CLKR - * and MCBSP_CLKS. - * Depending on different hardware connections it is possible - * to use this setting to change the behaviour of McBSP - * driver. - */ - int clk_input_pin; - - /* * This flag works when both clock and FS are outputs for the cpu * and makes clock more accurate (FS is not symmetrical and the * clock is very fast. @@ -91,11 +81,6 @@ enum { MCASP_VERSION_OMAP, /* OMAP4/5 */ }; -enum mcbsp_clk_input_pin { - MCBSP_CLKR = 0, /* as in DM365 */ - MCBSP_CLKS, -}; - #define INACTIVE_MODE 0 #define TX_MODE 1 #define RX_MODE 2 diff --git a/include/linux/platform_data/spi-omap2-mcspi.h b/include/linux/platform_data/spi-omap2-mcspi.h index 3b400b1919a9..9e3c15b4ac91 100644 --- a/include/linux/platform_data/spi-omap2-mcspi.h +++ b/include/linux/platform_data/spi-omap2-mcspi.h @@ -16,9 +16,6 @@ struct omap2_mcspi_platform_config { struct omap2_mcspi_device_config { unsigned turbo_mode:1; - - /* toggle chip select after every word */ - unsigned cs_per_word:1; }; #endif diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index eb556f988d57..d8f15770a522 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -71,7 +71,6 @@ struct sysc_regbits { #define SYSC_QUIRK_SWSUP_SIDLE_ACT BIT(12) #define SYSC_QUIRK_SWSUP_SIDLE BIT(11) #define SYSC_QUIRK_EXT_OPT_CLOCK BIT(10) -#define SYSC_QUIRK_LEGACY_IDLE BIT(9) #define SYSC_QUIRK_RESET_STATUS BIT(8) #define SYSC_QUIRK_NO_IDLE BIT(7) #define SYSC_QUIRK_NO_IDLE_ON_INIT BIT(6) diff --git a/include/linux/platform_data/x86/pmc_atom.h b/include/linux/platform_data/x86/pmc_atom.h index b8a701c77fd0..161e4bc1c9ee 100644 --- a/include/linux/platform_data/x86/pmc_atom.h +++ b/include/linux/platform_data/x86/pmc_atom.h @@ -43,6 +43,19 @@ BIT_ORED_DEDICATED_IRQ_GPSC | \ BIT_SHARED_IRQ_GPSS) +/* External clk generator settings */ +#define PMC_CLK_CTL_OFFSET 0x60 +#define PMC_CLK_CTL_SIZE 4 +#define PMC_CLK_NUM 6 +#define PMC_CLK_CTL_GATED_ON_D3 0x0 +#define PMC_CLK_CTL_FORCE_ON 0x1 +#define PMC_CLK_CTL_FORCE_OFF 0x2 +#define PMC_CLK_CTL_RESERVED 0x3 +#define PMC_MASK_CLK_CTL GENMASK(1, 0) +#define PMC_MASK_CLK_FREQ BIT(2) +#define PMC_CLK_FREQ_XTAL (0 << 2) /* 25 MHz */ +#define PMC_CLK_FREQ_PLL (1 << 2) /* 19.2 MHz */ + /* The timers accumulate time spent in sleep state */ #define PMC_S0IR_TMR 0x80 #define PMC_S0I1_TMR 0x84 @@ -104,14 +117,14 @@ #define BIT_SCC_SDIO BIT(9) #define BIT_SCC_SDCARD BIT(10) #define BIT_SCC_MIPI BIT(11) -#define BIT_HDA BIT(12) +#define BIT_HDA BIT(12) /* CHT datasheet: reserved */ #define BIT_LPE BIT(13) #define BIT_OTG BIT(14) -#define BIT_USH BIT(15) -#define BIT_GBE BIT(16) -#define BIT_SATA BIT(17) -#define BIT_USB_EHCI BIT(18) -#define BIT_SEC BIT(19) +#define BIT_USH BIT(15) /* CHT datasheet: reserved */ +#define BIT_GBE BIT(16) /* CHT datasheet: reserved */ +#define BIT_SATA BIT(17) /* CHT datasheet: reserved */ +#define BIT_USB_EHCI BIT(18) /* CHT datasheet: XHCI! */ +#define BIT_SEC BIT(19) /* BYT datasheet: reserved */ #define BIT_PCIE_PORT0 BIT(20) #define BIT_PCIE_PORT1 BIT(21) #define BIT_PCIE_PORT2 BIT(22) diff --git a/include/linux/platform_data/x86/pwm-lpss.h b/include/linux/platform_data/x86/pwm-lpss.h index c852fe24fe2a..752c06b47cc8 100644 --- a/include/linux/platform_data/x86/pwm-lpss.h +++ b/include/linux/platform_data/x86/pwm-lpss.h @@ -27,7 +27,7 @@ struct pwm_lpss_boardinfo { bool other_devices_aml_touches_pwm_regs; }; -struct pwm_lpss_chip *devm_pwm_lpss_probe(struct device *dev, void __iomem *base, - const struct pwm_lpss_boardinfo *info); +struct pwm_chip *devm_pwm_lpss_probe(struct device *dev, void __iomem *base, + const struct pwm_lpss_boardinfo *info); #endif /* __PLATFORM_DATA_X86_PWM_LPSS_H */ diff --git a/include/linux/pm.h b/include/linux/pm.h index a2f3e53a8196..97b0e23363c8 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -662,8 +662,8 @@ struct pm_subsys_data { struct dev_pm_info { pm_message_t power_state; - unsigned int can_wakeup:1; - unsigned int async_suspend:1; + bool can_wakeup:1; + bool async_suspend:1; bool in_dpm_list:1; /* Owned by the PM core */ bool is_prepared:1; /* Owned by the PM core */ bool is_suspended:1; /* Ditto */ @@ -682,10 +682,10 @@ struct dev_pm_info { bool syscore:1; bool no_pm_callbacks:1; /* Owned by the PM core */ bool async_in_progress:1; /* Owned by the PM core */ - unsigned int must_resume:1; /* Owned by the PM core */ - unsigned int may_skip_resume:1; /* Set by subsystems */ + bool must_resume:1; /* Owned by the PM core */ + bool may_skip_resume:1; /* Set by subsystems */ #else - unsigned int should_wakeup:1; + bool should_wakeup:1; #endif #ifdef CONFIG_PM struct hrtimer suspend_timer; @@ -696,17 +696,17 @@ struct dev_pm_info { atomic_t usage_count; atomic_t child_count; unsigned int disable_depth:3; - unsigned int idle_notification:1; - unsigned int request_pending:1; - unsigned int deferred_resume:1; - unsigned int needs_force_resume:1; - unsigned int runtime_auto:1; + bool idle_notification:1; + bool request_pending:1; + bool deferred_resume:1; + bool needs_force_resume:1; + bool runtime_auto:1; bool ignore_children:1; - unsigned int no_callbacks:1; - unsigned int irq_safe:1; - unsigned int use_autosuspend:1; - unsigned int timer_autosuspends:1; - unsigned int memalloc_noio:1; + bool no_callbacks:1; + bool irq_safe:1; + bool use_autosuspend:1; + bool timer_autosuspends:1; + bool memalloc_noio:1; unsigned int links_count; enum rpm_request request; enum rpm_status runtime_status; diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index b97c5e9820f9..772d3280d35f 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -20,6 +20,33 @@ #include <linux/time64.h> /* + * Flags to control the behaviour when attaching a device to its PM domains. + * + * PD_FLAG_NO_DEV_LINK: As the default behaviour creates a device-link + * for every PM domain that gets attached, this + * flag can be used to skip that. + * + * PD_FLAG_DEV_LINK_ON: Add the DL_FLAG_RPM_ACTIVE to power-on the + * supplier and its PM domain when creating the + * device-links. + * + */ +#define PD_FLAG_NO_DEV_LINK BIT(0) +#define PD_FLAG_DEV_LINK_ON BIT(1) + +struct dev_pm_domain_attach_data { + const char * const *pd_names; + const u32 num_pd_names; + const u32 pd_flags; +}; + +struct dev_pm_domain_list { + struct device **pd_devs; + struct device_link **pd_links; + u32 num_pds; +}; + +/* * Flags to control the behaviour of a genpd. * * These flags may be set in the struct generic_pm_domain's flags field by a @@ -322,7 +349,7 @@ static inline void dev_pm_genpd_resume(struct device *dev) {} /* OF PM domain providers */ struct of_device_id; -typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args, +typedef struct generic_pm_domain *(*genpd_xlate_t)(const struct of_phandle_args *args, void *data); struct genpd_onecell_data { @@ -337,11 +364,11 @@ int of_genpd_add_provider_simple(struct device_node *np, int of_genpd_add_provider_onecell(struct device_node *np, struct genpd_onecell_data *data); void of_genpd_del_provider(struct device_node *np); -int of_genpd_add_device(struct of_phandle_args *args, struct device *dev); -int of_genpd_add_subdomain(struct of_phandle_args *parent_spec, - struct of_phandle_args *subdomain_spec); -int of_genpd_remove_subdomain(struct of_phandle_args *parent_spec, - struct of_phandle_args *subdomain_spec); +int of_genpd_add_device(const struct of_phandle_args *args, struct device *dev); +int of_genpd_add_subdomain(const struct of_phandle_args *parent_spec, + const struct of_phandle_args *subdomain_spec); +int of_genpd_remove_subdomain(const struct of_phandle_args *parent_spec, + const struct of_phandle_args *subdomain_spec); struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n); @@ -366,20 +393,20 @@ static inline int of_genpd_add_provider_onecell(struct device_node *np, static inline void of_genpd_del_provider(struct device_node *np) {} -static inline int of_genpd_add_device(struct of_phandle_args *args, +static inline int of_genpd_add_device(const struct of_phandle_args *args, struct device *dev) { return -ENODEV; } -static inline int of_genpd_add_subdomain(struct of_phandle_args *parent_spec, - struct of_phandle_args *subdomain_spec) +static inline int of_genpd_add_subdomain(const struct of_phandle_args *parent_spec, + const struct of_phandle_args *subdomain_spec) { return -ENODEV; } -static inline int of_genpd_remove_subdomain(struct of_phandle_args *parent_spec, - struct of_phandle_args *subdomain_spec) +static inline int of_genpd_remove_subdomain(const struct of_phandle_args *parent_spec, + const struct of_phandle_args *subdomain_spec) { return -ENODEV; } @@ -420,7 +447,11 @@ struct device *dev_pm_domain_attach_by_id(struct device *dev, unsigned int index); struct device *dev_pm_domain_attach_by_name(struct device *dev, const char *name); +int dev_pm_domain_attach_list(struct device *dev, + const struct dev_pm_domain_attach_data *data, + struct dev_pm_domain_list **list); void dev_pm_domain_detach(struct device *dev, bool power_off); +void dev_pm_domain_detach_list(struct dev_pm_domain_list *list); int dev_pm_domain_start(struct device *dev); void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd); int dev_pm_domain_set_performance_state(struct device *dev, unsigned int state); @@ -439,7 +470,14 @@ static inline struct device *dev_pm_domain_attach_by_name(struct device *dev, { return NULL; } +static inline int dev_pm_domain_attach_list(struct device *dev, + const struct dev_pm_domain_attach_data *data, + struct dev_pm_domain_list **list) +{ + return 0; +} static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {} +static inline void dev_pm_domain_detach_list(struct dev_pm_domain_list *list) {} static inline int dev_pm_domain_start(struct device *dev) { return 0; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 76dcb7f37bcd..dd7c8441af42 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -16,6 +16,7 @@ #include <linux/notifier.h> struct clk; +struct cpufreq_frequency_table; struct regulator; struct dev_pm_opp; struct device; @@ -87,12 +88,14 @@ struct dev_pm_opp_config { /** * struct dev_pm_opp_data - The data to use to initialize an OPP. + * @turbo: Flag to indicate whether the OPP is to be marked turbo or not. * @level: The performance level for the OPP. Set level to OPP_LEVEL_UNSET if * level field isn't used. * @freq: The clock rate in Hz for the OPP. * @u_volt: The voltage in uV for the OPP. */ struct dev_pm_opp_data { + bool turbo; unsigned int level; unsigned long freq; unsigned long u_volt; @@ -444,6 +447,21 @@ static inline int dev_pm_opp_sync_regulators(struct device *dev) #endif /* CONFIG_PM_OPP */ +#if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP) +int dev_pm_opp_init_cpufreq_table(struct device *dev, struct cpufreq_frequency_table **table); +void dev_pm_opp_free_cpufreq_table(struct device *dev, struct cpufreq_frequency_table **table); +#else +static inline int dev_pm_opp_init_cpufreq_table(struct device *dev, struct cpufreq_frequency_table **table) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_free_cpufreq_table(struct device *dev, struct cpufreq_frequency_table **table) +{ +} +#endif + + #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) int dev_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_add_table_indexed(struct device *dev, int index); @@ -458,6 +476,8 @@ struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); int of_get_required_opp_performance_state(struct device_node *np, int index); int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table); int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus); +int dev_pm_opp_calc_power(struct device *dev, unsigned long *uW, + unsigned long *kHz); static inline void dev_pm_opp_of_unregister_em(struct device *dev) { em_dev_unregister_perf_domain(dev); @@ -521,6 +541,12 @@ static inline void dev_pm_opp_of_unregister_em(struct device *dev) { } +static inline int dev_pm_opp_calc_power(struct device *dev, unsigned long *uW, + unsigned long *kHz) +{ + return -EOPNOTSUPP; +} + static inline int of_get_required_opp_performance_state(struct device_node *np, int index) { return -EOPNOTSUPP; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 7c9b35448563..d39dc863f612 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -72,7 +72,8 @@ extern int pm_runtime_force_resume(struct device *dev); extern int __pm_runtime_idle(struct device *dev, int rpmflags); extern int __pm_runtime_suspend(struct device *dev, int rpmflags); extern int __pm_runtime_resume(struct device *dev, int rpmflags); -extern int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count); +extern int pm_runtime_get_if_active(struct device *dev); +extern int pm_runtime_get_if_in_use(struct device *dev); extern int pm_schedule_suspend(struct device *dev, unsigned int delay); extern int __pm_runtime_set_status(struct device *dev, unsigned int status); extern int pm_runtime_barrier(struct device *dev); @@ -95,18 +96,6 @@ extern void pm_runtime_release_supplier(struct device_link *link); extern int devm_pm_runtime_enable(struct device *dev); /** - * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. - * @dev: Target device. - * - * Increment the runtime PM usage counter of @dev if its runtime PM status is - * %RPM_ACTIVE and its runtime PM usage counter is greater than 0. - */ -static inline int pm_runtime_get_if_in_use(struct device *dev) -{ - return pm_runtime_get_if_active(dev, false); -} - -/** * pm_suspend_ignore_children - Set runtime PM behavior regarding children. * @dev: Target device. * @enable: Whether or not to ignore possible dependencies on children. @@ -275,8 +264,7 @@ static inline int pm_runtime_get_if_in_use(struct device *dev) { return -EINVAL; } -static inline int pm_runtime_get_if_active(struct device *dev, - bool ign_usage_count) +static inline int pm_runtime_get_if_active(struct device *dev) { return -EINVAL; } @@ -461,6 +449,18 @@ static inline int pm_runtime_put(struct device *dev) } /** + * __pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. + * @dev: Target device. + * + * Decrement the runtime PM usage counter of @dev and if it turns out to be + * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). + */ +static inline int __pm_runtime_put_autosuspend(struct device *dev) +{ + return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); +} + +/** * pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 6eb9adaef52b..76cd1f9f1365 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -107,7 +107,7 @@ extern void wakeup_sources_read_unlock(int idx); extern struct wakeup_source *wakeup_sources_walk_start(void); extern struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws); extern int device_wakeup_enable(struct device *dev); -extern int device_wakeup_disable(struct device *dev); +extern void device_wakeup_disable(struct device *dev); extern void device_set_wakeup_capable(struct device *dev, bool capable); extern int device_set_wakeup_enable(struct device *dev, bool enable); extern void __pm_stay_awake(struct wakeup_source *ws); @@ -154,10 +154,9 @@ static inline int device_wakeup_enable(struct device *dev) return 0; } -static inline int device_wakeup_disable(struct device *dev) +static inline void device_wakeup_disable(struct device *dev) { dev->power.should_wakeup = false; - return 0; } static inline int device_set_wakeup_enable(struct device *dev, bool enable) @@ -235,11 +234,10 @@ static inline int device_init_wakeup(struct device *dev, bool enable) if (enable) { device_set_wakeup_capable(dev, true); return device_wakeup_enable(dev); - } else { - device_wakeup_disable(dev); - device_set_wakeup_capable(dev, false); - return 0; } + device_wakeup_disable(dev); + device_set_wakeup_capable(dev, false); + return 0; } #endif /* _LINUX_PM_WAKEUP_H */ diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 7d8025fb74b7..b9e5bd2b42d3 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -61,7 +61,6 @@ struct bq27xxx_reg_cache { struct bq27xxx_device_info { struct device *dev; - int id; enum bq27xxx_chip chip; u32 opts; const char *name; diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index c0992a77feea..8e5705a56b85 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -242,6 +242,7 @@ struct power_supply_config { struct power_supply_desc { const char *name; enum power_supply_type type; + u8 charge_behaviours; const enum power_supply_usb_type *usb_types; size_t num_usb_types; const enum power_supply_property *properties; @@ -894,8 +895,7 @@ extern int power_supply_powers(struct power_supply *psy, struct device *dev); #define to_power_supply(device) container_of(device, struct power_supply, dev) extern void *power_supply_get_drvdata(struct power_supply *psy); -/* For APM emulation, think legacy userspace. */ -extern struct class *power_supply_class; +extern int power_supply_for_each_device(void *data, int (*fn)(struct device *dev, void *data)); static inline bool power_supply_is_amp_property(enum power_supply_property psp) { diff --git a/include/linux/profile.h b/include/linux/profile.h index 11db1ec516e2..04ae5ebcb637 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -18,13 +18,8 @@ struct proc_dir_entry; struct notifier_block; #if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS) -void create_prof_cpu_mask(void); int create_proc_profile(void); #else -static inline void create_prof_cpu_mask(void) -{ -} - static inline int create_proc_profile(void) { return 0; diff --git a/include/linux/property.h b/include/linux/property.h index e6516d0b7d52..3a1045eb786c 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -11,6 +11,7 @@ #define _LINUX_PROPERTY_H_ #include <linux/args.h> +#include <linux/array_size.h> #include <linux/bits.h> #include <linux/fwnode.h> #include <linux/stddef.h> @@ -27,12 +28,6 @@ enum dev_prop_type { DEV_PROP_REF, }; -enum dev_dma_attr { - DEV_DMA_NOT_SUPPORTED, - DEV_DMA_NON_COHERENT, - DEV_DMA_COHERENT, -}; - const struct fwnode_handle *__dev_fwnode_const(const struct device *dev); struct fwnode_handle *__dev_fwnode(struct device *dev); #define dev_fwnode(dev) \ @@ -156,11 +151,9 @@ 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(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(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( diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index fb724c65c77b..6d07c95dabb9 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -15,11 +15,14 @@ struct pse_controller_dev; /** * struct pse_control_config - PSE control/channel configuration. * - * @admin_cotrol: set PoDL PSE admin control as described in + * @podl_admin_control: set PoDL PSE admin control as described in * IEEE 802.3-2018 30.15.1.2.1 acPoDLPSEAdminControl + * @c33_admin_control: set PSE admin control as described in + * IEEE 802.3-2022 30.9.1.2.1 acPSEAdminControl */ struct pse_control_config { - enum ethtool_podl_pse_admin_state admin_cotrol; + enum ethtool_podl_pse_admin_state podl_admin_control; + enum ethtool_c33_pse_admin_state c33_admin_control; }; /** @@ -29,25 +32,36 @@ struct pse_control_config { * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState * @podl_pw_status: power detection status of the PoDL PSE. * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: + * @c33_admin_state: operational state of the PSE + * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState + * @c33_pw_status: power detection status of the PSE. + * IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus: */ struct pse_control_status { enum ethtool_podl_pse_admin_state podl_admin_state; enum ethtool_podl_pse_pw_d_status podl_pw_status; + enum ethtool_c33_pse_admin_state c33_admin_state; + enum ethtool_c33_pse_pw_d_status c33_pw_status; }; /** * struct pse_controller_ops - PSE controller driver callbacks * * @ethtool_get_status: get PSE control status for ethtool interface - * @ethtool_set_config: set PSE control configuration over ethtool interface + * @setup_pi_matrix: setup PI matrix of the PSE controller + * @pi_is_enabled: Return 1 if the PSE PI is enabled, 0 if not. + * May also return negative errno. + * @pi_enable: Configure the PSE PI as enabled. + * @pi_disable: Configure the PSE PI as disabled. */ struct pse_controller_ops { int (*ethtool_get_status)(struct pse_controller_dev *pcdev, unsigned long id, struct netlink_ext_ack *extack, struct pse_control_status *status); - int (*ethtool_set_config)(struct pse_controller_dev *pcdev, - unsigned long id, struct netlink_ext_ack *extack, - const struct pse_control_config *config); + int (*setup_pi_matrix)(struct pse_controller_dev *pcdev); + int (*pi_is_enabled)(struct pse_controller_dev *pcdev, int id); + int (*pi_enable)(struct pse_controller_dev *pcdev, int id); + int (*pi_disable)(struct pse_controller_dev *pcdev, int id); }; struct module; @@ -55,6 +69,40 @@ struct device_node; struct of_phandle_args; struct pse_control; +/* PSE PI pairset pinout can either be Alternative A or Alternative B */ +enum pse_pi_pairset_pinout { + ALTERNATIVE_A, + ALTERNATIVE_B, +}; + +/** + * struct pse_pi_pairset - PSE PI pairset entity describing the pinout + * alternative ant its phandle + * + * @pinout: description of the pinout alternative + * @np: device node pointer describing the pairset phandle + */ +struct pse_pi_pairset { + enum pse_pi_pairset_pinout pinout; + struct device_node *np; +}; + +/** + * struct pse_pi - PSE PI (Power Interface) entity as described in + * IEEE 802.3-2022 145.2.4 + * + * @pairset: table of the PSE PI pinout alternative for the two pairset + * @np: device node pointer of the PSE PI node + * @rdev: regulator represented by the PSE PI + * @admin_state_enabled: PI enabled state + */ +struct pse_pi { + struct pse_pi_pairset pairset[2]; + struct device_node *np; + struct regulator_dev *rdev; + bool admin_state_enabled; +}; + /** * struct pse_controller_dev - PSE controller entity that might * provide multiple PSE controls @@ -64,10 +112,11 @@ struct pse_control; * @pse_control_head: head of internal list of requested PSE controls * @dev: corresponding driver model device struct * @of_pse_n_cells: number of cells in PSE line specifiers - * @of_xlate: translation function to translate from specifier as found in the - * device tree to id as given to the PSE control ops * @nr_lines: number of PSE controls in this controller device * @lock: Mutex for serialization access to the PSE controller + * @types: types of the PSE controller + * @pi: table of PSE PIs described in this controller device + * @no_of_pse_pi: flag set if the pse_pis devicetree node is not used */ struct pse_controller_dev { const struct pse_controller_ops *ops; @@ -76,10 +125,11 @@ struct pse_controller_dev { struct list_head pse_control_head; struct device *dev; int of_pse_n_cells; - int (*of_xlate)(struct pse_controller_dev *pcdev, - const struct of_phandle_args *pse_spec); unsigned int nr_lines; struct mutex lock; + enum ethtool_pse_types types; + struct pse_pi *pi; + bool no_of_pse_pi; }; #if IS_ENABLED(CONFIG_PSE_CONTROLLER) @@ -99,6 +149,9 @@ int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config); +bool pse_has_podl(struct pse_control *psec); +bool pse_has_c33(struct pse_control *psec); + #else static inline struct pse_control *of_pse_control_get(struct device_node *node) @@ -124,6 +177,16 @@ static inline int pse_ethtool_set_config(struct pse_control *psec, return -ENOTSUPP; } +static inline bool pse_has_podl(struct pse_control *psec) +{ + return false; +} + +static inline bool pse_has_c33(struct pse_control *psec) +{ + return false; +} + #endif #endif diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h index 2a3a95586425..8dbd51ea8626 100644 --- a/include/linux/ptdump.h +++ b/include/linux/ptdump.h @@ -18,6 +18,16 @@ struct ptdump_state { const struct ptdump_range *range; }; +bool ptdump_walk_pgd_level_core(struct seq_file *m, + struct mm_struct *mm, pgd_t *pgd, + bool checkwx, bool dmesg); void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd); +bool ptdump_check_wx(void); + +static inline void debug_checkwx(void) +{ + if (IS_ENABLED(CONFIG_DEBUG_WX)) + ptdump_check_wx(); +} #endif /* _LINUX_PTDUMP_H */ diff --git a/include/linux/pwm.h b/include/linux/pwm.h index fcc2c4496f73..60b92c2c75ef 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -2,6 +2,7 @@ #ifndef __LINUX_PWM_H #define __LINUX_PWM_H +#include <linux/device.h> #include <linux/err.h> #include <linux/mutex.h> #include <linux/of.h> @@ -271,12 +272,12 @@ struct pwm_ops { * @id: unique number of this PWM chip * @npwm: number of PWMs controlled by this chip * @of_xlate: request a PWM device given a device tree PWM specifier - * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier * @atomic: can the driver's ->apply() be called in atomic context + * @uses_pwmchip_alloc: signals if pwmchip_allow was used to allocate this chip * @pwms: array of PWM devices allocated by the framework */ struct pwm_chip { - struct device *dev; + struct device dev; const struct pwm_ops *ops; struct module *owner; unsigned int id; @@ -284,13 +285,28 @@ struct pwm_chip { struct pwm_device * (*of_xlate)(struct pwm_chip *chip, const struct of_phandle_args *args); - unsigned int of_pwm_n_cells; bool atomic; /* only used internally by the PWM framework */ - struct pwm_device *pwms; + bool uses_pwmchip_alloc; + struct pwm_device pwms[] __counted_by(npwm); }; +static inline struct device *pwmchip_parent(const struct pwm_chip *chip) +{ + return chip->dev.parent; +} + +static inline void *pwmchip_get_drvdata(struct pwm_chip *chip) +{ + return dev_get_drvdata(&chip->dev); +} + +static inline void pwmchip_set_drvdata(struct pwm_chip *chip, void *data) +{ + dev_set_drvdata(&chip->dev, data); +} + #if IS_ENABLED(CONFIG_PWM) /* PWM user APIs */ int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state); @@ -380,6 +396,10 @@ static inline bool pwm_might_sleep(struct pwm_device *pwm) int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, unsigned long timeout); +void pwmchip_put(struct pwm_chip *chip); +struct pwm_chip *pwmchip_alloc(struct device *parent, unsigned int npwm, size_t sizeof_priv); +struct pwm_chip *devm_pwmchip_alloc(struct device *parent, unsigned int npwm, size_t sizeof_priv); + int __pwmchip_add(struct pwm_chip *chip, struct module *owner); #define pwmchip_add(chip) __pwmchip_add(chip, THIS_MODULE) void pwmchip_remove(struct pwm_chip *chip); @@ -452,6 +472,24 @@ static inline int pwm_capture(struct pwm_device *pwm, return -EINVAL; } +static inline void pwmchip_put(struct pwm_chip *chip) +{ +} + +static inline struct pwm_chip *pwmchip_alloc(struct device *parent, + unsigned int npwm, + size_t sizeof_priv) +{ + return ERR_PTR(-EINVAL); +} + +static inline struct pwm_chip *devm_pwmchip_alloc(struct device *parent, + unsigned int npwm, + size_t sizeof_priv) +{ + return pwmchip_alloc(parent, npwm, sizeof_priv); +} + static inline int pwmchip_add(struct pwm_chip *chip) { return -EINVAL; @@ -583,17 +621,4 @@ static inline void pwm_remove_table(struct pwm_lookup *table, size_t num) } #endif -#ifdef CONFIG_PWM_SYSFS -void pwmchip_sysfs_export(struct pwm_chip *chip); -void pwmchip_sysfs_unexport(struct pwm_chip *chip); -#else -static inline void pwmchip_sysfs_export(struct pwm_chip *chip) -{ -} - -static inline void pwmchip_sysfs_unexport(struct pwm_chip *chip) -{ -} -#endif /* CONFIG_PWM_SYSFS */ - #endif /* __LINUX_PWM_H */ diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index cd1973e6ac4b..844a2743ca94 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -217,9 +217,9 @@ enum pxa_ssp_type { PXA27x_SSP, PXA3xx_SSP, PXA168_SSP, - MMP2_SSP, PXA910_SSP, CE4100_SSP, + MMP2_SSP, MRFLD_SSP, QUARK_X1000_SSP, /* Keep LPSS types sorted with lpss_platforms[] */ diff --git a/include/linux/qat/qat_mig_dev.h b/include/linux/qat/qat_mig_dev.h new file mode 100644 index 000000000000..dbbb6a063dd2 --- /dev/null +++ b/include/linux/qat/qat_mig_dev.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2024 Intel Corporation */ +#ifndef QAT_MIG_DEV_H_ +#define QAT_MIG_DEV_H_ + +struct pci_dev; + +struct qat_mig_dev { + void *parent_accel_dev; + u8 *state; + u32 setup_size; + u32 remote_setup_size; + u32 state_size; + s32 vf_id; +}; + +struct qat_mig_dev *qat_vfmig_create(struct pci_dev *pdev, int vf_id); +int qat_vfmig_init(struct qat_mig_dev *mdev); +void qat_vfmig_cleanup(struct qat_mig_dev *mdev); +void qat_vfmig_reset(struct qat_mig_dev *mdev); +int qat_vfmig_open(struct qat_mig_dev *mdev); +void qat_vfmig_close(struct qat_mig_dev *mdev); +int qat_vfmig_suspend(struct qat_mig_dev *mdev); +int qat_vfmig_resume(struct qat_mig_dev *mdev); +int qat_vfmig_save_state(struct qat_mig_dev *mdev); +int qat_vfmig_save_setup(struct qat_mig_dev *mdev); +int qat_vfmig_load_state(struct qat_mig_dev *mdev); +int qat_vfmig_load_setup(struct qat_mig_dev *mdev, int size); +void qat_vfmig_destroy(struct qat_mig_dev *mdev); + +#endif /*QAT_MIG_DEV_H_*/ diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 5d868505a94e..6d92b68efbf6 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -80,7 +80,7 @@ DECLARE_PER_CPU(u32, kstack_offset); if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ u32 offset = raw_cpu_read(kstack_offset); \ - offset ^= (rand); \ + offset = ror32(offset, 5) ^ (rand); \ raw_cpu_write(kstack_offset, offset); \ } \ } while (0) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 16f519914415..dfd2399f2cde 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -247,6 +247,37 @@ do { \ cond_resched(); \ } while (0) +/** + * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states + * @old_ts: jiffies at start of processing. + * + * This helper is for long-running softirq handlers, such as NAPI threads in + * networking. The caller should initialize the variable passed in as @old_ts + * at the beginning of the softirq handler. When invoked frequently, this macro + * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will + * provide both RCU and RCU-Tasks quiescent states. Note that this macro + * modifies its old_ts argument. + * + * Because regions of code that have disabled softirq act as RCU read-side + * critical sections, this macro should be invoked with softirq (and + * preemption) enabled. + * + * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would + * have more chance to invoke schedule() calls and provide necessary quiescent + * states. As a contrast, calling cond_resched() only won't achieve the same + * effect because cond_resched() does not provide RCU-Tasks quiescent states. + */ +#define rcu_softirq_qs_periodic(old_ts) \ +do { \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ + time_after(jiffies, (old_ts) + HZ / 10)) { \ + preempt_disable(); \ + rcu_softirq_qs(); \ + preempt_enable(); \ + (old_ts) = jiffies; \ + } \ +} while (0) + /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. @@ -370,15 +401,15 @@ static inline int debug_lockdep_rcu_enabled(void) } \ } while (0) -#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) +#ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } -#else /* #ifdef CONFIG_PROVE_RCU */ +#else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } -#endif /* #else #ifdef CONFIG_PROVE_RCU */ +#endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ @@ -778,9 +809,9 @@ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); + rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release(RCU); __rcu_read_unlock(); - rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ } /** @@ -1059,6 +1090,18 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) extern int rcu_expedited; extern int rcu_normal; -DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock()) +DEFINE_LOCK_GUARD_0(rcu, + do { + rcu_read_lock(); + /* + * sparse doesn't call the cleanup function, + * so just release immediately and don't track + * the context. We don't need to anyway, since + * the whole point of the guard is to not need + * the explicit unlock. + */ + __release(RCU); + } while (0), + rcu_read_unlock()) #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index d07f0848802e..303ab9bee155 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -19,18 +19,18 @@ struct rcu_synchronize { }; void wakeme_after_rcu(struct rcu_head *head); -void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, +void __wait_rcu_gp(bool checktiny, unsigned int state, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array); -#define _wait_rcu_gp(checktiny, ...) \ -do { \ - call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ - struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ - __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \ - __crcu_array, __rs_array); \ +#define _wait_rcu_gp(checktiny, state, ...) \ +do { \ + call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ + struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ + __wait_rcu_gp(checktiny, state, ARRAY_SIZE(__crcu_array), __crcu_array, __rs_array); \ } while (0) -#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) +#define wait_rcu_gp(...) _wait_rcu_gp(false, TASK_UNINTERRUPTIBLE, __VA_ARGS__) +#define wait_rcu_gp_state(state, ...) _wait_rcu_gp(false, state, __VA_ARGS__) /** * synchronize_rcu_mult - Wait concurrently for multiple grace periods @@ -54,7 +54,7 @@ do { \ * grace period. */ #define synchronize_rcu_mult(...) \ - _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) + _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), TASK_UNINTERRUPTIBLE, __VA_ARGS__) static inline void cond_resched_rcu(void) { diff --git a/include/linux/regmap.h b/include/linux/regmap.h index c9182a47736e..a6bc2980a98b 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -297,15 +297,6 @@ typedef void (*regmap_unlock)(void *); * performed on such table (a register is no increment * readable if it belongs to one of the ranges specified * by rd_noinc_table). - * @disable_locking: This regmap is either protected by external means or - * is guaranteed not to be accessed from multiple threads. - * Don't use any locking mechanisms. - * @lock: Optional lock callback (overrides regmap's default lock - * function, based on spinlock or mutex). - * @unlock: As above for unlocking. - * @lock_arg: this field is passed as the only argument of lock/unlock - * functions (ignored in case regular lock/unlock functions - * are not overridden). * @reg_read: Optional callback that if filled will be used to perform * all the reads from the registers. Should only be provided for * devices whose read operation cannot be represented as a simple @@ -323,6 +314,7 @@ typedef void (*regmap_unlock)(void *); * @write: Same as above for writing. * @max_raw_read: Max raw read size that can be used on the device. * @max_raw_write: Max raw write size that can be used on the device. + * @can_sleep: Optional, specifies whether regmap operations can sleep. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). @@ -331,7 +323,20 @@ typedef void (*regmap_unlock)(void *); * Use it only for "no-bus" cases. * @io_port: Support IO port accessors. Makes sense only when MMIO vs. IO port * access can be distinguished. + * @disable_locking: This regmap is either protected by external means or + * is guaranteed not to be accessed from multiple threads. + * Don't use any locking mechanisms. + * @lock: Optional lock callback (overrides regmap's default lock + * function, based on spinlock or mutex). + * @unlock: As above for unlocking. + * @lock_arg: This field is passed as the only argument of lock/unlock + * functions (ignored in case regular lock/unlock functions + * are not overridden). * @max_register: Optional, specifies the maximum valid register address. + * @max_register_is_0: Optional, specifies that zero value in @max_register + * should be taken into account. This is a workaround to + * apply handling of @max_register for regmap that contains + * only one register. * @wr_table: Optional, points to a struct regmap_access_table specifying * valid ranges for write access. * @rd_table: As above, for read access. @@ -369,21 +374,20 @@ typedef void (*regmap_unlock)(void *); * @reg_defaults_raw: Power on reset values for registers (for use with * register cache support). * @num_reg_defaults_raw: Number of elements in reg_defaults_raw. - * @reg_format_endian: Endianness for formatted register addresses. If this is - * DEFAULT, the @reg_format_endian_default value from the - * regmap bus is used. - * @val_format_endian: Endianness for formatted register values. If this is - * DEFAULT, the @reg_format_endian_default value from the - * regmap bus is used. - * - * @ranges: Array of configuration entries for virtual address ranges. - * @num_ranges: Number of range configuration entries. * @use_hwlock: Indicate if a hardware spinlock should be used. * @use_raw_spinlock: Indicate if a raw spinlock should be used. * @hwlock_id: Specify the hardware spinlock id. * @hwlock_mode: The hardware spinlock mode, should be HWLOCK_IRQSTATE, * HWLOCK_IRQ or 0. - * @can_sleep: Optional, specifies whether regmap operations can sleep. + * @reg_format_endian: Endianness for formatted register addresses. If this is + * DEFAULT, the @reg_format_endian_default value from the + * regmap bus is used. + * @val_format_endian: Endianness for formatted register values. If this is + * DEFAULT, the @reg_format_endian_default value from the + * regmap bus is used. + * + * @ranges: Array of configuration entries for virtual address ranges. + * @num_ranges: Number of range configuration entries. */ struct regmap_config { const char *name; @@ -402,11 +406,6 @@ struct regmap_config { bool (*writeable_noinc_reg)(struct device *dev, unsigned int reg); bool (*readable_noinc_reg)(struct device *dev, unsigned int reg); - bool disable_locking; - regmap_lock lock; - regmap_unlock unlock; - void *lock_arg; - int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); int (*reg_update_bits)(void *context, unsigned int reg, @@ -418,10 +417,18 @@ struct regmap_config { size_t max_raw_read; size_t max_raw_write; + bool can_sleep; + bool fast_io; bool io_port; + bool disable_locking; + regmap_lock lock; + regmap_unlock unlock; + void *lock_arg; + unsigned int max_register; + bool max_register_is_0; const struct regmap_access_table *wr_table; const struct regmap_access_table *rd_table; const struct regmap_access_table *volatile_table; @@ -443,18 +450,16 @@ struct regmap_config { bool use_relaxed_mmio; bool can_multi_write; - enum regmap_endian reg_format_endian; - enum regmap_endian val_format_endian; - - const struct regmap_range_cfg *ranges; - unsigned int num_ranges; - bool use_hwlock; bool use_raw_spinlock; unsigned int hwlock_id; unsigned int hwlock_mode; - bool can_sleep; + enum regmap_endian reg_format_endian; + enum regmap_endian val_format_endian; + + const struct regmap_range_cfg *ranges; + unsigned int num_ranges; }; /** @@ -1225,6 +1230,7 @@ int regmap_multi_reg_write_bypassed(struct regmap *map, int regmap_raw_write_async(struct regmap *map, unsigned int reg, const void *val, size_t val_len); int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val); +int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val); int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); int regmap_noinc_read(struct regmap *map, unsigned int reg, @@ -1734,6 +1740,13 @@ static inline int regmap_read(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_read_bypassed(struct regmap *map, unsigned int reg, + unsigned int *val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len) { diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 4660582a3302..59d0b9a79e6e 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -164,6 +164,7 @@ struct regulator *__must_check devm_regulator_get_optional(struct device *dev, const char *id); int devm_regulator_get_enable(struct device *dev, const char *id); int devm_regulator_get_enable_optional(struct device *dev, const char *id); +int devm_regulator_get_enable_read_voltage(struct device *dev, const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); @@ -320,12 +321,18 @@ devm_regulator_get_exclusive(struct device *dev, const char *id) static inline int devm_regulator_get_enable(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline int devm_regulator_get_enable_optional(struct device *dev, const char *id) { + return 0; +} + +static inline int devm_regulator_get_enable_read_voltage(struct device *dev, + const char *id) +{ return -ENODEV; } diff --git a/include/linux/regulator/max8973-regulator.h b/include/linux/regulator/max8973-regulator.h index 8313e7ed6aec..a225e9eeb30d 100644 --- a/include/linux/regulator/max8973-regulator.h +++ b/include/linux/regulator/max8973-regulator.h @@ -48,10 +48,6 @@ * control signal from EN input pin. If it is false then * voltage output will be enabled/disabled through EN bit of * device register. - * @enable_gpio: Enable GPIO. If EN pin is controlled through GPIO from host - * then GPIO number can be provided. If no GPIO controlled then - * it should be -1. - * @dvs_gpio: GPIO for dvs. It should be -1 if this is tied with fixed logic. * @dvs_def_state: Default state of dvs. 1 if it is high else 0. */ struct max8973_regulator_platform_data { @@ -59,8 +55,6 @@ struct max8973_regulator_platform_data { unsigned long control_flags; unsigned long junction_temp_warning; bool enable_ext_control; - int enable_gpio; - int dvs_gpio; unsigned dvs_def_state:1; }; diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 505c908dbb81..243633c8dceb 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -9,6 +9,7 @@ enum pca9450_chip_type { PCA9450_TYPE_PCA9450A = 0, PCA9450_TYPE_PCA9450BC, + PCA9450_TYPE_PCA9451A, PCA9450_TYPE_AMOUNT, }; diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h index 0fa4f60e1186..357df16ede32 100644 --- a/include/linux/reset-controller.h +++ b/include/linux/reset-controller.h @@ -60,6 +60,9 @@ struct reset_control_lookup { * @reset_control_head: head of internal list of requested reset controls * @dev: corresponding driver model device struct * @of_node: corresponding device tree node as phandle target + * @of_args: for reset-gpios controllers: corresponding phandle args with + * of_node and GPIO number complementing of_node; either this or + * of_node should be present * @of_reset_n_cells: number of cells in reset line specifiers * @of_xlate: translation function to translate from specifier as found in the * device tree to id as given to the reset control ops, defaults @@ -73,6 +76,7 @@ struct reset_controller_dev { struct list_head reset_control_head; struct device *dev; struct device_node *of_node; + const struct of_phandle_args *of_args; int of_reset_n_cells; int (*of_xlate)(struct reset_controller_dev *rcdev, const struct of_phandle_args *reset_spec); diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 5b5357c0bd8c..8463a128e2f4 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -633,7 +633,7 @@ restart: * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. + * for an entry with an identical key. The first matching entry is returned. * * This must only be called under the RCU read lock. * @@ -655,7 +655,7 @@ static inline void *rhashtable_lookup( * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. + * for an entry with an identical key. The first matching entry is returned. * * Only use this function when you have other mechanisms guaranteeing * that the object won't go away after the RCU read lock is released. @@ -682,7 +682,7 @@ static inline void *rhashtable_lookup_fast( * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. All matching entries are returned + * for an entry with an identical key. All matching entries are returned * in a list. * * This must only be called under the RCU read lock. @@ -699,7 +699,7 @@ static inline struct rhlist_head *rhltable_lookup( } /* Internal function, please use rhashtable_insert_fast() instead. This - * function returns the existing element already in hashes in there is a clash, + * function returns the existing element already in hashes if there is a clash, * otherwise it returns an error via ERR_PTR(). */ static inline void *__rhashtable_insert_fast( @@ -1130,7 +1130,7 @@ static inline int rhashtable_remove_fast( * * Since the hash chain is single linked, the removal operation needs to * walk the bucket chain upon removal. The removal operation is thus - * considerable slow if the hash table is not correctly sized. + * considerably slower if the hash table is not correctly sized. * * Will automatically shrink the table if permitted when residency drops * below 30% diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index fa802db216f9..dc5ae4e96aee 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -98,7 +98,9 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) -int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); +typedef bool (*ring_buffer_cond_fn)(void *data); +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, + ring_buffer_cond_fn cond, void *data); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full); void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 5f8e438a0312..3f4d315aaec9 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -42,7 +42,7 @@ static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) #include <linux/timerqueue.h> #include <linux/workqueue.h> -extern struct class *rtc_class; +extern const struct class rtc_class; /* * For these RTC methods the device parameter is the physical device diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index cdfc897f1e3c..a7da7dfc06a2 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -7,6 +7,7 @@ #include <linux/netdevice.h> #include <linux/wait.h> #include <linux/refcount.h> +#include <linux/cleanup.h> #include <uapi/linux/rtnetlink.h> extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -46,6 +47,8 @@ extern int rtnl_is_locked(void); extern int rtnl_lock_killable(void); extern bool refcount_dec_and_rtnl_lock(refcount_t *r); +DEFINE_LOCK_GUARD_0(rtnl, rtnl_lock(), rtnl_unlock()) + extern wait_queue_head_t netdev_unregistering_wq; extern atomic_t dev_unreg_count; extern struct rw_semaphore pernet_ops_rwsem; diff --git a/include/linux/rwbase_rt.h b/include/linux/rwbase_rt.h index 1d264dd08625..f2394a409c9d 100644 --- a/include/linux/rwbase_rt.h +++ b/include/linux/rwbase_rt.h @@ -26,12 +26,17 @@ struct rwbase_rt { } while (0) -static __always_inline bool rw_base_is_locked(struct rwbase_rt *rwb) +static __always_inline bool rw_base_is_locked(const struct rwbase_rt *rwb) { return atomic_read(&rwb->readers) != READER_BIAS; } -static __always_inline bool rw_base_is_contended(struct rwbase_rt *rwb) +static __always_inline bool rw_base_is_write_locked(const struct rwbase_rt *rwb) +{ + return atomic_read(&rwb->readers) == WRITER_BIAS; +} + +static __always_inline bool rw_base_is_contended(const struct rwbase_rt *rwb) { return atomic_read(&rwb->readers) > 0; } diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 9c29689ff505..c8b543d428b0 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -66,14 +66,24 @@ struct rw_semaphore { #endif }; -/* In all implementations count != 0 means locked */ +#define RWSEM_UNLOCKED_VALUE 0UL +#define RWSEM_WRITER_LOCKED (1UL << 0) +#define __RWSEM_COUNT_INIT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) + static inline int rwsem_is_locked(struct rw_semaphore *sem) { - return atomic_long_read(&sem->count) != 0; + return atomic_long_read(&sem->count) != RWSEM_UNLOCKED_VALUE; } -#define RWSEM_UNLOCKED_VALUE 0L -#define __RWSEM_COUNT_INIT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) +static inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) +{ + WARN_ON(atomic_long_read(&sem->count) == RWSEM_UNLOCKED_VALUE); +} + +static inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) +{ + WARN_ON(!(atomic_long_read(&sem->count) & RWSEM_WRITER_LOCKED)); +} /* Common initializer macros and functions */ @@ -152,11 +162,21 @@ do { \ __init_rwsem((sem), #sem, &__key); \ } while (0) -static __always_inline int rwsem_is_locked(struct rw_semaphore *sem) +static __always_inline int rwsem_is_locked(const struct rw_semaphore *sem) { return rw_base_is_locked(&sem->rwbase); } +static __always_inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) +{ + WARN_ON(!rwsem_is_locked(sem)); +} + +static __always_inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) +{ + WARN_ON(!rw_base_is_write_locked(&sem->rwbase)); +} + static __always_inline int rwsem_is_contended(struct rw_semaphore *sem) { return rw_base_is_contended(&sem->rwbase); @@ -169,6 +189,22 @@ static __always_inline int rwsem_is_contended(struct rw_semaphore *sem) * the RT specific variant. */ +static inline void rwsem_assert_held(const struct rw_semaphore *sem) +{ + if (IS_ENABLED(CONFIG_LOCKDEP)) + lockdep_assert_held(sem); + else + rwsem_assert_held_nolockdep(sem); +} + +static inline void rwsem_assert_held_write(const struct rw_semaphore *sem) +{ + if (IS_ENABLED(CONFIG_LOCKDEP)) + lockdep_assert_held_write(sem); + else + rwsem_assert_held_write_nolockdep(sem); +} + /* * lock for reading */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 17cb0761ff65..c75fd46506df 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -301,7 +301,7 @@ enum { TASK_COMM_LEN = 16, }; -extern void scheduler_tick(void); +extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX @@ -835,6 +835,7 @@ struct task_struct { #endif unsigned int policy; + unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; @@ -1261,6 +1262,7 @@ struct task_struct { /* Protected by alloc_lock: */ struct mempolicy *mempolicy; short il_prev; + u8 il_weight; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING @@ -1625,25 +1627,26 @@ extern struct pid *cad_pid; #define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* Dumped core */ #define PF_SIGNALED 0x00000400 /* Killed by a signal */ -#define PF_MEMALLOC 0x00000800 /* Allocating memory */ +#define PF_MEMALLOC 0x00000800 /* Allocating memory to free memory. See memalloc_noreclaim_save() */ #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_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 */ -#define PF_MEMALLOC_NOFS 0x00040000 /* All allocation requests will inherit GFP_NOFS */ -#define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */ +#define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ +#define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ #define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ -#define PF__HOLE__00800000 0x00800000 -#define PF__HOLE__01000000 0x01000000 +#define PF_MEMALLOC_NORECLAIM 0x00800000 /* All allocation requests will clear __GFP_DIRECT_RECLAIM */ +#define PF_MEMALLOC_NOWARN 0x01000000 /* All allocation requests will inherit __GFP_NOWARN */ #define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ -#define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ +#define PF_MEMALLOC_PIN 0x10000000 /* Allocations constrained to zones which allow long term pinning. + * See memalloc_pin_save() */ #define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */ #define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h index 478084f9105e..e670ac282333 100644 --- a/include/linux/sched/idle.h +++ b/include/linux/sched/idle.h @@ -5,8 +5,8 @@ #include <linux/sched.h> enum cpu_idle_type { + __CPU_NOT_IDLE = 0, CPU_IDLE, - CPU_NOT_IDLE, CPU_NEWLY_IDLE, CPU_MAX_IDLE_TYPES }; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 9a19f1b42f64..b6543f9d78d6 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -236,16 +236,25 @@ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); - if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { + if (unlikely(pflags & (PF_MEMALLOC_NOIO | + PF_MEMALLOC_NOFS | + PF_MEMALLOC_NORECLAIM | + PF_MEMALLOC_NOWARN | + PF_MEMALLOC_PIN))) { /* - * NOIO implies both NOIO and NOFS and it is a weaker context - * so always make sure it makes precedence + * Stronger flags before weaker flags: + * NORECLAIM implies NOIO, which in turn implies NOFS */ - if (pflags & PF_MEMALLOC_NOIO) + if (pflags & PF_MEMALLOC_NORECLAIM) + flags &= ~__GFP_DIRECT_RECLAIM; + else if (pflags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; + if (pflags & PF_MEMALLOC_NOWARN) + flags |= __GFP_NOWARN; + if (pflags & PF_MEMALLOC_PIN) flags &= ~__GFP_MOVABLE; } @@ -307,6 +316,24 @@ static inline void might_alloc(gfp_t gfp_mask) } /** + * memalloc_flags_save - Add a PF_* flag to current->flags, save old value + * + * This allows PF_* flags to be conveniently added, irrespective of current + * value, and then the old version restored with memalloc_flags_restore(). + */ +static inline unsigned memalloc_flags_save(unsigned flags) +{ + unsigned oldflags = ~current->flags & flags; + current->flags |= flags; + return oldflags; +} + +static inline void memalloc_flags_restore(unsigned flags) +{ + current->flags &= ~flags; +} + +/** * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope. * * This functions marks the beginning of the GFP_NOIO allocation scope. @@ -315,13 +342,12 @@ static inline void might_alloc(gfp_t gfp_mask) * point of view. Use memalloc_noio_restore to end the scope with flags * returned by this function. * - * This function is safe to be used from any context. + * Context: This function is safe to be used from any context. + * Return: The saved flags to be passed to memalloc_noio_restore. */ static inline unsigned int memalloc_noio_save(void) { - unsigned int flags = current->flags & PF_MEMALLOC_NOIO; - current->flags |= PF_MEMALLOC_NOIO; - return flags; + return memalloc_flags_save(PF_MEMALLOC_NOIO); } /** @@ -334,7 +360,7 @@ static inline unsigned int memalloc_noio_save(void) */ static inline void memalloc_noio_restore(unsigned int flags) { - current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; + memalloc_flags_restore(flags); } /** @@ -346,13 +372,12 @@ static inline void memalloc_noio_restore(unsigned int flags) * point of view. Use memalloc_nofs_restore to end the scope with flags * returned by this function. * - * This function is safe to be used from any context. + * Context: This function is safe to be used from any context. + * Return: The saved flags to be passed to memalloc_nofs_restore. */ static inline unsigned int memalloc_nofs_save(void) { - unsigned int flags = current->flags & PF_MEMALLOC_NOFS; - current->flags |= PF_MEMALLOC_NOFS; - return flags; + return memalloc_flags_save(PF_MEMALLOC_NOFS); } /** @@ -365,32 +390,76 @@ static inline unsigned int memalloc_nofs_save(void) */ static inline void memalloc_nofs_restore(unsigned int flags) { - current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags; + memalloc_flags_restore(flags); } +/** + * memalloc_noreclaim_save - Marks implicit __GFP_MEMALLOC scope. + * + * This function marks the beginning of the __GFP_MEMALLOC allocation scope. + * All further allocations will implicitly add the __GFP_MEMALLOC flag, which + * prevents entering reclaim and allows access to all memory reserves. This + * should only be used when the caller guarantees the allocation will allow more + * memory to be freed very shortly, i.e. it needs to allocate some memory in + * the process of freeing memory, and cannot reclaim due to potential recursion. + * + * Users of this scope have to be extremely careful to not deplete the reserves + * completely and implement a throttling mechanism which controls the + * consumption of the reserve based on the amount of freed memory. Usage of a + * pre-allocated pool (e.g. mempool) should be always considered before using + * this scope. + * + * Individual allocations under the scope can opt out using __GFP_NOMEMALLOC + * + * Context: This function should not be used in an interrupt context as that one + * does not give PF_MEMALLOC access to reserves. + * See __gfp_pfmemalloc_flags(). + * Return: The saved flags to be passed to memalloc_noreclaim_restore. + */ static inline unsigned int memalloc_noreclaim_save(void) { - unsigned int flags = current->flags & PF_MEMALLOC; - current->flags |= PF_MEMALLOC; - return flags; + return memalloc_flags_save(PF_MEMALLOC); } +/** + * memalloc_noreclaim_restore - Ends the implicit __GFP_MEMALLOC scope. + * @flags: Flags to restore. + * + * Ends the implicit __GFP_MEMALLOC scope started by memalloc_noreclaim_save + * function. Always make sure that the given flags is the return value from the + * pairing memalloc_noreclaim_save call. + */ static inline void memalloc_noreclaim_restore(unsigned int flags) { - current->flags = (current->flags & ~PF_MEMALLOC) | flags; + memalloc_flags_restore(flags); } +/** + * memalloc_pin_save - Marks implicit ~__GFP_MOVABLE scope. + * + * This function marks the beginning of the ~__GFP_MOVABLE allocation scope. + * All further allocations will implicitly remove the __GFP_MOVABLE flag, which + * will constraint the allocations to zones that allow long term pinning, i.e. + * not ZONE_MOVABLE zones. + * + * Return: The saved flags to be passed to memalloc_pin_restore. + */ static inline unsigned int memalloc_pin_save(void) { - unsigned int flags = current->flags & PF_MEMALLOC_PIN; - - current->flags |= PF_MEMALLOC_PIN; - return flags; + return memalloc_flags_save(PF_MEMALLOC_PIN); } +/** + * memalloc_pin_restore - Ends the implicit ~__GFP_MOVABLE scope. + * @flags: Flags to restore. + * + * Ends the implicit ~__GFP_MOVABLE scope started by memalloc_pin_save function. + * Always make sure that the given flags is the return value from the pairing + * memalloc_pin_save call. + */ static inline void memalloc_pin_restore(unsigned int flags) { - current->flags = (current->flags & ~PF_MEMALLOC_PIN) | flags; + memalloc_flags_restore(flags); } #ifdef CONFIG_MEMCG diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 18572c9ea724..4237daa5ac7a 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -110,7 +110,7 @@ struct sched_domain { unsigned long last_decay_max_lb_cost; #ifdef CONFIG_SCHEDSTATS - /* load_balance() stats */ + /* sched_balance_rq() stats */ unsigned int lb_count[CPU_MAX_IDLE_TYPES]; unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; @@ -270,17 +270,17 @@ unsigned long arch_scale_cpu_capacity(int cpu) } #endif -#ifndef arch_scale_thermal_pressure +#ifndef arch_scale_hw_pressure static __always_inline -unsigned long arch_scale_thermal_pressure(int cpu) +unsigned long arch_scale_hw_pressure(int cpu) { return 0; } #endif -#ifndef arch_update_thermal_pressure +#ifndef arch_update_hw_pressure static __always_inline -void arch_update_thermal_pressure(const struct cpumask *cpus, +void arch_update_hw_pressure(const struct cpumask *cpus, unsigned long capped_frequency) { } #endif diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 2ee94ff0320c..3a9bb5b9a9e8 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -140,6 +140,8 @@ struct scmi_perf_domain_info { * @level_set: sets the performance level of a domain * @level_get: gets the performance level of a domain * @transition_latency_get: gets the DVFS transition latency for a given device + * @rate_limit_get: gets the minimum time (us) required between successive + * requests * @device_opps_add: adds all the OPPs for a given device * @freq_set: sets the frequency for a given device using sustained frequency * to sustained performance level mapping @@ -149,6 +151,8 @@ struct scmi_perf_domain_info { * at a given frequency * @fast_switch_possible: indicates if fast DVFS switching is possible or not * for a given device + * @fast_switch_rate_limit: gets the minimum time (us) required between + * successive fast_switching requests * @power_scale_mw_get: indicates if the power values provided are in milliWatts * or in some other (abstract) scale */ @@ -166,6 +170,8 @@ struct scmi_perf_proto_ops { u32 *level, bool poll); int (*transition_latency_get)(const struct scmi_protocol_handle *ph, u32 domain); + int (*rate_limit_get)(const struct scmi_protocol_handle *ph, + u32 domain, u32 *rate_limit); int (*device_opps_add)(const struct scmi_protocol_handle *ph, struct device *dev, u32 domain); int (*freq_set)(const struct scmi_protocol_handle *ph, u32 domain, @@ -176,6 +182,8 @@ struct scmi_perf_proto_ops { unsigned long *rate, unsigned long *power); bool (*fast_switch_possible)(const struct scmi_protocol_handle *ph, u32 domain); + int (*fast_switch_rate_limit)(const struct scmi_protocol_handle *ph, + u32 domain, u32 *rate_limit); enum scmi_power_scale (*power_scale_get)(const struct scmi_protocol_handle *ph); }; @@ -729,6 +737,89 @@ struct scmi_powercap_proto_ops { u32 *power_thresh_high); }; +enum scmi_pinctrl_selector_type { + PIN_TYPE = 0, + GROUP_TYPE, + FUNCTION_TYPE, +}; + +enum scmi_pinctrl_conf_type { + SCMI_PIN_DEFAULT = 0, + SCMI_PIN_BIAS_BUS_HOLD = 1, + SCMI_PIN_BIAS_DISABLE = 2, + SCMI_PIN_BIAS_HIGH_IMPEDANCE = 3, + SCMI_PIN_BIAS_PULL_UP = 4, + SCMI_PIN_BIAS_PULL_DEFAULT = 5, + SCMI_PIN_BIAS_PULL_DOWN = 6, + SCMI_PIN_DRIVE_OPEN_DRAIN = 7, + SCMI_PIN_DRIVE_OPEN_SOURCE = 8, + SCMI_PIN_DRIVE_PUSH_PULL = 9, + SCMI_PIN_DRIVE_STRENGTH = 10, + SCMI_PIN_INPUT_DEBOUNCE = 11, + SCMI_PIN_INPUT_MODE = 12, + SCMI_PIN_PULL_MODE = 13, + SCMI_PIN_INPUT_VALUE = 14, + SCMI_PIN_INPUT_SCHMITT = 15, + SCMI_PIN_LOW_POWER_MODE = 16, + SCMI_PIN_OUTPUT_MODE = 17, + SCMI_PIN_OUTPUT_VALUE = 18, + SCMI_PIN_POWER_SOURCE = 19, + SCMI_PIN_SLEW_RATE = 20, + SCMI_PIN_OEM_START = 192, + SCMI_PIN_OEM_END = 255, +}; + +/** + * struct scmi_pinctrl_proto_ops - represents the various operations provided + * by SCMI Pinctrl Protocol + * + * @count_get: returns count of the registered elements in given type + * @name_get: returns name by index of given type + * @group_pins_get: returns the set of pins, assigned to the specified group + * @function_groups_get: returns the set of groups, assigned to the specified + * function + * @mux_set: set muxing function for groups of pins + * @settings_get_one: returns one configuration parameter for pin or group + * specified by config_type + * @settings_get_all: returns all configuration parameters for pin or group + * @settings_conf: sets the configuration parameter for pin or group + * @pin_request: aquire pin before selecting mux setting + * @pin_free: frees pin, acquired by request_pin call + */ +struct scmi_pinctrl_proto_ops { + int (*count_get)(const struct scmi_protocol_handle *ph, + enum scmi_pinctrl_selector_type type); + int (*name_get)(const struct scmi_protocol_handle *ph, u32 selector, + enum scmi_pinctrl_selector_type type, + const char **name); + int (*group_pins_get)(const struct scmi_protocol_handle *ph, + u32 selector, const unsigned int **pins, + unsigned int *nr_pins); + int (*function_groups_get)(const struct scmi_protocol_handle *ph, + u32 selector, unsigned int *nr_groups, + const unsigned int **groups); + int (*mux_set)(const struct scmi_protocol_handle *ph, u32 selector, + u32 group); + int (*settings_get_one)(const struct scmi_protocol_handle *ph, + u32 selector, + enum scmi_pinctrl_selector_type type, + enum scmi_pinctrl_conf_type config_type, + u32 *config_value); + int (*settings_get_all)(const struct scmi_protocol_handle *ph, + u32 selector, + enum scmi_pinctrl_selector_type type, + unsigned int *nr_configs, + enum scmi_pinctrl_conf_type *config_types, + u32 *config_values); + int (*settings_conf)(const struct scmi_protocol_handle *ph, + u32 selector, enum scmi_pinctrl_selector_type type, + unsigned int nr_configs, + enum scmi_pinctrl_conf_type *config_type, + u32 *config_value); + int (*pin_request)(const struct scmi_protocol_handle *ph, u32 pin); + int (*pin_free)(const struct scmi_protocol_handle *ph, u32 pin); +}; + /** * struct scmi_notify_ops - represents notifications' operations provided by * SCMI core @@ -775,8 +866,6 @@ struct scmi_notify_ops { const u32 *src_id, struct notifier_block *nb); int (*devm_event_notifier_unregister)(struct scmi_device *sdev, - u8 proto_id, u8 evt_id, - const u32 *src_id, struct notifier_block *nb); int (*event_notifier_register)(const struct scmi_handle *handle, u8 proto_id, u8 evt_id, @@ -836,6 +925,7 @@ enum scmi_std_protocol { SCMI_PROTOCOL_RESET = 0x16, SCMI_PROTOCOL_VOLTAGE = 0x17, SCMI_PROTOCOL_POWERCAP = 0x18, + SCMI_PROTOCOL_PINCTRL = 0x19, }; enum scmi_system_events { diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h index eab7081392d5..75303c126285 100644 --- a/include/linux/screen_info.h +++ b/include/linux/screen_info.h @@ -4,6 +4,132 @@ #include <uapi/linux/screen_info.h> +#include <linux/bits.h> + +/** + * SCREEN_INFO_MAX_RESOURCES - maximum number of resources per screen_info + */ +#define SCREEN_INFO_MAX_RESOURCES 3 + +struct pci_dev; +struct resource; + +static inline bool __screen_info_has_lfb(unsigned int type) +{ + return (type == VIDEO_TYPE_VLFB) || (type == VIDEO_TYPE_EFI); +} + +static inline u64 __screen_info_lfb_base(const struct screen_info *si) +{ + u64 lfb_base = si->lfb_base; + + if (si->capabilities & VIDEO_CAPABILITY_64BIT_BASE) + lfb_base |= (u64)si->ext_lfb_base << 32; + + return lfb_base; +} + +static inline void __screen_info_set_lfb_base(struct screen_info *si, u64 lfb_base) +{ + si->lfb_base = lfb_base & GENMASK_ULL(31, 0); + si->ext_lfb_base = (lfb_base & GENMASK_ULL(63, 32)) >> 32; + + if (si->ext_lfb_base) + si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + else + si->capabilities &= ~VIDEO_CAPABILITY_64BIT_BASE; +} + +static inline u64 __screen_info_lfb_size(const struct screen_info *si, unsigned int type) +{ + u64 lfb_size = si->lfb_size; + + if (type == VIDEO_TYPE_VLFB) + lfb_size <<= 16; + return lfb_size; +} + +static inline unsigned int __screen_info_video_type(unsigned int type) +{ + switch (type) { + case VIDEO_TYPE_MDA: + case VIDEO_TYPE_CGA: + case VIDEO_TYPE_EGAM: + case VIDEO_TYPE_EGAC: + case VIDEO_TYPE_VGAC: + case VIDEO_TYPE_VLFB: + case VIDEO_TYPE_PICA_S3: + case VIDEO_TYPE_MIPS_G364: + case VIDEO_TYPE_SGI: + case VIDEO_TYPE_TGAC: + case VIDEO_TYPE_SUN: + case VIDEO_TYPE_SUNPCI: + case VIDEO_TYPE_PMAC: + case VIDEO_TYPE_EFI: + return type; + default: + return 0; + } +} + +/** + * screen_info_video_type() - Decodes the video type from struct screen_info + * @si: an instance of struct screen_info + * + * Returns: + * A VIDEO_TYPE_ constant representing si's type of video display, or 0 otherwise. + */ +static inline unsigned int screen_info_video_type(const struct screen_info *si) +{ + unsigned int type; + + // check if display output is on + if (!si->orig_video_isVGA) + return 0; + + // check for a known VIDEO_TYPE_ constant + type = __screen_info_video_type(si->orig_video_isVGA); + if (type) + return si->orig_video_isVGA; + + // check if text mode has been initialized + if (!si->orig_video_lines || !si->orig_video_cols) + return 0; + + // 80x25 text, mono + if (si->orig_video_mode == 0x07) { + if ((si->orig_video_ega_bx & 0xff) != 0x10) + return VIDEO_TYPE_EGAM; + else + return VIDEO_TYPE_MDA; + } + + // EGA/VGA, 16 colors + if ((si->orig_video_ega_bx & 0xff) != 0x10) { + if (si->orig_video_isVGA) + return VIDEO_TYPE_VGAC; + else + return VIDEO_TYPE_EGAC; + } + + // the rest... + return VIDEO_TYPE_CGA; +} + +ssize_t screen_info_resources(const struct screen_info *si, struct resource *r, size_t num); + +#if defined(CONFIG_PCI) +void screen_info_apply_fixups(void); +struct pci_dev *screen_info_pci_dev(const struct screen_info *si); +#else +static inline void screen_info_apply_fixups(void) +{ } +static inline struct pci_dev *screen_info_pci_dev(const struct screen_info *si) +{ + return NULL; +} +#endif + extern struct screen_info screen_info; #endif /* _SCREEN_INFO_H */ diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 35f3a4a8ceb1..acf7e1a3f3de 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -13,10 +13,10 @@ static inline bool folio_is_secretmem(struct folio *folio) /* * Using folio_mapping() is quite slow because of the actual call * instruction. - * We know that secretmem pages are not compound and LRU so we can + * We know that secretmem pages are not compound, so we can * save a couple of cycles here. */ - if (folio_test_large(folio) || !folio_test_lru(folio)) + if (folio_test_large(folio)) return false; mapping = (struct address_space *) diff --git a/include/linux/security.h b/include/linux/security.h index f249f5b9a9d7..21cf70346b33 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -398,7 +398,7 @@ int security_inode_setsecurity(struct inode *inode, const char *name, const void int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size); void security_inode_getsecid(struct inode *inode, u32 *secid); int security_inode_copy_up(struct dentry *src, struct cred **new); -int security_inode_copy_up_xattr(const char *name); +int security_inode_copy_up_xattr(struct dentry *src, const char *name); int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn); int security_file_permission(struct file *file, int mask); @@ -491,9 +491,9 @@ int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter); void security_d_instantiate(struct dentry *dentry, struct inode *inode); int security_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx, - size_t __user *size, u32 flags); + u32 __user *size, u32 flags); int security_setselfattr(unsigned int attr, struct lsm_ctx __user *ctx, - size_t size, u32 flags); + u32 size, u32 flags); int security_getprocattr(struct task_struct *p, int lsmid, const char *name, char **value); int security_setprocattr(int lsmid, const char *name, void *value, size_t size); @@ -507,7 +507,7 @@ int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen); int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen); int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen); int security_locked_down(enum lockdown_reason what); -int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, size_t *uctx_len, +int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags); #else /* CONFIG_SECURITY */ @@ -1016,7 +1016,7 @@ static inline int security_kernfs_init_security(struct kernfs_node *kn_dir, return 0; } -static inline int security_inode_copy_up_xattr(const char *name) +static inline int security_inode_copy_up_xattr(struct dentry *src, const char *name) { return -EOPNOTSUPP; } @@ -1478,7 +1478,7 @@ static inline int security_locked_down(enum lockdown_reason what) return 0; } static inline int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, - size_t *uctx_len, void *val, size_t val_len, + u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags) { return -EOPNOTSUPP; diff --git a/include/linux/selection.h b/include/linux/selection.h index 170ef28ff26b..bab7d30d3446 100644 --- a/include/linux/selection.h +++ b/include/linux/selection.h @@ -14,17 +14,16 @@ struct tty_struct; struct vc_data; -extern void clear_selection(void); -extern int set_selection_user(const struct tiocl_selection __user *sel, - struct tty_struct *tty); -extern int set_selection_kernel(struct tiocl_selection *v, - struct tty_struct *tty); -extern int paste_selection(struct tty_struct *tty); -extern int sel_loadlut(char __user *p); -extern int mouse_reporting(void); -extern void mouse_report(struct tty_struct * tty, int butt, int mrx, int mry); - -bool vc_is_sel(struct vc_data *vc); +void clear_selection(void); +int set_selection_user(const struct tiocl_selection __user *sel, + struct tty_struct *tty); +int set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty); +int paste_selection(struct tty_struct *tty); +int sel_loadlut(u32 __user *lut); +int mouse_reporting(void); +void mouse_report(struct tty_struct *tty, int butt, int mrx, int mry); + +bool vc_is_sel(const struct vc_data *vc); extern int console_blanked; @@ -33,24 +32,21 @@ extern unsigned char default_red[]; extern unsigned char default_grn[]; extern unsigned char default_blu[]; -extern unsigned short *screen_pos(const struct vc_data *vc, int w_offset, - bool viewed); -extern u16 screen_glyph(const struct vc_data *vc, int offset); -extern u32 screen_glyph_unicode(const struct vc_data *vc, int offset); -extern void complement_pos(struct vc_data *vc, int offset); -extern void invert_screen(struct vc_data *vc, int offset, int count, bool viewed); - -extern void getconsxy(const struct vc_data *vc, unsigned char xy[static 2]); -extern void putconsxy(struct vc_data *vc, unsigned char xy[static const 2]); - -extern u16 vcs_scr_readw(const struct vc_data *vc, const u16 *org); -extern void vcs_scr_writew(struct vc_data *vc, u16 val, u16 *org); -extern void vcs_scr_updated(struct vc_data *vc); - -extern int vc_uniscr_check(struct vc_data *vc); -extern void vc_uniscr_copy_line(const struct vc_data *vc, void *dest, - bool viewed, - unsigned int row, unsigned int col, - unsigned int nr); +unsigned short *screen_pos(const struct vc_data *vc, int w_offset, bool viewed); +u16 screen_glyph(const struct vc_data *vc, int offset); +u32 screen_glyph_unicode(const struct vc_data *vc, int offset); +void complement_pos(struct vc_data *vc, int offset); +void invert_screen(struct vc_data *vc, int offset, int count, bool viewed); + +void getconsxy(const struct vc_data *vc, unsigned char xy[static 2]); +void putconsxy(struct vc_data *vc, unsigned char xy[static const 2]); + +u16 vcs_scr_readw(const struct vc_data *vc, const u16 *org); +void vcs_scr_writew(struct vc_data *vc, u16 val, u16 *org); +void vcs_scr_updated(struct vc_data *vc); + +int vc_uniscr_check(struct vc_data *vc); +void vc_uniscr_copy_line(const struct vc_data *vc, void *dest, bool viewed, + unsigned int row, unsigned int col, unsigned int nr); #endif diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 234bcdb1fba4..8bd4fda6e027 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -118,7 +118,18 @@ void seq_vprintf(struct seq_file *m, const char *fmt, va_list args); __printf(2, 3) void seq_printf(struct seq_file *m, const char *fmt, ...); void seq_putc(struct seq_file *m, char c); -void seq_puts(struct seq_file *m, const char *s); +void __seq_puts(struct seq_file *m, const char *s); + +static __always_inline void seq_puts(struct seq_file *m, const char *s) +{ + if (!__builtin_constant_p(*s)) + __seq_puts(m, s); + else if (s[0] && !s[1]) + seq_putc(m, s[0]); + else + seq_write(m, s, __builtin_strlen(s)); +} + void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, unsigned long long num, unsigned int width); void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, diff --git a/include/linux/serdev.h b/include/linux/serdev.h index 3fab88ba265e..ff78efc1f60d 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -27,7 +27,7 @@ struct serdev_device; * not sleep. */ struct serdev_device_ops { - ssize_t (*receive_buf)(struct serdev_device *, const u8 *, size_t); + size_t (*receive_buf)(struct serdev_device *, const u8 *, size_t); void (*write_wakeup)(struct serdev_device *); }; @@ -185,9 +185,9 @@ static inline void serdev_controller_write_wakeup(struct serdev_controller *ctrl serdev->ops->write_wakeup(serdev); } -static inline ssize_t serdev_controller_receive_buf(struct serdev_controller *ctrl, - const u8 *data, - size_t count) +static inline size_t serdev_controller_receive_buf(struct serdev_controller *ctrl, + const u8 *data, + size_t count) { struct serdev_device *serdev = ctrl->serdev; diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index be65de65fe61..fd59ed2cca53 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -210,6 +210,12 @@ int serial8250_console_exit(struct uart_port *port); void serial8250_set_isa_configurator(void (*v)(int port, struct uart_port *up, u32 *capabilities)); +#ifdef CONFIG_SERIAL_8250_CONSOLE +extern int hp300_setup_serial_console(void) __init; +#else +static inline int hp300_setup_serial_console(void) { return 0; } +#endif + #ifdef CONFIG_SERIAL_8250_RT288X int rt288x_setup(struct uart_port *p); int au_platform_setup(struct plat_serial8250_port *p); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 55b1f3ba48ac..0a0f6e21d40e 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -467,9 +467,10 @@ struct uart_port { unsigned int fifosize; /* tx fifo size */ unsigned char x_char; /* xon/xoff char */ unsigned char regshift; /* reg offset shift */ + unsigned char iotype; /* io access style */ - unsigned char quirks; /* internal quirks */ +#define UPIO_UNKNOWN ((unsigned char)~0U) /* UCHAR_MAX */ #define UPIO_PORT (SERIAL_IO_PORT) /* 8b I/O port access */ #define UPIO_HUB6 (SERIAL_IO_HUB6) /* Hub6 ISA card */ #define UPIO_MEM (SERIAL_IO_MEM) /* driver-specific */ @@ -479,7 +480,9 @@ struct uart_port { #define UPIO_MEM32BE (SERIAL_IO_MEM32BE) /* 32b big endian */ #define UPIO_MEM16 (SERIAL_IO_MEM16) /* 16b little endian */ - /* quirks must be updated while holding port mutex */ + unsigned char quirks; /* internal quirks */ + + /* internal quirks must be updated while holding port mutex */ #define UPQ_NO_TXEN_TEST BIT(0) unsigned int read_status_mask; /* driver specific */ @@ -786,7 +789,8 @@ enum UART_TX_FLAGS { if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ - if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ + if (!((flags) & UART_TX_NOSTOP) && pending == 0 && \ + __port->ops->tx_empty(__port)) \ __port->ops->stop_tx(__port); \ } \ \ @@ -959,6 +963,8 @@ int uart_register_driver(struct uart_driver *uart); void uart_unregister_driver(struct uart_driver *uart); int uart_add_one_port(struct uart_driver *reg, struct uart_port *port); void uart_remove_one_port(struct uart_driver *reg, struct uart_port *port); +int uart_read_port_properties(struct uart_port *port); +int uart_read_and_validate_port_properties(struct uart_port *port); bool uart_match_port(const struct uart_port *port1, const struct uart_port *port2); diff --git a/include/linux/serio.h b/include/linux/serio.h index 6c27d413da92..7ca41af93b37 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -15,7 +15,7 @@ #include <linux/mod_devicetable.h> #include <uapi/linux/serio.h> -extern struct bus_type serio_bus; +extern const struct bus_type serio_bus; struct serio { void *port_data; diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 9346cd44814d..a45da7eef9a2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -554,7 +554,7 @@ bool sfp_may_have_phy(struct sfp_bus *bus, const struct sfp_eeprom_id *id); void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support, unsigned long *interfaces); phy_interface_t sfp_select_interface(struct sfp_bus *bus, - unsigned long *link_modes); + const unsigned long *link_modes); int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo); int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, @@ -592,7 +592,7 @@ static inline void sfp_parse_support(struct sfp_bus *bus, } static inline phy_interface_t sfp_select_interface(struct sfp_bus *bus, - unsigned long *link_modes) + const unsigned long *link_modes) { return PHY_INTERFACE_MODE_NA; } diff --git a/include/linux/shm.h b/include/linux/shm.h index c55bef0538e5..1d3d3ae958fb 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -16,7 +16,6 @@ struct sysv_shm { long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr, unsigned long shmlba); -bool is_file_shm_hugepages(struct file *file); void exit_shm(struct task_struct *task); #define shm_init_task(task) INIT_LIST_HEAD(&(task)->sysvshm.shm_clist) #else @@ -30,10 +29,6 @@ static inline long do_shmat(int shmid, char __user *shmaddr, { return -ENOSYS; } -static inline bool is_file_shm_hugepages(struct file *file) -{ - return false; -} static inline void exit_shm(struct task_struct *task) { } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 2caa6b86106a..3fb18f7eb73e 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -37,7 +37,7 @@ struct shmem_inode_info { unsigned int fsflags; /* for FS_IOC_[SG]ETFLAGS */ atomic_t stop_eviction; /* hold when working on inode */ #ifdef CONFIG_TMPFS_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif struct inode vfs_inode; }; @@ -97,11 +97,7 @@ extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts); #ifdef CONFIG_SHMEM -extern const struct address_space_operations shmem_aops; -static inline bool shmem_mapping(struct address_space *mapping) -{ - return mapping->a_ops == &shmem_aops; -} +bool shmem_mapping(struct address_space *mapping); #else static inline bool shmem_mapping(struct address_space *mapping) { @@ -114,8 +110,17 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +#else +static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, + struct mm_struct *mm, unsigned long vm_flags) +{ + return false; +} +#endif + #ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); #else diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3023bc2be6a1..c0b97c93a6de 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -353,8 +353,6 @@ struct sk_buff; #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 * segment using its current segmentation instead. */ @@ -527,6 +525,13 @@ enum { #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) +struct ubuf_info_ops { + void (*complete)(struct sk_buff *, struct ubuf_info *, + bool zerocopy_success); + /* has to be compatible with skb_zcopy_set() */ + int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); +}; + /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. @@ -536,8 +541,7 @@ enum { * The desc field is used to track userspace buffer index. */ struct ubuf_info { - void (*callback)(struct sk_buff *, struct ubuf_info *, - bool zerocopy_success); + const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; @@ -753,8 +757,6 @@ typedef unsigned char *sk_buff_data_t; * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by - * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in - * fragmentation management * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here @@ -822,9 +824,9 @@ typedef unsigned char *sk_buff_data_t; * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @mono_delivery_time: When set, skb->tstamp has the - * delivery_time in mono clock base (i.e., EDT) or a clock base chosen - * by SO_TXTIME. If zero, skb->tstamp has the (rcv) timestamp at - * ingress. + * delivery_time in mono clock base (i.e. EDT). Otherwise, the + * skb->tstamp has the (rcv) timestamp at ingress and + * delivery_time at egress. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. @@ -875,10 +877,7 @@ struct sk_buff { struct llist_node ll_node; }; - union { - struct sock *sk; - int ip_defrag_offset; - }; + struct sock *sk; union { ktime_t tstamp; @@ -997,7 +996,7 @@ struct sk_buff { #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; @@ -1179,15 +1178,6 @@ static inline bool skb_dst_is_noref(const struct sk_buff *skb) return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } -/** - * skb_rtable - Returns the skb &rtable - * @skb: buffer - */ -static inline struct rtable *skb_rtable(const struct sk_buff *skb) -{ - return (struct rtable *)skb_dst(skb); -} - /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. @@ -1620,17 +1610,26 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } +static inline bool skb_is_decrypted(const struct sk_buff *skb) +{ +#ifdef CONFIG_SKB_DECRYPTED + return skb->decrypted; +#else + return false; +#endif +} + static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } @@ -1667,14 +1666,13 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; + struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); - int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length); @@ -1762,13 +1760,13 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) - uarg->callback(NULL, uarg, true); + uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { - if (uarg->callback == msg_zerocopy_callback) + if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); @@ -1782,7 +1780,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (uarg) { if (!skb_zcopy_is_nouarg(skb)) - uarg->callback(skb, uarg, zerocopy_success); + uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } @@ -3036,6 +3034,21 @@ static inline void skb_mac_header_rebuild(struct sk_buff *skb) } } +/* Move the full mac header up to current network_header. + * Leaves skb->data pointing at offset skb->mac_len into the mac_header. + * Must be provided the complete mac header length. + */ +static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) +{ + if (skb_mac_header_was_set(skb)) { + const unsigned char *old_mac = skb_mac_header(skb); + + skb_set_mac_header(skb, -full_mac_len); + memmove(skb_mac_header(skb), old_mac, full_mac_len); + __skb_push(skb, full_mac_len - skb->mac_len); + } +} + static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); @@ -3355,13 +3368,7 @@ static inline void *napi_alloc_frag_align(unsigned int fragsz, return __napi_alloc_frag_align(fragsz, -align); } -struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, - unsigned int length, gfp_t gfp_mask); -static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, - unsigned int length) -{ - return __napi_alloc_skb(napi, length, GFP_ATOMIC); -} +struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); @@ -3494,75 +3501,10 @@ static inline struct page *skb_frag_page(const skb_frag_t *frag) return netmem_to_page(frag->netmem); } -/** - * __skb_frag_ref - take an addition reference on a paged fragment. - * @frag: the paged fragment - * - * Takes an additional reference on the paged fragment @frag. - */ -static inline void __skb_frag_ref(skb_frag_t *frag) -{ - get_page(skb_frag_page(frag)); -} - -/** - * skb_frag_ref - take an addition reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset. - * - * Takes an additional reference on the @f'th paged fragment of @skb. - */ -static inline void skb_frag_ref(struct sk_buff *skb, int f) -{ - __skb_frag_ref(&skb_shinfo(skb)->frags[f]); -} - int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); -bool napi_pp_put_page(struct page *page, bool napi_safe); - -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 && napi_pp_put_page(page, napi_safe)) - return; -#endif - put_page(page); -} - -/** - * __skb_frag_unref - release a reference on a paged fragment. - * @frag: the paged fragment - * @recycle: recycle the page if allocated via page_pool - * - * Releases a reference on the paged fragment @frag - * or recycles the page via the page_pool API. - */ -static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) -{ - napi_frag_unref(frag, recycle, false); -} - -/** - * skb_frag_unref - release a reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset - * - * Releases a reference on the @f'th paged fragment of @skb. - */ -static inline void skb_frag_unref(struct sk_buff *skb, int f) -{ - struct skb_shared_info *shinfo = skb_shinfo(skb); - - if (!skb_zcopy_managed(skb)) - __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); -} - /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer @@ -4053,12 +3995,6 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); -void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len); -static inline void skb_free_datagram_locked(struct sock *sk, - struct sk_buff *skb) -{ - __skb_free_datagram_locked(sk, skb, 0); -} int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h new file mode 100644 index 000000000000..11f0a4063403 --- /dev/null +++ b/include/linux/skbuff_ref.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Skb ref helpers. + * + */ + +#ifndef _LINUX_SKBUFF_REF_H +#define _LINUX_SKBUFF_REF_H + +#include <linux/skbuff.h> + +/** + * __skb_frag_ref - take an addition reference on a paged fragment. + * @frag: the paged fragment + * + * Takes an additional reference on the paged fragment @frag. + */ +static inline void __skb_frag_ref(skb_frag_t *frag) +{ + get_page(skb_frag_page(frag)); +} + +/** + * skb_frag_ref - take an addition reference on a paged fragment of an skb. + * @skb: the buffer + * @f: the fragment offset. + * + * Takes an additional reference on the @f'th paged fragment of @skb. + */ +static inline void skb_frag_ref(struct sk_buff *skb, int f) +{ + __skb_frag_ref(&skb_shinfo(skb)->frags[f]); +} + +bool napi_pp_put_page(struct page *page); + +static inline void +skb_page_unref(struct page *page, bool recycle) +{ +#ifdef CONFIG_PAGE_POOL + if (recycle && napi_pp_put_page(page)) + return; +#endif + put_page(page); +} + +/** + * __skb_frag_unref - release a reference on a paged fragment. + * @frag: the paged fragment + * @recycle: recycle the page if allocated via page_pool + * + * Releases a reference on the paged fragment @frag + * or recycles the page via the page_pool API. + */ +static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) +{ + skb_page_unref(skb_frag_page(frag), recycle); +} + +/** + * skb_frag_unref - release a reference on a paged fragment of an skb. + * @skb: the buffer + * @f: the fragment offset + * + * Releases a reference on the @f'th paged fragment of @skb. + */ +static inline void skb_frag_unref(struct sk_buff *skb, int f) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (!skb_zcopy_managed(skb)) + __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); +} + +#endif /* _LINUX_SKBUFF_REF_H */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e65ec3fd2799..3f3246a6a6fb 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -58,6 +58,10 @@ struct sk_psock_progs { struct bpf_prog *stream_parser; struct bpf_prog *stream_verdict; struct bpf_prog *skb_verdict; + struct bpf_link *msg_parser_link; + struct bpf_link *stream_parser_link; + struct bpf_link *stream_verdict_link; + struct bpf_link *skb_verdict_link; }; enum sk_psock_state_bits { @@ -461,10 +465,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { + read_lock_bh(&sk->sk_callback_lock); if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); + read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, diff --git a/include/linux/slab.h b/include/linux/slab.h index e53cbfa18325..ebc20173cd4e 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -266,7 +266,7 @@ void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); -DEFINE_FREE(kfree, void *, if (_T) kfree(_T)) +DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) /** * ksize - Report actual allocation size of associated object @@ -774,14 +774,27 @@ static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags) return kvmalloc(size, flags | __GFP_ZERO); } -static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void * +kvmalloc_array_node(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - return kvmalloc(bytes, flags); + return kvmalloc_node(bytes, flags, node); +} + +static inline __alloc_size(1, 2) void * +kvmalloc_array(size_t n, size_t size, gfp_t flags) +{ + return kvmalloc_array_node(n, size, flags, NUMA_NO_NODE); +} + +static inline __alloc_size(1, 2) void * +kvcalloc_node(size_t n, size_t size, gfp_t flags, int node) +{ + return kvmalloc_array_node(n, size, flags | __GFP_ZERO, node); } static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t flags) @@ -792,7 +805,7 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) __realloc_size(3); extern void kvfree(const void *addr); -DEFINE_FREE(kvfree, void *, if (_T) kvfree(_T)) +DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) extern void kvfree_sensitive(const void *addr, size_t len); diff --git a/include/linux/slimbus.h b/include/linux/slimbus.h index 12c9719b2a55..3042385b7b40 100644 --- a/include/linux/slimbus.h +++ b/include/linux/slimbus.h @@ -10,7 +10,7 @@ #include <linux/completion.h> #include <linux/mod_devicetable.h> -extern struct bus_type slimbus_bus; +extern const struct bus_type slimbus_bus; /** * struct slim_eaddr - Enumeration address for a SLIMbus device diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 649955d2cf5c..d4a8e34505e6 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -14,6 +14,15 @@ #define CMDQ_ADDR_HIGH(addr) ((u32)(((addr) >> 16) & GENMASK(31, 0))) #define CMDQ_ADDR_LOW(addr) ((u16)(addr) | BIT(1)) +/* + * Every cmdq thread has its own SPRs (Specific Purpose Registers), + * so there are 4 * N (threads) SPRs in GCE that shares the same indexes below. + */ +#define CMDQ_THR_SPR_IDX0 (0) +#define CMDQ_THR_SPR_IDX1 (1) +#define CMDQ_THR_SPR_IDX2 (2) +#define CMDQ_THR_SPR_IDX3 (3) + struct cmdq_pkt; struct cmdq_client_reg { @@ -62,17 +71,19 @@ void cmdq_mbox_destroy(struct cmdq_client *client); /** * cmdq_pkt_create() - create a CMDQ packet * @client: the CMDQ mailbox client + * @pkt: the CMDQ packet * @size: required CMDQ buffer size * - * Return: CMDQ packet pointer + * Return: 0 for success; else the error code is returned */ -struct cmdq_pkt *cmdq_pkt_create(struct cmdq_client *client, size_t size); +int cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt *pkt, size_t size); /** * cmdq_pkt_destroy() - destroy the CMDQ packet + * @client: the CMDQ mailbox client * @pkt: the CMDQ packet */ -void cmdq_pkt_destroy(struct cmdq_pkt *pkt); +void cmdq_pkt_destroy(struct cmdq_client *client, struct cmdq_pkt *pkt); /** * cmdq_pkt_write() - append write command to the CMDQ packet @@ -174,6 +185,18 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, u16 addr_low, u32 value, u32 mask); /** + * cmdq_pkt_mem_move() - append memory move command to the CMDQ packet + * @pkt: the CMDQ packet + * @src_addr: source address + * @dst_addr: destination address + * + * Appends a CMDQ command to copy the value found in `src_addr` to `dst_addr`. + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_mem_move(struct cmdq_pkt *pkt, dma_addr_t src_addr, dma_addr_t dst_addr); + +/** * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet * @pkt: the CMDQ packet * @event: the desired event type to wait @@ -184,6 +207,21 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear); /** + * cmdq_pkt_acquire_event() - append acquire event command to the CMDQ packet + * @pkt: the CMDQ packet + * @event: the desired event to be acquired + * + * User can use cmdq_pkt_acquire_event() as `mutex_lock` and cmdq_pkt_clear_event() + * as `mutex_unlock` to protect some `critical section` instructions between them. + * cmdq_pkt_acquire_event() would wait for event to be cleared. + * After event is cleared by cmdq_pkt_clear_event in other GCE threads, + * cmdq_pkt_acquire_event() would set event and keep executing next instruction. + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_acquire_event(struct cmdq_pkt *pkt, u16 event); + +/** * cmdq_pkt_clear_event() - append clear event command to the CMDQ packet * @pkt: the CMDQ packet * @event: the desired event to be cleared @@ -248,36 +286,76 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value); /** - * cmdq_pkt_jump() - Append jump command to the CMDQ packet, ask GCE - * to execute an instruction that change current thread PC to - * a physical address which should contains more instruction. + * cmdq_pkt_poll_addr() - Append blocking POLL command to CMDQ packet + * @pkt: the CMDQ packet + * @addr: the hardware register address + * @value: the specified target register value + * @mask: the specified target register mask + * + * Appends a polling (POLL) command to the CMDQ packet and asks the GCE + * to execute an instruction that checks for the specified `value` (with + * or without `mask`) to appear in the specified hardware register `addr`. + * All GCE threads will be blocked by this instruction. + * + * Return: 0 for success or negative error code + */ +int cmdq_pkt_poll_addr(struct cmdq_pkt *pkt, dma_addr_t addr, u32 value, u32 mask); + +/** + * cmdq_pkt_jump_abs() - Append jump command to the CMDQ packet, ask GCE + * to execute an instruction that change current thread + * PC to a absolute physical address which should + * contains more instruction. * @pkt: the CMDQ packet - * @addr: physical address of target instruction buffer + * @addr: absolute physical address of target instruction buffer + * @shift_pa: shift bits of physical address in CMDQ instruction. This value + * is got by cmdq_get_shift_pa(). * * Return: 0 for success; else the error code is returned */ -int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr); +int cmdq_pkt_jump_abs(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa); + +/* This wrapper has to be removed after all users migrated to jump_abs */ +static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return cmdq_pkt_jump_abs(pkt, addr, shift_pa); +} /** - * cmdq_pkt_finalize() - Append EOC and jump command to pkt. + * cmdq_pkt_jump_rel() - Append jump command to the CMDQ packet, ask GCE + * to execute an instruction that change current thread + * PC to a physical address with relative offset. The + * target address should contains more instruction. * @pkt: the CMDQ packet + * @offset: relative offset of target instruction buffer from current PC. + * @shift_pa: shift bits of physical address in CMDQ instruction. This value + * is got by cmdq_get_shift_pa(). * * Return: 0 for success; else the error code is returned */ -int cmdq_pkt_finalize(struct cmdq_pkt *pkt); +int cmdq_pkt_jump_rel(struct cmdq_pkt *pkt, s32 offset, u8 shift_pa); + +/** + * cmdq_pkt_eoc() - Append EOC and ask GCE to generate an IRQ at end of execution + * @pkt: The CMDQ packet + * + * Appends an End Of Code (EOC) command to the CMDQ packet and asks the GCE + * to generate an interrupt at the end of the execution of all commands in + * the pipeline. + * The EOC command is usually appended to the end of the pipeline to notify + * that all commands are done. + * + * Return: 0 for success or negative error number + */ +int cmdq_pkt_eoc(struct cmdq_pkt *pkt); /** - * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ - * packet and call back at the end of done packet + * cmdq_pkt_finalize() - Append EOC and jump command to pkt. * @pkt: the CMDQ packet * * Return: 0 for success; else the error code is returned - * - * Trigger CMDQ to asynchronously execute the CMDQ packet and call back - * at the end of done packet. Note that this is an ASYNC function. When the - * function returned, it may or may not be finished. */ -int cmdq_pkt_flush_async(struct cmdq_pkt *pkt); +int cmdq_pkt_finalize(struct cmdq_pkt *pkt); #else /* IS_ENABLED(CONFIG_MTK_CMDQ) */ @@ -294,12 +372,12 @@ static inline struct cmdq_client *cmdq_mbox_create(struct device *dev, int index 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) +static inline int cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt *pkt, size_t size) { - return ERR_PTR(-EINVAL); + return -EINVAL; } -static inline void cmdq_pkt_destroy(struct cmdq_pkt *pkt) { } +static inline void cmdq_pkt_destroy(struct cmdq_client *client, struct cmdq_pkt *pkt) { } static inline int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value) { @@ -374,17 +452,32 @@ 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) +static inline int cmdq_pkt_poll_addr(struct cmdq_pkt *pkt, dma_addr_t addr, u32 value, u32 mask) { return -EINVAL; } -static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) +static inline int cmdq_pkt_jump_abs(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_jump_rel(struct cmdq_pkt *pkt, s32 offset, u8 shift_pa) { return -EINVAL; } -static inline int cmdq_pkt_flush_async(struct cmdq_pkt *pkt) +static inline int cmdq_pkt_eoc(struct cmdq_pkt *pkt) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) { return -EINVAL; } diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h index 29e06905bc1f..0f038a1a0330 100644 --- a/include/linux/soc/qcom/geni-se.h +++ b/include/linux/soc/qcom/geni-se.h @@ -178,6 +178,7 @@ struct geni_se { #define M_GP_IRQ_3_EN BIT(12) #define M_GP_IRQ_4_EN BIT(13) #define M_GP_IRQ_5_EN BIT(14) +#define M_TX_FIFO_NOT_EMPTY_EN BIT(21) #define M_IO_DATA_DEASSERT_EN BIT(22) #define M_IO_DATA_ASSERT_EN BIT(23) #define M_RX_FIFO_RD_ERR_EN BIT(24) diff --git a/include/linux/socket.h b/include/linux/socket.h index cfcb7e2c3813..139c330ccf2c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -422,13 +422,6 @@ extern long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags); -extern int sendmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct iovec **iov); -extern int recvmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct sockaddr __user **uaddr, - struct iovec **iov); extern int __copy_msghdr(struct msghdr *kmsg, struct user_msghdr *umsg, struct sockaddr __user **save_addr); diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 307961b41541..317200cd3a60 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -50,11 +50,36 @@ static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, return 0; } +/* Deprecated. + * This is unsafe, unless caller checked user provided optlen. + * Prefer copy_safe_from_sockptr() instead. + */ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) { return copy_from_sockptr_offset(dst, src, 0, size); } +/** + * copy_safe_from_sockptr: copy a struct from sockptr + * @dst: Destination address, in kernel space. This buffer must be @ksize + * bytes long. + * @ksize: Size of @dst struct. + * @optval: Source address. (in user or kernel space) + * @optlen: Size of @optval data. + * + * Returns: + * * -EINVAL: @optlen < @ksize + * * -EFAULT: access to userspace failed. + * * 0 : @ksize bytes were copied + */ +static inline int copy_safe_from_sockptr(void *dst, size_t ksize, + sockptr_t optval, unsigned int optlen) +{ + if (optlen < ksize) + return -EINVAL; + return copy_from_sockptr(dst, optval, ksize); +} + static inline int copy_struct_from_sockptr(void *dst, size_t ksize, sockptr_t src, size_t usize) { diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h index ceecad74aef9..28a4eb77717f 100644 --- a/include/linux/soundwire/sdw_amd.h +++ b/include/linux/soundwire/sdw_amd.h @@ -1,11 +1,12 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* - * Copyright (C) 2023 Advanced Micro Devices, Inc. All rights reserved. + * Copyright (C) 2023-24 Advanced Micro Devices, Inc. All rights reserved. */ #ifndef __SDW_AMD_H #define __SDW_AMD_H +#include <linux/acpi.h> #include <linux/soundwire/sdw.h> /* AMD pm_runtime quirk definitions */ @@ -25,6 +26,7 @@ #define AMD_SDW_POWER_OFF_MODE 2 #define ACP_SDW0 0 #define ACP_SDW1 1 +#define AMD_SDW_MAX_MANAGER_COUNT 2 struct acp_sdw_pdata { u16 instance; @@ -32,12 +34,6 @@ struct acp_sdw_pdata { 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 * @@ -59,10 +55,8 @@ struct sdw_amd_dai_runtime { * @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 @@ -83,10 +77,8 @@ struct amd_sdw_manager { 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; @@ -106,4 +98,71 @@ struct amd_sdw_manager { struct sdw_amd_dai_runtime **dai_runtime_array; }; + +/** + * struct sdw_amd_acpi_info - Soundwire AMD information found in ACPI tables + * @handle: ACPI controller handle + * @count: maximum no of soundwire manager links supported on AMD platform. + * @link_mask: bit-wise mask listing links enabled by BIOS menu + */ +struct sdw_amd_acpi_info { + acpi_handle handle; + int count; + u32 link_mask; +}; + +/** + * struct sdw_amd_ctx - context allocated by the controller driver probe + * + * @count: link count + * @num_slaves: total number of devices exposed across all enabled links + * @link_mask: bit-wise mask listing SoundWire links reported by the + * Controller + * @ids: array of slave_id, representing Slaves exposed across all enabled + * links + * @pdev: platform device structure + */ +struct sdw_amd_ctx { + int count; + int num_slaves; + u32 link_mask; + struct sdw_extended_slave_id *ids; + struct platform_device *pdev[AMD_SDW_MAX_MANAGER_COUNT]; +}; + +/** + * struct sdw_amd_res - Soundwire AMD global resource structure, + * typically populated by the DSP driver/Legacy driver + * + * @addr: acp pci device resource start address + * @reg_range: ACP register range + * @link_mask: bit-wise mask listing links selected by the DSP driver/ + * legacy driver + * @count: link count + * @mmio_base: mmio base of SoundWire registers + * @handle: ACPI parent handle + * @parent: parent device + * @dev: device implementing hwparams and free callbacks + * @acp_lock: mutex protecting acp common registers access + */ +struct sdw_amd_res { + u32 addr; + u32 reg_range; + u32 link_mask; + int count; + void __iomem *mmio_base; + acpi_handle handle; + struct device *parent; + struct device *dev; + /* use to protect acp common registers access */ + struct mutex *acp_lock; +}; + +int sdw_amd_probe(struct sdw_amd_res *res, struct sdw_amd_ctx **ctx); + +void sdw_amd_exit(struct sdw_amd_ctx *ctx); + +int sdw_amd_get_slave_info(struct sdw_amd_ctx *ctx); + +int amd_sdw_scan_controller(struct sdw_amd_acpi_info *info); #endif diff --git a/include/linux/soundwire/sdw_type.h b/include/linux/soundwire/sdw_type.h index d8c27f1e5559..693320b4f5c2 100644 --- a/include/linux/soundwire/sdw_type.h +++ b/include/linux/soundwire/sdw_type.h @@ -4,9 +4,9 @@ #ifndef __SOUNDWIRE_TYPES_H #define __SOUNDWIRE_TYPES_H -extern struct bus_type sdw_bus_type; -extern struct device_type sdw_slave_type; -extern struct device_type sdw_master_type; +extern const struct bus_type sdw_bus_type; +extern const struct device_type sdw_slave_type; +extern const struct device_type sdw_master_type; static inline int is_sdw_slave(const struct device *dev) { diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h deleted file mode 100644 index 0916cb9bcb0a..000000000000 --- a/include/linux/spi/pxa2xx_spi.h +++ /dev/null @@ -1,55 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2005 Stephen Street / StreetFire Sound Labs - */ -#ifndef __LINUX_SPI_PXA2XX_SPI_H -#define __LINUX_SPI_PXA2XX_SPI_H - -#include <linux/types.h> - -#include <linux/pxa2xx_ssp.h> - -struct dma_chan; - -/* - * The platform data for SSP controller devices - * (resides in device.platform_data). - */ -struct pxa2xx_spi_controller { - u16 num_chipselect; - u8 enable_dma; - u8 dma_burst_size; - bool is_target; - - /* DMA engine specific config */ - bool (*dma_filter)(struct dma_chan *chan, void *param); - void *tx_param; - void *rx_param; - - /* For non-PXA arches */ - struct ssp_device ssp; -}; - -/* - * The controller specific data for SPI target devices - * (resides in spi_board_info.controller_data), - * copied to spi_device.platform_data ... mostly for - * DMA tuning. - */ -struct pxa2xx_spi_chip { - u8 tx_threshold; - u8 tx_hi_threshold; - u8 rx_threshold; - u8 dma_burst_size; - u32 timeout; -}; - -#if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) - -#include <linux/clk.h> - -extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_controller *info); - -#endif - -#endif /* __LINUX_SPI_PXA2XX_SPI_H */ diff --git a/include/linux/spi/rspi.h b/include/linux/spi/rspi.h deleted file mode 100644 index dbdfcc7a3db2..000000000000 --- a/include/linux/spi/rspi.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Renesas SPI driver - * - * Copyright (C) 2012 Renesas Solutions Corp. - */ - -#ifndef __LINUX_SPI_RENESAS_SPI_H__ -#define __LINUX_SPI_RENESAS_SPI_H__ - -struct rspi_plat_data { - unsigned int dma_tx_id; - unsigned int dma_rx_id; - - u16 num_chipselect; -}; - -#endif diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 600fbd5daf68..e8e1e798924f 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -36,7 +36,7 @@ struct spi_message; * INTERFACES between SPI master-side drivers and SPI slave protocol handlers, * and SPI infrastructure. */ -extern struct bus_type spi_bus_type; +extern const struct bus_type spi_bus_type; /** * struct spi_statistics - statistics for spi transfers @@ -131,7 +131,6 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg, * struct spi_device - Controller side proxy for an SPI slave device * @dev: Driver model representation of the device. * @controller: SPI controller used with the device. - * @master: Copy of controller, for backwards compatibility. * @max_speed_hz: Maximum clock rate to be used with this chip * (on this board); may be changed by the device's driver. * The spi_transfer.speed_hz can override this for each transfer. @@ -185,7 +184,6 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg, struct spi_device { struct device dev; struct spi_controller *controller; - struct spi_controller *master; /* Compatibility layer */ u32 max_speed_hz; u8 chip_select[SPI_CS_CNT_MAX]; u8 bits_per_word; @@ -422,8 +420,6 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @bus_lock_spinlock: spinlock for SPI bus locking * @bus_lock_mutex: mutex for exclusion of multiple callers * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use - * @multi_cs_cap: indicates that the SPI Controller can assert/de-assert - * more than one chip select at once. * @setup: updates the device mode and clocking records used by a * device's SPI controller; protocol code may call this. This * must fail if an unrecognized or unsupported mode is requested. @@ -452,9 +448,12 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * the @cur_msg_completion. This flag is used to signal the context that * is running spi_finalize_current_message() that it needs to complete() * @cur_msg_mapped: message has been mapped for DMA + * @fallback: fallback to PIO if DMA transfer return failure with + * SPI_TRANS_FAIL_NO_START. + * @last_cs_mode_high: was (mode & SPI_CS_HIGH) true on the last call to set_cs. * @last_cs: the last chip_select that is recorded by set_cs, -1 on non chip * selected - * @last_cs_mode_high: was (mode & SPI_CS_HIGH) true on the last call to set_cs. + * @last_cs_index_mask: bit mask the last chip selects that were used * @xfer_completion: used by core transfer_one_message() * @busy: message pump is busy * @running: message pump is running @@ -477,6 +476,8 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * * @set_cs: set the logic level of the chip select line. May be called * from interrupt context. + * @optimize_message: optimize the message for reuse + * @unoptimize_message: release resources allocated by optimize_message * @prepare_message: set up the controller to transfer a single message, * for example doing DMA mapping. Called from threaded * context. @@ -529,8 +530,6 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * If the driver does not set this, the SPI core takes the snapshot as * close to the driver hand-over as possible. * @irq_flags: Interrupt enable state during PTP system timestamping - * @fallback: fallback to PIO if DMA transfer return failure with - * SPI_TRANS_FAIL_NO_START. * @queue_empty: signal green light for opportunistically skipping the queue * for spi_sync transfers. * @must_async: disable all fast paths in the core @@ -710,13 +709,15 @@ struct spi_controller { bool rt; bool auto_runtime_pm; bool cur_msg_mapped; - char last_cs[SPI_CS_CNT_MAX]; - char last_cs_index_mask; - bool last_cs_mode_high; bool fallback; + bool last_cs_mode_high; + s8 last_cs[SPI_CS_CNT_MAX]; + u32 last_cs_index_mask : SPI_CS_CNT_MAX; struct completion xfer_completion; size_t max_dma_len; + int (*optimize_message)(struct spi_message *msg); + int (*unoptimize_message)(struct spi_message *msg); int (*prepare_transfer_hardware)(struct spi_controller *ctlr); int (*transfer_one_message)(struct spi_controller *ctlr, struct spi_message *mesg); @@ -955,8 +956,8 @@ struct spi_res { * struct spi_transfer - a read/write buffer pair * @tx_buf: data to be written (DMA-safe memory), or NULL * @rx_buf: data to be read (DMA-safe memory), or NULL - * @tx_dma: DMA address of tx_buf, if @spi_message.is_dma_mapped - * @rx_dma: DMA address of rx_buf, if @spi_message.is_dma_mapped + * @tx_dma: DMA address of tx_buf, currently not for client use + * @rx_dma: DMA address of rx_buf, currently not for client use * @tx_nbits: number of bits used for writing. If 0 the default * (SPI_NBITS_SINGLE) is used. * @rx_nbits: number of bits used for reading. If 0 the default @@ -1066,8 +1067,7 @@ struct spi_transfer { /* * It's okay if tx_buf == rx_buf (right?). * For MicroWire, one buffer must be NULL. - * Buffers must work with dma_*map_single() calls, unless - * spi_message.is_dma_mapped reports a pre-existing mapping. + * Buffers must work with dma_*map_single() calls. */ const void *tx_buf; void *rx_buf; @@ -1111,18 +1111,19 @@ struct spi_transfer { * struct spi_message - one multi-segment SPI transaction * @transfers: list of transfer segments in this transaction * @spi: SPI device to which the transaction is queued - * @is_dma_mapped: if true, the caller provided both DMA and CPU virtual - * addresses for each transfer buffer + * @pre_optimized: peripheral driver pre-optimized the message + * @optimized: the message is in the optimized state + * @prepared: spi_prepare_message was called for the this message + * @status: zero for success, else negative errno * @complete: called to report transaction completions * @context: the argument to complete() when it's called * @frame_length: the total number of bytes in the message * @actual_length: the total number of bytes that were transferred in all * successful segments - * @status: zero for success, else negative errno * @queue: for use by whichever driver currently owns the message * @state: for use by whichever driver currently owns the message + * @opt_state: for use by whichever driver currently owns the message * @resources: for resource management when the SPI message is processed - * @prepared: spi_prepare_message was called for the this message * * A @spi_message is used to execute an atomic sequence of data transfers, * each represented by a struct spi_transfer. The sequence is "atomic" @@ -1143,7 +1144,10 @@ struct spi_message { struct spi_device *spi; - unsigned is_dma_mapped:1; + /* spi_optimize_message() was called for this message */ + bool pre_optimized; + /* __spi_optimize_message() was called for this message */ + bool optimized; /* spi_prepare_message() was called for this message */ bool prepared; @@ -1174,6 +1178,11 @@ struct spi_message { */ struct list_head queue; void *state; + /* + * Optional state for use by controller driver between calls to + * __spi_optimize_message() and __spi_unoptimize_message(). + */ + void *opt_state; /* List of spi_res resources when the SPI message is processed */ struct list_head resources; @@ -1257,6 +1266,9 @@ static inline void spi_message_free(struct spi_message *m) kfree(m); } +extern int spi_optimize_message(struct spi_device *spi, struct spi_message *msg); +extern void spi_unoptimize_message(struct spi_message *msg); + extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); extern int spi_slave_abort(struct spi_device *spi); @@ -1298,7 +1310,7 @@ spi_max_transfer_size(struct spi_device *spi) */ static inline bool spi_is_bpw_supported(struct spi_device *spi, u32 bpw) { - u32 bpw_mask = spi->master->bits_per_word_mask; + u32 bpw_mask = spi->controller->bits_per_word_mask; if (bpw == 8 || (bpw <= 32 && bpw_mask & SPI_BPW_MASK(bpw))) return true; @@ -1365,12 +1377,10 @@ struct spi_replaced_transfers { extern int spi_split_transfers_maxsize(struct spi_controller *ctlr, struct spi_message *msg, - size_t maxsize, - gfp_t gfp); + size_t maxsize); extern int spi_split_transfers_maxwords(struct spi_controller *ctlr, struct spi_message *msg, - size_t maxwords, - gfp_t gfp); + size_t maxwords); /*---------------------------------------------------------------------------*/ @@ -1670,20 +1680,4 @@ spi_transfer_is_last(struct spi_controller *ctlr, struct spi_transfer *xfer) return list_is_last(&xfer->transfer_list, &ctlr->cur_msg->transfers); } -/* Compatibility layer */ -#define spi_master spi_controller - -#define spi_master_get_devdata(_ctlr) spi_controller_get_devdata(_ctlr) -#define spi_master_set_devdata(_ctlr, _data) \ - spi_controller_set_devdata(_ctlr, _data) -#define spi_master_get(_ctlr) spi_controller_get(_ctlr) -#define spi_master_put(_ctlr) spi_controller_put(_ctlr) -#define spi_master_suspend(_ctlr) spi_controller_suspend(_ctlr) -#define spi_master_resume(_ctlr) spi_controller_resume(_ctlr) - -#define spi_register_master(_ctlr) spi_register_controller(_ctlr) -#define devm_spi_register_master(_dev, _ctlr) \ - devm_spi_register_controller(_dev, _ctlr) -#define spi_unregister_master(_ctlr) spi_unregister_controller(_ctlr) - #endif /* __LINUX_SPI_H */ diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index 4444c2a992cb..b930eca2ef7b 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -10,7 +10,7 @@ struct spi_bitbang { u8 use_dma; u16 flags; /* extra spi->mode support */ - struct spi_master *master; + struct spi_controller *ctlr; /* setup_transfer() changes clock and/or wordsize to match settings * for this transfer; zeroes restore defaults from spi_device. diff --git a/include/linux/spi/spi_gpio.h b/include/linux/spi/spi_gpio.h index 9e7e83d8645b..5f0e1407917a 100644 --- a/include/linux/spi/spi_gpio.h +++ b/include/linux/spi/spi_gpio.h @@ -15,8 +15,8 @@ */ /** - * struct spi_gpio_platform_data - parameter for bitbanged SPI master - * @num_chipselect: how many slaves to allow + * struct spi_gpio_platform_data - parameter for bitbanged SPI host controller + * @num_chipselect: how many target devices to allow */ struct spi_gpio_platform_data { u16 num_chipselect; diff --git a/include/linux/spi/xilinx_spi.h b/include/linux/spi/xilinx_spi.h index 3934ce789d87..1b8d984668b6 100644 --- a/include/linux/spi/xilinx_spi.h +++ b/include/linux/spi/xilinx_spi.h @@ -2,19 +2,23 @@ #ifndef __LINUX_SPI_XILINX_SPI_H #define __LINUX_SPI_XILINX_SPI_H +#include <linux/types.h> + +struct spi_board_info; + /** * struct xspi_platform_data - Platform data of the Xilinx SPI driver - * @num_chipselect: Number of chip select by the IP. - * @little_endian: If registers should be accessed little endian or not. - * @bits_per_word: Number of bits per word. * @devices: Devices to add when the driver is probed. * @num_devices: Number of devices in the devices array. + * @num_chipselect: Number of chip select by the IP. + * @bits_per_word: Number of bits per word. + * @force_irq: If set, forces QSPI transaction requirements. */ struct xspi_platform_data { - u16 num_chipselect; - u8 bits_per_word; struct spi_board_info *devices; u8 num_devices; + u8 num_chipselect; + u8 bits_per_word; bool force_irq; }; diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 447133171d95..4d96bbdb45f0 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -64,8 +64,10 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp) { int idx; + preempt_disable(); // Needed for PREEMPT_AUTO idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; WRITE_ONCE(ssp->srcu_lock_nesting[idx], READ_ONCE(ssp->srcu_lock_nesting[idx]) + 1); + preempt_enable(); return idx; } diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 1f326da289d3..a2257380c3f1 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -621,14 +621,6 @@ extern u32 ssb_dma_translation(struct ssb_device *dev); #define SSB_DMA_TRANSLATION_MASK 0xC0000000 #define SSB_DMA_TRANSLATION_SHIFT 30 -static inline void __cold __ssb_dma_not_implemented(struct ssb_device *dev) -{ -#ifdef CONFIG_SSB_DEBUG - printk(KERN_ERR "SSB: BUG! Calling DMA API for " - "unsupported bustype %d\n", dev->bus->bustype); -#endif /* DEBUG */ -} - #ifdef CONFIG_SSB_PCIHOST /* PCI-host wrapper driver */ extern int ssb_pcihost_register(struct pci_driver *driver); diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index adcbb8f23600..e9ec32fb97d4 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -30,6 +30,52 @@ typedef u32 depot_stack_handle_t; */ #define STACK_DEPOT_EXTRA_BITS 5 +#define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8) + +#define DEPOT_POOL_ORDER 2 /* Pool size order, 4 pages */ +#define DEPOT_POOL_SIZE (1LL << (PAGE_SHIFT + DEPOT_POOL_ORDER)) +#define DEPOT_STACK_ALIGN 4 +#define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN) +#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \ + STACK_DEPOT_EXTRA_BITS) + +#ifdef CONFIG_STACKDEPOT +/* Compact structure that stores a reference to a stack. */ +union handle_parts { + depot_stack_handle_t handle; + struct { + u32 pool_index_plus_1 : DEPOT_POOL_INDEX_BITS; + u32 offset : DEPOT_OFFSET_BITS; + u32 extra : STACK_DEPOT_EXTRA_BITS; + }; +}; + +struct stack_record { + struct list_head hash_list; /* Links in the hash table */ + u32 hash; /* Hash in hash table */ + u32 size; /* Number of stored frames */ + union handle_parts handle; /* Constant after initialization */ + refcount_t count; + union { + unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES]; /* Frames */ + struct { + /* + * An important invariant of the implementation is to + * only place a stack record onto the freelist iff its + * refcount is zero. Because stack records with a zero + * refcount are never considered as valid, it is safe to + * union @entries and freelist management state below. + * Conversely, as soon as an entry is off the freelist + * and its refcount becomes non-zero, the below must not + * be accessed until being placed back on the freelist. + */ + struct list_head free_list; /* Links in the freelist */ + unsigned long rcu_state; /* RCU cookie */ + }; + }; +}; +#endif + typedef u32 depot_flags_t; /* @@ -132,6 +178,17 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); /** + * __stack_depot_get_stack_record - Get a pointer to a stack_record struct + * + * @handle: Stack depot handle + * + * This function is only for internal purposes. + * + * Return: Returns a pointer to a stack_record struct + */ +struct stack_record *__stack_depot_get_stack_record(depot_stack_handle_t handle); + +/** * stack_depot_fetch - Fetch a stack trace from stack depot * * @handle: Stack depot handle returned from stack_depot_save() diff --git a/include/linux/start_kernel.h b/include/linux/start_kernel.h index a9806a44a605..09f994ac87df 100644 --- a/include/linux/start_kernel.h +++ b/include/linux/start_kernel.h @@ -9,7 +9,5 @@ up something else. */ 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/stat.h b/include/linux/stat.h index 52150570d37a..bf92441dbad2 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -53,6 +53,7 @@ struct kstat { u32 dio_mem_align; u32 dio_offset_align; u64 change_cookie; + u64 subvol; }; /* These definitions are internal to the kernel for now. Mainly used by nfsd. */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dfa1828cd756..f92c195c76ed 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -115,21 +115,6 @@ struct stmmac_axi { bool axi_rb; }; -#define EST_GCL 1024 -struct stmmac_est { - struct mutex lock; - int enable; - u32 btr_reserve[2]; - u32 btr_offset[2]; - u32 btr[2]; - u32 ctr[2]; - u32 ter; - u32 gcl_unaligned[EST_GCL]; - u32 gcl[EST_GCL]; - u32 gcl_size; - u32 max_sdu[MTL_MAX_TX_QUEUES]; -}; - struct stmmac_rxq_cfg { u8 mode_to_use; u32 chan; @@ -246,7 +231,6 @@ struct plat_stmmacenet_data { struct fwnode_handle *port_node; struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; - struct stmmac_est *est; struct stmmac_fpe_cfg *fpe_cfg; struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; @@ -285,6 +269,8 @@ struct plat_stmmacenet_data { int (*crosststamp)(ktime_t *device, struct system_counterval_t *system, void *ctx); void (*dump_debug_regs)(void *priv); + int (*pcs_init)(struct stmmac_priv *priv); + void (*pcs_exit)(struct stmmac_priv *priv); void *bsp_priv; struct clk *stmmac_clk; struct clk *pclk; diff --git a/include/linux/string.h b/include/linux/string.h index 9ba8b4597009..10e5177bb49c 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -14,8 +14,8 @@ #include <uapi/linux/string.h> extern char *strndup_user(const char __user *, long); -extern void *memdup_user(const void __user *, size_t); -extern void *vmemdup_user(const void __user *, size_t); +extern void *memdup_user(const void __user *, size_t) __realloc_size(2); +extern void *vmemdup_user(const void __user *, size_t) __realloc_size(2); extern void *memdup_user_nul(const void __user *, size_t); /** @@ -27,7 +27,8 @@ extern void *memdup_user_nul(const void __user *, size_t); * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ -static inline void *memdup_array_user(const void __user *src, size_t n, size_t size) +static inline __realloc_size(2, 3) +void *memdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; @@ -46,7 +47,8 @@ static inline void *memdup_array_user(const void __user *src, size_t n, size_t s * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ -static inline void *vmemdup_array_user(const void __user *src, size_t n, size_t size) +static inline __realloc_size(2, 3) +void *vmemdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; @@ -285,7 +287,8 @@ extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern void *kvmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); -extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp); +extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp) + __realloc_size(2, 3); /* lib/argv_split.c */ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); @@ -423,6 +426,55 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, } while (0) /** + * memtostr - Copy a possibly non-NUL-term string to a NUL-term string + * @dest: Pointer to destination NUL-terminates string + * @src: Pointer to character array (likely marked as __nonstring) + * + * This is a replacement for strncpy() uses where the source is not + * a NUL-terminated string. + * + * Note that sizes of @dest and @src must be known at compile-time. + */ +#define memtostr(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_chars = strnlen(src, _src_len); \ + const size_t _copy_len = min(_dest_len - 1, _src_chars); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + !__builtin_constant_p(_src_len) || \ + _dest_len == 0 || _dest_len == (size_t)-1 || \ + _src_len == 0 || _src_len == (size_t)-1); \ + memcpy(dest, src, _copy_len); \ + dest[_copy_len] = '\0'; \ +} while (0) + +/** + * memtostr_pad - Copy a possibly non-NUL-term string to a NUL-term string + * with NUL padding in the destination + * @dest: Pointer to destination NUL-terminates string + * @src: Pointer to character array (likely marked as __nonstring) + * + * This is a replacement for strncpy() uses where the source is not + * a NUL-terminated string. + * + * Note that sizes of @dest and @src must be known at compile-time. + */ +#define memtostr_pad(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_chars = strnlen(src, _src_len); \ + const size_t _copy_len = min(_dest_len - 1, _src_chars); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + !__builtin_constant_p(_src_len) || \ + _dest_len == 0 || _dest_len == (size_t)-1 || \ + _src_len == 0 || _src_len == (size_t)-1); \ + memcpy(dest, src, _copy_len); \ + memset(&dest[_copy_len], 0, _dest_len - _copy_len); \ +} while (0) + +/** * memset_after - Set a value after a struct member to the end of a struct * * @obj: Address of target struct instance diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 5e9d1469c6fa..5321585c778f 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -139,6 +139,7 @@ struct rpc_create_args { const char *servername; const char *nodename; const struct rpc_program *program; + struct rpc_stat *stats; u32 prognumber; /* overrides program->number */ u32 version; rpc_authflavor_t authflavor; diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 2d61987b3545..0c77ba488bba 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -197,7 +197,7 @@ struct rpc_wait_queue { unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */ unsigned char priority; /* current priority */ unsigned char nr; /* # tasks remaining for cookie */ - unsigned short qlen; /* total # tasks waiting in queue */ + unsigned int qlen; /* total # tasks waiting in queue */ struct rpc_timer timer_list; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) const char * name; diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24cd199dd6f3..d33bab33099a 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -210,7 +210,6 @@ struct svc_rdma_recv_ctxt { */ struct svc_rdma_write_info { struct svcxprt_rdma *wi_rdma; - struct list_head wi_list; const struct svc_rdma_chunk *wi_chunk; @@ -239,10 +238,7 @@ struct svc_rdma_send_ctxt { struct ib_cqe sc_cqe; struct xdr_buf sc_hdrbuf; struct xdr_stream sc_stream; - - struct list_head sc_write_info_list; struct svc_rdma_write_info sc_reply_info; - void *sc_xprt_buf; int sc_page_count; int sc_cur_sge_no; @@ -274,14 +270,11 @@ extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma, extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma, struct svc_rdma_chunk_ctxt *cc, enum dma_data_direction dir); -extern void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma, - struct svc_rdma_send_ctxt *ctxt); extern void svc_rdma_reply_chunk_release(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt); -extern int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma, - const struct svc_rdma_pcl *write_pcl, - struct svc_rdma_send_ctxt *sctxt, - const struct xdr_buf *xdr); +extern int svc_rdma_send_write_list(struct svcxprt_rdma *rdma, + const struct svc_rdma_recv_ctxt *rctxt, + const struct xdr_buf *xdr); extern int svc_rdma_prepare_reply_chunk(struct svcxprt_rdma *rdma, const struct svc_rdma_pcl *write_pcl, const struct svc_rdma_pcl *reply_pcl, diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 464f6a9492ab..81b952649d35 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -152,6 +152,7 @@ struct rpc_xprt_ops { int (*prepare_request)(struct rpc_rqst *req, struct xdr_buf *buf); int (*send_request)(struct rpc_rqst *req); + void (*abort_send_request)(struct rpc_rqst *req); void (*wait_for_reply_request)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); void (*release_request)(struct rpc_task *task); diff --git a/include/linux/suspend.h b/include/linux/suspend.h index ef503088942d..da6ebca3ff77 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -40,65 +40,6 @@ typedef int __bitwise suspend_state_t; #define PM_SUSPEND_MIN PM_SUSPEND_TO_IDLE #define PM_SUSPEND_MAX ((__force suspend_state_t) 4) -enum suspend_stat_step { - SUSPEND_FREEZE = 1, - SUSPEND_PREPARE, - SUSPEND_SUSPEND, - SUSPEND_SUSPEND_LATE, - SUSPEND_SUSPEND_NOIRQ, - SUSPEND_RESUME_NOIRQ, - SUSPEND_RESUME_EARLY, - SUSPEND_RESUME -}; - -struct suspend_stats { - int success; - int fail; - int failed_freeze; - int failed_prepare; - int failed_suspend; - int failed_suspend_late; - int failed_suspend_noirq; - int failed_resume; - int failed_resume_early; - int failed_resume_noirq; -#define REC_FAILED_NUM 2 - int last_failed_dev; - char failed_devs[REC_FAILED_NUM][40]; - 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]; -}; - -extern struct suspend_stats suspend_stats; - -static inline void dpm_save_failed_dev(const char *name) -{ - strscpy(suspend_stats.failed_devs[suspend_stats.last_failed_dev], - name, - sizeof(suspend_stats.failed_devs[0])); - suspend_stats.last_failed_dev++; - suspend_stats.last_failed_dev %= REC_FAILED_NUM; -} - -static inline void dpm_save_failed_errno(int err) -{ - suspend_stats.errno[suspend_stats.last_failed_errno] = err; - suspend_stats.last_failed_errno++; - suspend_stats.last_failed_errno %= REC_FAILED_NUM; -} - -static inline void dpm_save_failed_step(enum suspend_stat_step step) -{ - suspend_stats.failed_steps[suspend_stats.last_failed_step] = step; - suspend_stats.last_failed_step++; - suspend_stats.last_failed_step %= REC_FAILED_NUM; -} - /** * struct platform_suspend_ops - Callbacks for managing platform dependent * system sleep states. @@ -626,4 +567,19 @@ static inline void queue_up_suspend_work(void) {} #endif /* !CONFIG_PM_AUTOSLEEP */ +enum suspend_stat_step { + SUSPEND_WORKING = 0, + SUSPEND_FREEZE, + SUSPEND_PREPARE, + SUSPEND_SUSPEND, + SUSPEND_SUSPEND_LATE, + SUSPEND_SUSPEND_NOIRQ, + SUSPEND_RESUME_NOIRQ, + SUSPEND_RESUME_EARLY, + SUSPEND_RESUME +}; + +void dpm_save_failed_dev(const char *name); +void dpm_save_failed_step(enum suspend_stat_step step); + #endif /* _LINUX_SUSPEND_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 378ab1cd23bd..f53d608daa01 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -350,16 +350,6 @@ void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); -/* Only track the nodes of mappings with shadow entries */ -void workingset_update_node(struct xa_node *node); -extern struct list_lru shadow_nodes; -#define mapping_set_update(xas, mapping) do { \ - if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ - xas_set_update(xas, workingset_update_node); \ - xas_set_lru(xas, &shadow_nodes); \ - } \ -} while (0) - /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; @@ -447,9 +437,9 @@ static inline unsigned long total_swapcache_pages(void) return global_node_page_state(NR_SWAPCACHE); } -extern void free_swap_cache(struct page *page); -extern void free_page_and_swap_cache(struct page *); -extern void free_pages_and_swap_cache(struct encoded_page **, int); +void free_swap_cache(struct folio *folio); +void free_page_and_swap_cache(struct page *); +void free_pages_and_swap_cache(struct encoded_page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; @@ -531,7 +521,7 @@ static inline void put_swap_device(struct swap_info_struct *si) /* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ #define free_swap_and_cache(e) is_pfn_swap_entry(e) -static inline void free_swap_cache(struct page *page) +static inline void free_swap_cache(struct folio *folio) { } diff --git a/include/linux/swapops.h b/include/linux/swapops.h index bff1e8d97de0..a5c560a2f8c2 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -390,6 +390,35 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) } #endif /* CONFIG_MIGRATION */ +#ifdef CONFIG_MEMORY_FAILURE + +/* + * Support for hardware poisoned pages + */ +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + BUG_ON(!PageLocked(page)); + return swp_entry(SWP_HWPOISON, page_to_pfn(page)); +} + +static inline int is_hwpoison_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_HWPOISON; +} + +#else + +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + return swp_entry(0, 0); +} + +static inline int is_hwpoison_entry(swp_entry_t swp) +{ + return 0; +} +#endif + typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) @@ -468,10 +497,24 @@ static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) return p; } +static inline struct folio *pfn_swap_entry_folio(swp_entry_t entry) +{ + struct folio *folio = pfn_folio(swp_offset_pfn(entry)); + + /* + * Any use of migration entries may only occur while the + * corresponding folio is locked + */ + BUG_ON(is_migration_entry(entry) && !folio_test_locked(folio)); + + return folio; +} + /* * A pfn swap entry is a special type of swap entry that always has a pfn stored - * in the swap offset. They are used to represent unaddressable device memory - * and to restrict access to a page undergoing migration. + * in the swap offset. They can either be used to represent unaddressable device + * memory, to restrict access to a page undergoing migration or to represent a + * pfn which has been hwpoisoned and unmapped. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { @@ -479,7 +522,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); return is_migration_entry(entry) || is_device_private_entry(entry) || - is_device_exclusive_entry(entry); + is_device_exclusive_entry(entry) || is_hwpoison_entry(entry); } struct page_vma_mapped_walk; @@ -548,35 +591,6 @@ static inline int is_pmd_migration_entry(pmd_t pmd) } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ -#ifdef CONFIG_MEMORY_FAILURE - -/* - * Support for hardware poisoned pages - */ -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - BUG_ON(!PageLocked(page)); - return swp_entry(SWP_HWPOISON, page_to_pfn(page)); -} - -static inline int is_hwpoison_entry(swp_entry_t entry) -{ - return swp_type(entry) == SWP_HWPOISON; -} - -#else - -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - return swp_entry(0, 0); -} - -static inline int is_hwpoison_entry(swp_entry_t swp) -{ - return 0; -} -#endif - static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index ecde0312dd52..ea23097e351f 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -120,6 +120,8 @@ struct io_tlb_pool { * debugfs. * @used_hiwater: The high water mark for total_used. Used only for reporting * in debugfs. + * @transient_nslabs: The total number of slots in all transient pools that + * are currently used across all areas. */ struct io_tlb_mem { struct io_tlb_pool defpool; @@ -137,6 +139,7 @@ struct io_tlb_mem { #ifdef CONFIG_DEBUG_FS atomic_long_t total_used; atomic_long_t used_hiwater; + atomic_long_t transient_nslabs; #endif }; diff --git a/include/linux/sync_core.h b/include/linux/sync_core.h index 013da4b8b327..67bb9794b875 100644 --- a/include/linux/sync_core.h +++ b/include/linux/sync_core.h @@ -17,5 +17,19 @@ static inline void sync_core_before_usermode(void) } #endif -#endif /* _LINUX_SYNC_CORE_H */ +#ifdef CONFIG_ARCH_HAS_PREPARE_SYNC_CORE_CMD +#include <asm/sync_core.h> +#else +/* + * This is a dummy prepare_sync_core_cmd() implementation that can be used on + * all architectures which provide unconditional core serializing instructions + * in switch_mm(). + * If your architecture doesn't provide such core serializing instructions in + * switch_mm(), you may need to write your own functions. + */ +static inline void prepare_sync_core_cmd(struct mm_struct *mm) +{ +} +#endif +#endif /* _LINUX_SYNC_CORE_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 77eb9b0e7685..e619ac10cd23 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -960,10 +960,10 @@ asmlinkage long sys_cachestat(unsigned int fd, struct cachestat __user *cstat, unsigned int flags); asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags); asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx, - size_t *size, __u32 flags); + u32 *size, u32 flags); asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx *ctx, - size_t size, __u32 flags); -asmlinkage long sys_lsm_list_modules(u64 *ids, size_t *size, u32 flags); + u32 size, u32 flags); +asmlinkage long sys_lsm_list_modules(u64 *ids, u32 *size, u32 flags); /* * Architecture-specific system calls diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index ee7d33b89e9e..9413241df962 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -182,7 +182,7 @@ struct ctl_table_header { struct rcu_head rcu; }; struct completion *unregistering; - struct ctl_table *ctl_table_arg; + const struct ctl_table *ctl_table_arg; struct ctl_table_root *root; struct ctl_table_set *set; struct ctl_dir *parent; diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index 19cb803dd5ec..c9cb657dad08 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -91,7 +91,8 @@ static inline void sysfb_set_efifb_fwnode(struct platform_device *pd) bool sysfb_parse_mode(const struct screen_info *si, struct simplefb_platform_data *mode); struct platform_device *sysfb_create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode); + const struct simplefb_platform_data *mode, + struct device *parent); #else /* CONFIG_SYSFB_SIMPLE */ @@ -102,7 +103,8 @@ static inline bool sysfb_parse_mode(const struct screen_info *si, } static inline struct platform_device *sysfb_create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode) + const struct simplefb_platform_data *mode, + struct device *parent) { return ERR_PTR(-EINVAL); } diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index b717a70219f6..326341c62385 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -61,22 +61,32 @@ do { \ /** * struct attribute_group - data structure used to declare an attribute group. * @name: Optional: Attribute group name - * If specified, the attribute group will be created in - * a new subdirectory with this name. + * If specified, the attribute group will be created in a + * new subdirectory with this name. Additionally when a + * group is named, @is_visible and @is_bin_visible may + * return SYSFS_GROUP_INVISIBLE to control visibility of + * the directory itself. * @is_visible: Optional: Function to return permissions associated with an - * attribute of the group. Will be called repeatedly for each - * non-binary attribute in the group. Only read/write + * attribute of the group. Will be called repeatedly for + * each non-binary attribute in the group. Only read/write * permissions as well as SYSFS_PREALLOC are accepted. Must - * return 0 if an attribute is not visible. The returned value - * will replace static permissions defined in struct attribute. + * return 0 if an attribute is not visible. The returned + * value will replace static permissions defined in struct + * attribute. Use SYSFS_GROUP_VISIBLE() when assigning this + * callback to specify separate _group_visible() and + * _attr_visible() handlers. * @is_bin_visible: * Optional: Function to return permissions associated with a * binary attribute of the group. Will be called repeatedly * for each binary attribute in the group. Only read/write - * permissions as well as SYSFS_PREALLOC are accepted. Must - * return 0 if a binary attribute is not visible. The returned - * value will replace static permissions defined in - * struct bin_attribute. + * permissions as well as SYSFS_PREALLOC (and the + * visibility flags for named groups) are accepted. Must + * return 0 if a binary attribute is not visible. The + * returned value will replace static permissions defined + * in struct bin_attribute. If @is_visible is not set, Use + * SYSFS_GROUP_VISIBLE() when assigning this callback to + * specify separate _group_visible() and _attr_visible() + * handlers. * @attrs: Pointer to NULL terminated list of attributes. * @bin_attrs: Pointer to NULL terminated list of binary attributes. * Either attrs or bin_attrs or both must be provided. @@ -91,13 +101,121 @@ struct attribute_group { struct bin_attribute **bin_attrs; }; +#define SYSFS_PREALLOC 010000 +#define SYSFS_GROUP_INVISIBLE 020000 + +/* + * DEFINE_SYSFS_GROUP_VISIBLE(name): + * A helper macro to pair with the assignment of ".is_visible = + * SYSFS_GROUP_VISIBLE(name)", that arranges for the directory + * associated with a named attribute_group to optionally be hidden. + * This allows for static declaration of attribute_groups, and the + * simplification of attribute visibility lifetime that implies, + * without polluting sysfs with empty attribute directories. + * Ex. + * + * static umode_t example_attr_visible(struct kobject *kobj, + * struct attribute *attr, int n) + * { + * if (example_attr_condition) + * return 0; + * else if (ro_attr_condition) + * return 0444; + * return a->mode; + * } + * + * static bool example_group_visible(struct kobject *kobj) + * { + * if (example_group_condition) + * return false; + * return true; + * } + * + * DEFINE_SYSFS_GROUP_VISIBLE(example); + * + * static struct attribute_group example_group = { + * .name = "example", + * .is_visible = SYSFS_GROUP_VISIBLE(example), + * .attrs = &example_attrs, + * }; + * + * Note that it expects <name>_attr_visible and <name>_group_visible to + * be defined. For cases where individual attributes do not need + * separate visibility consideration, only entire group visibility at + * once, see DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE(). + */ +#define DEFINE_SYSFS_GROUP_VISIBLE(name) \ + static inline umode_t sysfs_group_visible_##name( \ + struct kobject *kobj, struct attribute *attr, int n) \ + { \ + if (n == 0 && !name##_group_visible(kobj)) \ + return SYSFS_GROUP_INVISIBLE; \ + return name##_attr_visible(kobj, attr, n); \ + } + +/* + * DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE(name): + * A helper macro to pair with SYSFS_GROUP_VISIBLE() that like + * DEFINE_SYSFS_GROUP_VISIBLE() controls group visibility, but does + * not require the implementation of a per-attribute visibility + * callback. + * Ex. + * + * static bool example_group_visible(struct kobject *kobj) + * { + * if (example_group_condition) + * return false; + * return true; + * } + * + * DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE(example); + * + * static struct attribute_group example_group = { + * .name = "example", + * .is_visible = SYSFS_GROUP_VISIBLE(example), + * .attrs = &example_attrs, + * }; + */ +#define DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE(name) \ + static inline umode_t sysfs_group_visible_##name( \ + struct kobject *kobj, struct attribute *a, int n) \ + { \ + if (n == 0 && !name##_group_visible(kobj)) \ + return SYSFS_GROUP_INVISIBLE; \ + return a->mode; \ + } + +/* + * Same as DEFINE_SYSFS_GROUP_VISIBLE, but for groups with only binary + * attributes. If an attribute_group defines both text and binary + * attributes, the group visibility is determined by the function + * specified to is_visible() not is_bin_visible() + */ +#define DEFINE_SYSFS_BIN_GROUP_VISIBLE(name) \ + static inline umode_t sysfs_group_visible_##name( \ + struct kobject *kobj, struct bin_attribute *attr, int n) \ + { \ + if (n == 0 && !name##_group_visible(kobj)) \ + return SYSFS_GROUP_INVISIBLE; \ + return name##_attr_visible(kobj, attr, n); \ + } + +#define DEFINE_SIMPLE_SYSFS_BIN_GROUP_VISIBLE(name) \ + static inline umode_t sysfs_group_visible_##name( \ + struct kobject *kobj, struct bin_attribute *a, int n) \ + { \ + if (n == 0 && !name##_group_visible(kobj)) \ + return SYSFS_GROUP_INVISIBLE; \ + return a->mode; \ + } + +#define SYSFS_GROUP_VISIBLE(fn) sysfs_group_visible_##fn + /* * Use these macros to make defining attributes easier. * See include/linux/device.h for examples.. */ -#define SYSFS_PREALLOC 010000 - #define __ATTR(_name, _mode, _show, _store) { \ .attr = {.name = __stringify(_name), \ .mode = VERIFY_OCTAL_PERMISSIONS(_mode) }, \ diff --git a/include/linux/tc.h b/include/linux/tc.h index a60639f37963..1638660abf5e 100644 --- a/include/linux/tc.h +++ b/include/linux/tc.h @@ -120,7 +120,7 @@ static inline unsigned long tc_get_speed(struct tc_bus *tbus) #ifdef CONFIG_TC -extern struct bus_type tc_bus_type; +extern const struct bus_type tc_bus_type; extern int tc_register_driver(struct tc_driver *tdrv); extern void tc_unregister_driver(struct tc_driver *tdrv); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 55399ee2a57e..6a5e08b937b3 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -244,6 +244,7 @@ struct tcp_sock { /* OOO segments go in this rbtree. Socket lock must be held. */ struct rb_root out_of_order_queue; u32 snd_ssthresh; /* Slow start size threshold */ + u8 recvmsg_inq : 1;/* Indicate # of bytes in queue upon recvmsg */ __cacheline_group_end(tcp_sock_read_rx); /* TX read-write hotpath cache lines */ @@ -266,8 +267,6 @@ struct tcp_sock { u32 mdev_us; /* medium deviation */ u32 rtt_seq; /* sequence number to update rttvar */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ - u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ - u64 tcp_mstamp; /* most recent packet received/sent */ struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ struct sk_buff *highest_sack; /* skb just after the highest * skb with SACKed bit set @@ -284,6 +283,8 @@ struct tcp_sock { * 0x5?10 << 16 + snd_wnd in net byte order */ __be32 pred_flags; + u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ + u64 tcp_mstamp; /* most recent packet received/sent */ u32 rcv_nxt; /* What we want to receive next */ u32 snd_nxt; /* Next sequence we send */ u32 snd_una; /* First byte we want an ack for */ @@ -370,7 +371,6 @@ struct tcp_sock { tlp_retrans:1, /* TLP is a retransmission */ unused:5; u8 thin_lto : 1,/* Use linear timeouts for thin streams */ - recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ fastopen_client_fail:2, /* reason why fastopen failed */ diff --git a/include/linux/tee_core.h b/include/linux/tee_core.h new file mode 100644 index 000000000000..efd16ed52315 --- /dev/null +++ b/include/linux/tee_core.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Linaro Limited + */ + +#ifndef __TEE_CORE_H +#define __TEE_CORE_H + +#include <linux/cdev.h> +#include <linux/device.h> +#include <linux/idr.h> +#include <linux/kref.h> +#include <linux/list.h> +#include <linux/tee.h> +#include <linux/tee_drv.h> +#include <linux/types.h> +#include <linux/uuid.h> + +/* + * The file describes the API provided by the generic TEE driver to the + * specific TEE driver. + */ + +#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ + /* in secure world */ +#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ +#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ +#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ + +#define TEE_DEVICE_FLAG_REGISTERED 0x1 +#define TEE_MAX_DEV_NAME_LEN 32 + +/** + * struct tee_device - TEE Device representation + * @name: name of device + * @desc: description of device + * @id: unique id of device + * @flags: represented by TEE_DEVICE_FLAG_REGISTERED above + * @dev: embedded basic device structure + * @cdev: embedded cdev + * @num_users: number of active users of this device + * @c_no_user: completion used when unregistering the device + * @mutex: mutex protecting @num_users and @idr + * @idr: register of user space shared memory objects allocated or + * registered on this device + * @pool: shared memory pool + */ +struct tee_device { + char name[TEE_MAX_DEV_NAME_LEN]; + const struct tee_desc *desc; + int id; + unsigned int flags; + + struct device dev; + struct cdev cdev; + + size_t num_users; + struct completion c_no_users; + struct mutex mutex; /* protects num_users and idr */ + + struct idr idr; + struct tee_shm_pool *pool; +}; + +/** + * struct tee_driver_ops - driver operations vtable + * @get_version: returns version of driver + * @open: called when the device file is opened + * @release: release this open file + * @open_session: open a new session + * @close_session: close a session + * @system_session: declare session as a system session + * @invoke_func: invoke a trusted function + * @cancel_req: request cancel of an ongoing invoke or open + * @supp_recv: called for supplicant to get a command + * @supp_send: called for supplicant to send a response + * @shm_register: register shared memory buffer in TEE + * @shm_unregister: unregister shared memory buffer in TEE + */ +struct tee_driver_ops { + void (*get_version)(struct tee_device *teedev, + struct tee_ioctl_version_data *vers); + int (*open)(struct tee_context *ctx); + void (*release)(struct tee_context *ctx); + int (*open_session)(struct tee_context *ctx, + struct tee_ioctl_open_session_arg *arg, + struct tee_param *param); + int (*close_session)(struct tee_context *ctx, u32 session); + int (*system_session)(struct tee_context *ctx, u32 session); + int (*invoke_func)(struct tee_context *ctx, + struct tee_ioctl_invoke_arg *arg, + struct tee_param *param); + int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session); + int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params, + struct tee_param *param); + int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params, + struct tee_param *param); + int (*shm_register)(struct tee_context *ctx, struct tee_shm *shm, + struct page **pages, size_t num_pages, + unsigned long start); + int (*shm_unregister)(struct tee_context *ctx, struct tee_shm *shm); +}; + +/** + * struct tee_desc - Describes the TEE driver to the subsystem + * @name: name of driver + * @ops: driver operations vtable + * @owner: module providing the driver + * @flags: Extra properties of driver, defined by TEE_DESC_* below + */ +#define TEE_DESC_PRIVILEGED 0x1 +struct tee_desc { + const char *name; + const struct tee_driver_ops *ops; + struct module *owner; + u32 flags; +}; + +/** + * tee_device_alloc() - Allocate a new struct tee_device instance + * @teedesc: Descriptor for this driver + * @dev: Parent device for this device + * @pool: Shared memory pool, NULL if not used + * @driver_data: Private driver data for this device + * + * Allocates a new struct tee_device instance. The device is + * removed by tee_device_unregister(). + * + * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure + */ +struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, + struct device *dev, + struct tee_shm_pool *pool, + void *driver_data); + +/** + * tee_device_register() - Registers a TEE device + * @teedev: Device to register + * + * tee_device_unregister() need to be called to remove the @teedev if + * this function fails. + * + * @returns < 0 on failure + */ +int tee_device_register(struct tee_device *teedev); + +/** + * tee_device_unregister() - Removes a TEE device + * @teedev: Device to unregister + * + * This function should be called to remove the @teedev even if + * tee_device_register() hasn't been called yet. Does nothing if + * @teedev is NULL. + */ +void tee_device_unregister(struct tee_device *teedev); + +/** + * tee_session_calc_client_uuid() - Calculates client UUID for session + * @uuid: Resulting UUID + * @connection_method: Connection method for session (TEE_IOCTL_LOGIN_*) + * @connectuon_data: Connection data for opening session + * + * Based on connection method calculates UUIDv5 based client UUID. + * + * For group based logins verifies that calling process has specified + * credentials. + * + * @return < 0 on failure + */ +int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, + const u8 connection_data[TEE_IOCTL_UUID_LEN]); + +/** + * struct tee_shm_pool - shared memory pool + * @ops: operations + * @private_data: private data for the shared memory manager + */ +struct tee_shm_pool { + const struct tee_shm_pool_ops *ops; + void *private_data; +}; + +/** + * struct tee_shm_pool_ops - shared memory pool operations + * @alloc: called when allocating shared memory + * @free: called when freeing shared memory + * @destroy_pool: called when destroying the pool + */ +struct tee_shm_pool_ops { + int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, + size_t size, size_t align); + void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); + void (*destroy_pool)(struct tee_shm_pool *pool); +}; + +/* + * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory + * @vaddr: Virtual address of start of pool + * @paddr: Physical address of start of pool + * @size: Size in bytes of the pool + * + * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. + */ +struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, + phys_addr_t paddr, size_t size, + int min_alloc_order); + +/** + * tee_shm_pool_free() - Free a shared memory pool + * @pool: The shared memory pool to free + * + * The must be no remaining shared memory allocated from this pool when + * this function is called. + */ +static inline void tee_shm_pool_free(struct tee_shm_pool *pool) +{ + pool->ops->destroy_pool(pool); +} + +/** + * tee_get_drvdata() - Return driver_data pointer + * @returns the driver_data pointer supplied to tee_register(). + */ +void *tee_get_drvdata(struct tee_device *teedev); + +/** + * tee_shm_alloc_priv_buf() - Allocate shared memory for private use by specific + * TEE driver + * @ctx: The TEE context for shared memory allocation + * @size: Shared memory allocation size + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure + */ +struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); + +int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align, + int (*shm_register)(struct tee_context *ctx, + struct tee_shm *shm, + struct page **pages, + size_t num_pages, + unsigned long start)); +void tee_dyn_shm_free_helper(struct tee_shm *shm, + int (*shm_unregister)(struct tee_context *ctx, + struct tee_shm *shm)); + +/** + * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind + * @shm: Shared memory handle + * @returns true if object is dynamic shared memory + */ +static inline bool tee_shm_is_dynamic(struct tee_shm *shm) +{ + return shm && (shm->flags & TEE_SHM_DYNAMIC); +} + +/** + * tee_shm_put() - Decrease reference count on a shared memory handle + * @shm: Shared memory handle + */ +void tee_shm_put(struct tee_shm *shm); + +/** + * tee_shm_get_id() - Get id of a shared memory object + * @shm: Shared memory handle + * @returns id + */ +static inline int tee_shm_get_id(struct tee_shm *shm) +{ + return shm->id; +} + +/** + * tee_shm_get_from_id() - Find shared memory object and increase reference + * count + * @ctx: Context owning the shared memory + * @id: Id of shared memory object + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure + */ +struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); + +static inline bool tee_param_is_memref(struct tee_param *param) +{ + switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: + return true; + default: + return false; + } +} + +/** + * teedev_open() - Open a struct tee_device + * @teedev: Device to open + * + * @return a pointer to struct tee_context on success or an ERR_PTR on failure. + */ +struct tee_context *teedev_open(struct tee_device *teedev); + +/** + * teedev_close_context() - closes a struct tee_context + * @ctx: The struct tee_context to close + */ +void teedev_close_context(struct tee_context *ctx); + +#endif /*__TEE_CORE_H*/ diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 71632e3c5f18..786b9ae6cf4d 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -1,40 +1,28 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2015-2022 Linaro Limited + * Copyright (c) 2015-2024 Linaro Limited */ #ifndef __TEE_DRV_H #define __TEE_DRV_H #include <linux/device.h> -#include <linux/idr.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/mod_devicetable.h> #include <linux/tee.h> #include <linux/types.h> -#include <linux/uuid.h> /* - * The file describes the API provided by the generic TEE driver to the - * specific TEE driver. + * The file describes the API provided by the TEE subsystem to the + * TEE client drivers. */ -#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ - /* in secure world */ -#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ -#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ -#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ - -struct device; struct tee_device; -struct tee_shm; -struct tee_shm_pool; /** * struct tee_context - driver specific context on file pointer data * @teedev: pointer to this drivers struct tee_device - * @list_shm: List of shared memory object owned by this context * @data: driver specific context data, managed by the driver * @refcount: reference counter for this structure * @releasing: flag that indicates if context is being released right now. @@ -57,134 +45,6 @@ struct tee_context { bool cap_memref_null; }; -struct tee_param_memref { - size_t shm_offs; - size_t size; - struct tee_shm *shm; -}; - -struct tee_param_value { - u64 a; - u64 b; - u64 c; -}; - -struct tee_param { - u64 attr; - union { - struct tee_param_memref memref; - struct tee_param_value value; - } u; -}; - -/** - * struct tee_driver_ops - driver operations vtable - * @get_version: returns version of driver - * @open: called when the device file is opened - * @release: release this open file - * @open_session: open a new session - * @close_session: close a session - * @system_session: declare session as a system session - * @invoke_func: invoke a trusted function - * @cancel_req: request cancel of an ongoing invoke or open - * @supp_recv: called for supplicant to get a command - * @supp_send: called for supplicant to send a response - * @shm_register: register shared memory buffer in TEE - * @shm_unregister: unregister shared memory buffer in TEE - */ -struct tee_driver_ops { - void (*get_version)(struct tee_device *teedev, - struct tee_ioctl_version_data *vers); - int (*open)(struct tee_context *ctx); - void (*release)(struct tee_context *ctx); - int (*open_session)(struct tee_context *ctx, - struct tee_ioctl_open_session_arg *arg, - struct tee_param *param); - int (*close_session)(struct tee_context *ctx, u32 session); - int (*system_session)(struct tee_context *ctx, u32 session); - int (*invoke_func)(struct tee_context *ctx, - struct tee_ioctl_invoke_arg *arg, - struct tee_param *param); - int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session); - int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params, - struct tee_param *param); - int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params, - struct tee_param *param); - int (*shm_register)(struct tee_context *ctx, struct tee_shm *shm, - struct page **pages, size_t num_pages, - unsigned long start); - int (*shm_unregister)(struct tee_context *ctx, struct tee_shm *shm); -}; - -/** - * struct tee_desc - Describes the TEE driver to the subsystem - * @name: name of driver - * @ops: driver operations vtable - * @owner: module providing the driver - * @flags: Extra properties of driver, defined by TEE_DESC_* below - */ -#define TEE_DESC_PRIVILEGED 0x1 -struct tee_desc { - const char *name; - const struct tee_driver_ops *ops; - struct module *owner; - u32 flags; -}; - -/** - * tee_device_alloc() - Allocate a new struct tee_device instance - * @teedesc: Descriptor for this driver - * @dev: Parent device for this device - * @pool: Shared memory pool, NULL if not used - * @driver_data: Private driver data for this device - * - * Allocates a new struct tee_device instance. The device is - * removed by tee_device_unregister(). - * - * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure - */ -struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, - struct device *dev, - struct tee_shm_pool *pool, - void *driver_data); - -/** - * tee_device_register() - Registers a TEE device - * @teedev: Device to register - * - * tee_device_unregister() need to be called to remove the @teedev if - * this function fails. - * - * @returns < 0 on failure - */ -int tee_device_register(struct tee_device *teedev); - -/** - * tee_device_unregister() - Removes a TEE device - * @teedev: Device to unregister - * - * This function should be called to remove the @teedev even if - * tee_device_register() hasn't been called yet. Does nothing if - * @teedev is NULL. - */ -void tee_device_unregister(struct tee_device *teedev); - -/** - * tee_session_calc_client_uuid() - Calculates client UUID for session - * @uuid: Resulting UUID - * @connection_method: Connection method for session (TEE_IOCTL_LOGIN_*) - * @connectuon_data: Connection data for opening session - * - * Based on connection method calculates UUIDv5 based client UUID. - * - * For group based logins verifies that calling process has specified - * credentials. - * - * @return < 0 on failure - */ -int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, - const u8 connection_data[TEE_IOCTL_UUID_LEN]); - /** * struct tee_shm - shared memory object * @ctx: context using the object @@ -195,15 +55,12 @@ int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, * @pages: locked pages from userspace * @num_pages: number of locked pages * @refcount: reference counter - * @flags: defined by TEE_SHM_* in tee_drv.h + * @flags: defined by TEE_SHM_* in tee_core.h * @id: unique id of a shared memory object on this device, shared * with user space * @sec_world_id: * secure world assigned id of this shared memory object, not * used by all drivers - * - * This pool is only supposed to be accessed directly from the TEE - * subsystem and from drivers that implements their own shm pool manager. */ struct tee_shm { struct tee_context *ctx; @@ -219,88 +76,53 @@ struct tee_shm { u64 sec_world_id; }; -/** - * struct tee_shm_pool - shared memory pool - * @ops: operations - * @private_data: private data for the shared memory manager - */ -struct tee_shm_pool { - const struct tee_shm_pool_ops *ops; - void *private_data; +struct tee_param_memref { + size_t shm_offs; + size_t size; + struct tee_shm *shm; }; -/** - * struct tee_shm_pool_ops - shared memory pool operations - * @alloc: called when allocating shared memory - * @free: called when freeing shared memory - * @destroy_pool: called when destroying the pool - */ -struct tee_shm_pool_ops { - int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, - size_t size, size_t align); - void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); - void (*destroy_pool)(struct tee_shm_pool *pool); +struct tee_param_value { + u64 a; + u64 b; + u64 c; }; -/* - * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory - * @vaddr: Virtual address of start of pool - * @paddr: Physical address of start of pool - * @size: Size in bytes of the pool - * - * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. - */ -struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, - phys_addr_t paddr, size_t size, - int min_alloc_order); +struct tee_param { + u64 attr; + union { + struct tee_param_memref memref; + struct tee_param_value value; + } u; +}; /** - * tee_shm_pool_free() - Free a shared memory pool - * @pool: The shared memory pool to free - * - * The must be no remaining shared memory allocated from this pool when - * this function is called. + * tee_shm_alloc_kernel_buf() - Allocate kernel shared memory for a + * particular TEE client driver + * @ctx: The TEE context for shared memory allocation + * @size: Shared memory allocation size + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure */ -static inline void tee_shm_pool_free(struct tee_shm_pool *pool) -{ - pool->ops->destroy_pool(pool); -} +struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); /** - * tee_get_drvdata() - Return driver_data pointer - * @returns the driver_data pointer supplied to tee_register(). + * tee_shm_register_kernel_buf() - Register kernel shared memory for a + * particular TEE client driver + * @ctx: The TEE context for shared memory registration + * @addr: Kernel buffer address + * @length: Kernel buffer length + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure */ -void *tee_get_drvdata(struct tee_device *teedev); - -struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); -struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); - struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, void *addr, size_t length); /** - * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind - * @shm: Shared memory handle - * @returns true if object is dynamic shared memory - */ -static inline bool tee_shm_is_dynamic(struct tee_shm *shm) -{ - return shm && (shm->flags & TEE_SHM_DYNAMIC); -} - -/** * tee_shm_free() - Free shared memory * @shm: Handle to shared memory to free */ void tee_shm_free(struct tee_shm *shm); /** - * tee_shm_put() - Decrease reference count on a shared memory handle - * @shm: Shared memory handle - */ -void tee_shm_put(struct tee_shm *shm); - -/** * tee_shm_get_va() - Get virtual address of a shared memory plus an offset * @shm: Shared memory handle * @offs: Offset from start of this shared memory @@ -353,25 +175,6 @@ static inline size_t tee_shm_get_page_offset(struct tee_shm *shm) } /** - * tee_shm_get_id() - Get id of a shared memory object - * @shm: Shared memory handle - * @returns id - */ -static inline int tee_shm_get_id(struct tee_shm *shm) -{ - return shm->id; -} - -/** - * tee_shm_get_from_id() - Find shared memory object and increase reference - * count - * @ctx: Context owning the shared memory - * @id: Id of shared memory object - * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure - */ -struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); - -/** * tee_client_open_context() - Open a TEE context * @start: if not NULL, continue search after this context * @match: function to check TEE device @@ -470,18 +273,6 @@ int tee_client_invoke_func(struct tee_context *ctx, int tee_client_cancel_req(struct tee_context *ctx, struct tee_ioctl_cancel_arg *arg); -static inline bool tee_param_is_memref(struct tee_param *param) -{ - switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: - return true; - default: - return false; - } -} - extern const struct bus_type tee_bus_type; /** @@ -509,18 +300,4 @@ struct tee_client_driver { #define to_tee_client_driver(d) \ container_of(d, struct tee_client_driver, driver) -/** - * teedev_open() - Open a struct tee_device - * @teedev: Device to open - * - * @return a pointer to struct tee_context on success or an ERR_PTR on failure. - */ -struct tee_context *teedev_open(struct tee_device *teedev); - -/** - * teedev_close_context() - closes a struct tee_context - * @ctx: The struct tee_context to close - */ -void teedev_close_context(struct tee_context *ctx); - #endif /*__TEE_DRV_H*/ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index b7a3deb372fd..f1155c0439c4 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -61,18 +61,26 @@ enum thermal_notify_event { * struct thermal_trip - representation of a point in temperature domain * @temperature: temperature value in miliCelsius * @hysteresis: relative hysteresis in miliCelsius - * @threshold: trip crossing notification threshold miliCelsius * @type: trip point type * @priv: pointer to driver data associated with this trip + * @flags: flags representing binary properties of the trip */ struct thermal_trip { int temperature; int hysteresis; - int threshold; enum thermal_trip_type type; + u8 flags; void *priv; }; +#define THERMAL_TRIP_FLAG_RW_TEMP BIT(0) +#define THERMAL_TRIP_FLAG_RW_HYST BIT(1) + +#define THERMAL_TRIP_FLAG_RW (THERMAL_TRIP_FLAG_RW_TEMP | \ + THERMAL_TRIP_FLAG_RW_HYST) + +struct thermal_zone_device; + struct thermal_zone_device_ops { int (*bind) (struct thermal_zone_device *, struct thermal_cooling_device *); @@ -83,7 +91,6 @@ struct thermal_zone_device_ops { int (*change_mode) (struct thermal_zone_device *, enum thermal_device_mode); int (*set_trip_temp) (struct thermal_zone_device *, int, int); - int (*set_trip_hyst) (struct thermal_zone_device *, int, int); int (*get_crit_temp) (struct thermal_zone_device *, int *); int (*set_emul_temp) (struct thermal_zone_device *, int); int (*get_trend) (struct thermal_zone_device *, @@ -119,114 +126,9 @@ struct thermal_cooling_device { #endif }; -/** - * struct thermal_zone_device - structure for a thermal zone - * @id: unique id number for each thermal zone - * @type: the thermal zone device type - * @device: &struct device for this thermal zone - * @removal: removal completion - * @trip_temp_attrs: attributes for trip points for sysfs: trip temperature - * @trip_type_attrs: attributes for trip points for sysfs: trip type - * @trip_hyst_attrs: attributes for trip points for sysfs: trip hysteresis - * @mode: current mode of this thermal zone - * @devdata: private pointer for device private data - * @trips: an array of struct thermal_trip - * @num_trips: number of trip points the thermal zone supports - * @passive_delay_jiffies: number of jiffies to wait between polls when - * performing passive cooling. - * @polling_delay_jiffies: number of jiffies to wait between polls when - * checking whether trip points have been crossed (0 for - * interrupt driven systems) - * @temperature: current temperature. This is only for core code, - * drivers should use thermal_zone_get_temp() to get the - * current temperature - * @last_temperature: previous temperature read - * @emul_temperature: emulated temperature when using CONFIG_THERMAL_EMULATION - * @passive: 1 if you've crossed a passive trip point, 0 otherwise. - * @prev_low_trip: the low current temperature if you've crossed a passive - trip point. - * @prev_high_trip: the above current temperature if you've crossed a - passive trip point. - * @need_update: if equals 1, thermal_zone_device_update needs to be invoked. - * @ops: operations this &thermal_zone_device supports - * @tzp: thermal zone parameters - * @governor: pointer to the governor for this thermal zone - * @governor_data: private pointer for governor data - * @thermal_instances: list of &struct thermal_instance of this thermal zone - * @ida: &struct ida to generate unique id for this zone's cooling - * devices - * @lock: lock to protect thermal_instances list - * @node: node in thermal_tz_list (in thermal_core.c) - * @poll_queue: delayed work for polling - * @notify_event: Last notification event - * @suspended: thermal zone suspend indicator - */ -struct thermal_zone_device { - int id; - char type[THERMAL_NAME_LENGTH]; - struct device device; - struct completion removal; - struct attribute_group trips_attribute_group; - struct thermal_attr *trip_temp_attrs; - struct thermal_attr *trip_type_attrs; - struct thermal_attr *trip_hyst_attrs; - enum thermal_device_mode mode; - void *devdata; - struct thermal_trip *trips; - int num_trips; - unsigned long passive_delay_jiffies; - unsigned long polling_delay_jiffies; - int temperature; - int last_temperature; - int emul_temperature; - int passive; - int prev_low_trip; - int prev_high_trip; - atomic_t need_update; - struct thermal_zone_device_ops *ops; - struct thermal_zone_params *tzp; - struct thermal_governor *governor; - void *governor_data; - struct list_head thermal_instances; - struct ida ida; - struct mutex lock; - struct list_head node; - struct delayed_work poll_queue; - enum thermal_notify_event notify_event; -#ifdef CONFIG_THERMAL_DEBUGFS - struct thermal_debugfs *debugfs; -#endif - bool suspended; -}; - -/** - * struct thermal_governor - structure that holds thermal governor information - * @name: name of the governor - * @bind_to_tz: callback called when binding to a thermal zone. If it - * returns 0, the governor is bound to the thermal zone, - * otherwise it fails. - * @unbind_from_tz: callback called when a governor is unbound from a - * thermal zone. - * @throttle: callback called for every trip point even if temperature is - * below the trip point temperature - * @update_tz: callback called when thermal zone internals have changed, e.g. - * thermal cooling instance was added/removed - * @governor_list: node in thermal_governor_list (in thermal_core.c) - */ -struct thermal_governor { - char name[THERMAL_NAME_LENGTH]; - int (*bind_to_tz)(struct thermal_zone_device *tz); - void (*unbind_from_tz)(struct thermal_zone_device *tz); - int (*throttle)(struct thermal_zone_device *tz, - const struct thermal_trip *trip); - void (*update_tz)(struct thermal_zone_device *tz, - enum thermal_notify_event reason); - struct list_head governor_list; -}; - /* Structure to define Thermal Zone parameters */ struct thermal_zone_params { - char governor_name[THERMAL_NAME_LENGTH]; + const char *governor_name; /* * a boolean to indicate if the thermal to hwmon sysfs interface @@ -315,17 +217,16 @@ int thermal_zone_get_crit_temp(struct thermal_zone_device *tz, int *temp); #ifdef CONFIG_THERMAL struct thermal_zone_device *thermal_zone_device_register_with_trips( const char *type, - struct thermal_trip *trips, - int num_trips, int mask, - void *devdata, - struct thermal_zone_device_ops *ops, + const struct thermal_trip *trips, + int num_trips, void *devdata, + const struct thermal_zone_device_ops *ops, const struct thermal_zone_params *tzp, int passive_delay, int polling_delay); struct thermal_zone_device *thermal_tripless_zone_device_register( const char *type, void *devdata, - struct thermal_zone_device_ops *ops, + const struct thermal_zone_device_ops *ops, const struct thermal_zone_params *tzp); void thermal_zone_device_unregister(struct thermal_zone_device *tz); @@ -375,10 +276,9 @@ void thermal_zone_device_critical(struct thermal_zone_device *tz); #else static inline struct thermal_zone_device *thermal_zone_device_register_with_trips( const char *type, - struct thermal_trip *trips, - int num_trips, int mask, - void *devdata, - struct thermal_zone_device_ops *ops, + const struct thermal_trip *trips, + int num_trips, void *devdata, + const struct thermal_zone_device_ops *ops, const struct thermal_zone_params *tzp, int passive_delay, int polling_delay) { return ERR_PTR(-ENODEV); } diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 2c835e5c41f6..4338ea9ac4fd 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -87,8 +87,8 @@ struct tb { }; extern const struct bus_type tb_bus_type; -extern struct device_type tb_service_type; -extern struct device_type tb_xdomain_type; +extern const struct device_type tb_service_type; +extern const struct device_type tb_xdomain_type; #define TB_LINKS_PER_PHY_PORT 2 diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h index c6540ceea143..0982d1d52b24 100644 --- a/include/linux/timecounter.h +++ b/include/linux/timecounter.h @@ -22,7 +22,7 @@ * * @read: returns the current cycle value * @mask: bitmask for two's complement - * subtraction of non 64 bit counters, + * subtraction of non-64-bit counters, * see CYCLECOUNTER_MASK() helper macro * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) @@ -35,7 +35,7 @@ struct cyclecounter { }; /** - * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds + * struct timecounter - layer above a &struct cyclecounter which counts nanoseconds * Contains the state needed by timecounter_read() to detect * cycle counter wrap around. Initialize with * timecounter_init(). Also used to convert cycle counts into the @@ -66,6 +66,8 @@ struct timecounter { * @cycles: Cycles * @mask: bit mask for maintaining the 'frac' field * @frac: pointer to storage for the fractional nanoseconds. + * + * Returns: cycle counter cycles converted to nanoseconds */ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, u64 cycles, u64 mask, u64 *frac) @@ -79,6 +81,7 @@ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, /** * timecounter_adjtime - Shifts the time of the clock. + * @tc: The &struct timecounter to adjust * @delta: Desired change in nanoseconds. */ static inline void timecounter_adjtime(struct timecounter *tc, s64 delta) @@ -107,6 +110,8 @@ extern void timecounter_init(struct timecounter *tc, * * In other words, keeps track of time since the same epoch as * the function which generated the initial time stamp. + * + * Returns: nanoseconds since the initial time stamp */ extern u64 timecounter_read(struct timecounter *tc); @@ -123,6 +128,8 @@ extern u64 timecounter_read(struct timecounter *tc); * * This allows conversion of cycle counter values which were generated * in the past. + * + * Returns: cycle counter converted to nanoseconds since the initial time stamp */ extern u64 timecounter_cyc2time(const struct timecounter *tc, u64 cycle_tstamp); diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7e50cbd97f86..0ea7823b7f31 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -22,14 +22,14 @@ extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* - * ktime_get() family: read the current time in a multitude of ways, + * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * - * To get the time in a different format, use the ones wit + * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. @@ -74,6 +74,8 @@ extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format + * + * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { @@ -86,10 +88,12 @@ static inline ktime_t ktime_get_coarse_real(void) } /** - * ktime_get_boottime - Returns monotonic time since boot in ktime_t format + * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. + * + * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { @@ -102,7 +106,9 @@ static inline ktime_t ktime_get_coarse_boottime(void) } /** - * ktime_get_clocktai - Returns the TAI time of day in ktime_t format + * ktime_get_clocktai - Get the TAI time of day in ktime_t format + * + * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { @@ -144,32 +150,60 @@ static inline u64 ktime_get_coarse_clocktai_ns(void) /** * ktime_mono_to_real - Convert monotonic time to clock realtime + * @mono: monotonic time to convert + * + * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } +/** + * ktime_get_ns - Get the current time in nanoseconds + * + * Returns: current time converted to nanoseconds + */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } +/** + * ktime_get_real_ns - Get the current real/wall time in nanoseconds + * + * Returns: current real time converted to nanoseconds + */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } +/** + * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds + * + * Returns: current boottime converted to nanoseconds + */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } +/** + * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds + * + * Returns: current TAI time converted to nanoseconds + */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } +/** + * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds + * + * Returns: current raw monotonic time converted to nanoseconds + */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); @@ -224,8 +258,8 @@ extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); -/* - * struct ktime_timestanps - Simultaneous mono/boot/real timestamps +/** + * struct ktime_timestamps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp @@ -242,7 +276,8 @@ struct ktime_timestamps { * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time - * @clock_was_set_seq: The sequence number of clock was set events + * @cs_id: Clocksource ID + * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { diff --git a/include/linux/timer.h b/include/linux/timer.h index 14a633ba61d6..e67ecd1cbc97 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -22,7 +22,7 @@ #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) #endif -/** +/* * @TIMER_DEFERRABLE: A deferrable timer will work normally when the * system is busy, but will not cause a CPU to come out of idle just * to service it; instead, the timer will be serviced when the CPU @@ -140,7 +140,7 @@ static inline void destroy_timer_on_stack(struct timer_list *timer) { } * or not. Callers must ensure serialization wrt. other operations done * to this timer, eg. interrupt contexts, or other CPUs on SMP. * - * return value: 1 if the timer is pending, 0 if not. + * Returns: 1 if the timer is pending, 0 if not. */ static inline int timer_pending(const struct timer_list * timer) { @@ -175,6 +175,10 @@ extern int timer_shutdown(struct timer_list *timer); * See timer_delete_sync() for detailed explanation. * * Do not use in new code. Use timer_delete_sync() instead. + * + * Returns: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ static inline int del_timer_sync(struct timer_list *timer) { @@ -188,6 +192,10 @@ static inline int del_timer_sync(struct timer_list *timer) * See timer_delete() for detailed explanation. * * Do not use in new code. Use timer_delete() instead. + * + * Returns: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ static inline int del_timer(struct timer_list *timer) { diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index 62973f7d4610..d306d9dd2207 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -37,11 +37,6 @@ static inline bool timerqueue_node_queued(struct timerqueue_node *node) return !RB_EMPTY_NODE(&node->node); } -static inline bool timerqueue_node_expires(struct timerqueue_node *node) -{ - return node->expires; -} - static inline void timerqueue_init_head(struct timerqueue_head *head) { head->rb_root = RB_ROOT_CACHED; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4ee9d13749ad..c17e4efbb2e5 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -23,6 +23,7 @@ #include <linux/fs.h> #include <linux/highmem.h> #include <crypto/hash_info.h> +#include <crypto/aes.h> #define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ #define TPM_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE @@ -30,17 +31,28 @@ struct tpm_chip; struct trusted_key_payload; struct trusted_key_options; +/* opaque structure, holds auth session parameters like the session key */ +struct tpm2_auth; + +enum tpm2_session_types { + TPM2_SE_HMAC = 0x00, + TPM2_SE_POLICY = 0x01, + TPM2_SE_TRIAL = 0x02, +}; /* if you add a new hash to this, increment TPM_MAX_HASHES below */ enum tpm_algorithms { TPM_ALG_ERROR = 0x0000, TPM_ALG_SHA1 = 0x0004, + TPM_ALG_AES = 0x0006, TPM_ALG_KEYEDHASH = 0x0008, TPM_ALG_SHA256 = 0x000B, TPM_ALG_SHA384 = 0x000C, TPM_ALG_SHA512 = 0x000D, TPM_ALG_NULL = 0x0010, TPM_ALG_SM3_256 = 0x0012, + TPM_ALG_ECC = 0x0023, + TPM_ALG_CFB = 0x0043, }; /* @@ -49,6 +61,11 @@ enum tpm_algorithms { */ #define TPM_MAX_HASHES 5 +enum tpm2_curves { + TPM2_ECC_NONE = 0x0000, + TPM2_ECC_NIST_P256 = 0x0003, +}; + struct tpm_digest { u16 alg_id; u8 digest[TPM_MAX_DIGEST_SIZE]; @@ -116,6 +133,20 @@ struct tpm_chip_seqops { const struct seq_operations *seqops; }; +/* fixed define for the curve we use which is NIST_P256 */ +#define EC_PT_SZ 32 + +/* + * fixed define for the size of a name. This is actually HASHALG size + * plus 2, so 32 for SHA256 + */ +#define TPM2_NAME_SIZE 34 + +/* + * The maximum size for an object context + */ +#define TPM2_MAX_CONTEXT_SIZE 4096 + struct tpm_chip { struct device dev; struct device devs; @@ -170,6 +201,18 @@ struct tpm_chip { /* active locality */ int locality; + +#ifdef CONFIG_TCG_TPM2_HMAC + /* details for communication security via sessions */ + + /* saved context for NULL seed */ + u8 null_key_context[TPM2_MAX_CONTEXT_SIZE]; + /* name of NULL seed */ + u8 null_key_name[TPM2_NAME_SIZE]; + u8 null_ec_key_x[EC_PT_SZ]; + u8 null_ec_key_y[EC_PT_SZ]; + struct tpm2_auth *auth; +#endif }; #define TPM_HEADER_SIZE 10 @@ -194,6 +237,7 @@ enum tpm2_timeouts { enum tpm2_structures { TPM2_ST_NO_SESSIONS = 0x8001, TPM2_ST_SESSIONS = 0x8002, + TPM2_ST_CREATION = 0x8021, }; /* Indicates from what layer of the software stack the error comes from */ @@ -204,6 +248,7 @@ enum tpm2_return_codes { TPM2_RC_SUCCESS = 0x0000, TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ TPM2_RC_HANDLE = 0x008B, + TPM2_RC_INTEGRITY = 0x009F, TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ TPM2_RC_FAILURE = 0x0101, TPM2_RC_DISABLED = 0x0120, @@ -231,6 +276,8 @@ enum tpm2_command_codes { TPM2_CC_CONTEXT_LOAD = 0x0161, TPM2_CC_CONTEXT_SAVE = 0x0162, TPM2_CC_FLUSH_CONTEXT = 0x0165, + TPM2_CC_READ_PUBLIC = 0x0173, + TPM2_CC_START_AUTH_SESS = 0x0176, TPM2_CC_VERIFY_SIGNATURE = 0x0177, TPM2_CC_GET_CAPABILITY = 0x017A, TPM2_CC_GET_RANDOM = 0x017B, @@ -243,9 +290,25 @@ enum tpm2_command_codes { }; enum tpm2_permanent_handles { + TPM2_RH_NULL = 0x40000007, TPM2_RS_PW = 0x40000009, }; +/* Most Significant Octet for key types */ +enum tpm2_mso_type { + TPM2_MSO_NVRAM = 0x01, + TPM2_MSO_SESSION = 0x02, + TPM2_MSO_POLICY = 0x03, + TPM2_MSO_PERMANENT = 0x40, + TPM2_MSO_VOLATILE = 0x80, + TPM2_MSO_PERSISTENT = 0x81, +}; + +static inline enum tpm2_mso_type tpm2_handle_mso(u32 handle) +{ + return handle >> 24; +} + enum tpm2_capabilities { TPM2_CAP_HANDLES = 1, TPM2_CAP_COMMANDS = 2, @@ -284,6 +347,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), TPM_CHIP_FLAG_SUSPENDED = BIT(8), TPM_CHIP_FLAG_HWRNG_DISABLED = BIT(9), + TPM_CHIP_FLAG_DISABLE = BIT(10), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) @@ -297,28 +361,61 @@ struct tpm_header { }; } __packed; -/* A string buffer type for constructing TPM commands. This is based on the - * ideas of string buffer code in security/keys/trusted.h but is heap based - * in order to keep the stack usage minimal. - */ - enum tpm_buf_flags { + /* the capacity exceeded: */ TPM_BUF_OVERFLOW = BIT(0), + /* TPM2B format: */ + TPM_BUF_TPM2B = BIT(1), + /* read out of boundary: */ + TPM_BUF_BOUNDARY_ERROR = BIT(2), }; +/* + * A string buffer type for constructing TPM commands. + */ struct tpm_buf { - unsigned int flags; + u32 flags; + u32 length; u8 *data; + u8 handles; }; enum tpm2_object_attributes { TPM2_OA_FIXED_TPM = BIT(1), + TPM2_OA_ST_CLEAR = BIT(2), TPM2_OA_FIXED_PARENT = BIT(4), + TPM2_OA_SENSITIVE_DATA_ORIGIN = BIT(5), TPM2_OA_USER_WITH_AUTH = BIT(6), + TPM2_OA_ADMIN_WITH_POLICY = BIT(7), + TPM2_OA_NO_DA = BIT(10), + TPM2_OA_ENCRYPTED_DUPLICATION = BIT(11), + TPM2_OA_RESTRICTED = BIT(16), + TPM2_OA_DECRYPT = BIT(17), + TPM2_OA_SIGN = BIT(18), }; +/* + * definitions for the canonical template. These are mandated + * by the TCG key template documents + */ + +#define AES_KEY_BYTES AES_KEYSIZE_128 +#define AES_KEY_BITS (AES_KEY_BYTES*8) +#define TPM2_OA_TMPL (TPM2_OA_NO_DA | \ + TPM2_OA_FIXED_TPM | \ + TPM2_OA_FIXED_PARENT | \ + TPM2_OA_SENSITIVE_DATA_ORIGIN | \ + TPM2_OA_USER_WITH_AUTH | \ + TPM2_OA_DECRYPT | \ + TPM2_OA_RESTRICTED) + enum tpm2_session_attributes { TPM2_SA_CONTINUE_SESSION = BIT(0), + TPM2_SA_AUDIT_EXCLUSIVE = BIT(1), + TPM2_SA_AUDIT_RESET = BIT(3), + TPM2_SA_DECRYPT = BIT(5), + TPM2_SA_ENCRYPT = BIT(6), + TPM2_SA_AUDIT = BIT(7), }; struct tpm2_hash { @@ -326,84 +423,21 @@ struct tpm2_hash { unsigned int tpm_id; }; -static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - head->tag = cpu_to_be16(tag); - head->length = cpu_to_be32(sizeof(*head)); - head->ordinal = cpu_to_be32(ordinal); -} - -static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - buf->data = (u8 *)__get_free_page(GFP_KERNEL); - if (!buf->data) - return -ENOMEM; - - buf->flags = 0; - tpm_buf_reset(buf, tag, ordinal); - return 0; -} - -static inline void tpm_buf_destroy(struct tpm_buf *buf) -{ - free_page((unsigned long)buf->data); -} - -static inline u32 tpm_buf_length(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be32_to_cpu(head->length); -} - -static inline u16 tpm_buf_tag(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be16_to_cpu(head->tag); -} - -static inline void tpm_buf_append(struct tpm_buf *buf, - const unsigned char *new_data, - unsigned int new_len) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - u32 len = tpm_buf_length(buf); - - /* Return silently if overflow has already happened. */ - if (buf->flags & TPM_BUF_OVERFLOW) - return; - - if ((len + new_len) > PAGE_SIZE) { - WARN(1, "tpm_buf: overflow\n"); - buf->flags |= TPM_BUF_OVERFLOW; - return; - } - - memcpy(&buf->data[len], new_data, new_len); - head->length = cpu_to_be32(len + new_len); -} - -static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value) -{ - tpm_buf_append(buf, &value, 1); -} - -static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value) -{ - __be16 value2 = cpu_to_be16(value); - - tpm_buf_append(buf, (u8 *) &value2, 2); -} - -static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) -{ - __be32 value2 = cpu_to_be32(value); - - tpm_buf_append(buf, (u8 *) &value2, 4); -} +int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal); +void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal); +int tpm_buf_init_sized(struct tpm_buf *buf); +void tpm_buf_reset_sized(struct tpm_buf *buf); +void tpm_buf_destroy(struct tpm_buf *buf); +u32 tpm_buf_length(struct tpm_buf *buf); +void tpm_buf_append(struct tpm_buf *buf, const u8 *new_data, u16 new_length); +void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value); +void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value); +void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value); +u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); +u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); +u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); + +u8 *tpm_buf_parameters(struct tpm_buf *buf); /* * Check if TPM device is in the firmware upgrade mode. @@ -415,7 +449,7 @@ static inline bool tpm_is_firmware_upgrade(struct tpm_chip *chip) static inline u32 tpm2_rc_value(u32 rc) { - return (rc & BIT(7)) ? rc & 0xff : rc; + return (rc & BIT(7)) ? rc & 0xbf : rc; } #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) @@ -429,10 +463,19 @@ extern int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digest); extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); -extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); extern struct tpm_chip *tpm_default_chip(void); void tpm2_flush_context(struct tpm_chip *chip, u32 handle); + +static inline void tpm_buf_append_empty_auth(struct tpm_buf *buf, u32 handle) +{ + /* simple authorization for empty auth */ + tpm_buf_append_u32(buf, 9); /* total length of auth */ + tpm_buf_append_u32(buf, handle); + tpm_buf_append_u16(buf, 0); /* nonce len */ + tpm_buf_append_u8(buf, 0); /* attributes */ + tpm_buf_append_u16(buf, 0); /* hmac len */ +} #else static inline int tpm_is_tpm2(struct tpm_chip *chip) { @@ -450,10 +493,6 @@ static inline int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, return -ENODEV; } -static inline int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen) -{ - return -ENODEV; -} static inline int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max) { return -ENODEV; @@ -463,5 +502,102 @@ static inline struct tpm_chip *tpm_default_chip(void) { return NULL; } + +static inline void tpm_buf_append_empty_auth(struct tpm_buf *buf, u32 handle) +{ +} #endif +#ifdef CONFIG_TCG_TPM2_HMAC + +int tpm2_start_auth_session(struct tpm_chip *chip); +void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, + u32 handle, u8 *name); +void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf, + u8 attributes, u8 *passphrase, + int passphraselen); +static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, + u8 *passphrase, + int passphraselen) +{ + tpm_buf_append_hmac_session(chip, buf, attributes, passphrase, + passphraselen); +} +void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf); +int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, + int rc); +void tpm2_end_auth_session(struct tpm_chip *chip); +#else +#include <asm/unaligned.h> + +static inline int tpm2_start_auth_session(struct tpm_chip *chip) +{ + return 0; +} +static inline void tpm2_end_auth_session(struct tpm_chip *chip) +{ +} +static inline void tpm_buf_append_name(struct tpm_chip *chip, + struct tpm_buf *buf, + u32 handle, u8 *name) +{ + tpm_buf_append_u32(buf, handle); + /* count the number of handles in the upper bits of flags */ + buf->handles++; +} +static inline void tpm_buf_append_hmac_session(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, u8 *passphrase, + int passphraselen) +{ + /* offset tells us where the sessions area begins */ + int offset = buf->handles * 4 + TPM_HEADER_SIZE; + u32 len = 9 + passphraselen; + + if (tpm_buf_length(buf) != offset) { + /* not the first session so update the existing length */ + len += get_unaligned_be32(&buf->data[offset]); + put_unaligned_be32(len, &buf->data[offset]); + } else { + tpm_buf_append_u32(buf, len); + } + /* auth handle */ + tpm_buf_append_u32(buf, TPM2_RS_PW); + /* nonce */ + tpm_buf_append_u16(buf, 0); + /* attributes */ + tpm_buf_append_u8(buf, 0); + /* passphrase */ + tpm_buf_append_u16(buf, passphraselen); + tpm_buf_append(buf, passphrase, passphraselen); +} +static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, + u8 *passphrase, + int passphraselen) +{ + int offset = buf->handles * 4 + TPM_HEADER_SIZE; + struct tpm_header *head = (struct tpm_header *) buf->data; + + /* + * if the only sessions are optional, the command tag + * must change to TPM2_ST_NO_SESSIONS + */ + if (tpm_buf_length(buf) == offset) + head->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS); +} +static inline void tpm_buf_fill_hmac_session(struct tpm_chip *chip, + struct tpm_buf *buf) +{ +} +static inline int tpm_buf_check_hmac_response(struct tpm_chip *chip, + struct tpm_buf *buf, + int rc) +{ + return rc; +} +#endif /* CONFIG_TCG_TPM2_HMAC */ + #endif diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index d68ff9b1247f..9df3e2973626 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -17,6 +17,9 @@ struct dentry; struct bpf_prog; union bpf_attr; +/* Used for event string fields when they are NULL */ +#define EVENT_NULL_STR "(null)" + const char *trace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long flags, const struct trace_print_flags *flag_array); @@ -103,13 +106,16 @@ struct trace_iterator { unsigned int temp_size; char *fmt; /* modified format holder */ unsigned int fmt_size; - long wait_index; + atomic_t wait_index; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; cpumask_var_t started; + /* Set when the file is closed to prevent new waiters */ + bool closed; + /* it's true when current open file is snapshot */ bool snapshot; @@ -759,8 +765,11 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_detach_bpf_prog(struct perf_event *event); int perf_event_query_prog_array(struct perf_event *event, void __user *info); -int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog); -int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog); + +struct bpf_raw_tp_link; +int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); +int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); + struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, @@ -788,11 +797,12 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info) { return -EOPNOTSUPP; } -static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p) +struct bpf_raw_tp_link; +static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } -static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p) +static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } @@ -903,31 +913,31 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_free_bpf_prog(struct perf_event *event); -void bpf_trace_run1(struct bpf_prog *prog, u64 arg1); -void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2); -void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run1(struct bpf_raw_tp_link *link, u64 arg1); +void bpf_trace_run2(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2); +void bpf_trace_run3(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3); -void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run4(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4); -void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run5(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5); -void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run6(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6); -void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run7(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7); -void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run8(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8); -void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run9(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9); -void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run10(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10); -void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run11(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11); -void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run12(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12); void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 7a5fe17b6bf9..d03f74658716 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -62,6 +62,8 @@ struct eventfs_file; typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); +typedef void (*eventfs_release)(const char *name, void *data); + /** * struct eventfs_entry - dynamically created eventfs file call back handler * @name: Then name of the dynamic file in an eventfs directory @@ -72,6 +74,7 @@ typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, struct eventfs_entry { const char *name; eventfs_callback callback; + eventfs_release release; }; struct eventfs_inode; diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 88c0ba623ee6..689b6d71590e 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -199,7 +199,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) if (!(cond)) \ return; \ \ - if (WARN_ON_ONCE(RCUIDLE_COND(rcuidle))) \ + if (WARN_ONCE(RCUIDLE_COND(rcuidle), \ + "Bad RCU usage for tracepoint")) \ return; \ \ /* keep srcu and sched-rcu usage consistent */ \ @@ -259,7 +260,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) TP_ARGS(args), \ TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ - WARN_ON_ONCE(!rcu_is_watching()); \ + WARN_ONCE(!rcu_is_watching(), \ + "RCU not watching for tracepoint"); \ } \ } \ __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \ diff --git a/include/linux/tty.h b/include/linux/tty.h index 8c76fd97d4ad..2372f9357240 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -6,7 +6,6 @@ #include <linux/major.h> #include <linux/termios.h> #include <linux/workqueue.h> -#include <linux/tty_buffer.h> #include <linux/tty_driver.h> #include <linux/tty_ldisc.h> #include <linux/tty_port.h> @@ -146,15 +145,12 @@ struct tty_operations; * @count: count of open processes, reaching zero cancels all the work for * this tty and drops a @kref too (but does not free this tty) * @winsize: size of the terminal "window" (cf. @winsize_mutex) - * @flow: flow settings grouped together, see also @flow.unused + * @flow: flow settings grouped together * @flow.lock: lock for @flow members * @flow.stopped: tty stopped/started by stop_tty()/start_tty() * @flow.tco_stopped: tty stopped/started by %TCOOFF/%TCOON ioctls (it has * precedence over @flow.stopped) - * @flow.unused: alignment for Alpha, so that no members other than @flow.* are - * modified by the same 64b word store. The @flow's __aligned is - * there for the very same reason. - * @ctrl: control settings grouped together, see also @ctrl.unused + * @ctrl: control settings grouped together * @ctrl.lock: lock for @ctrl members * @ctrl.pgrp: process group of this tty (setpgrp(2)) * @ctrl.session: session of this tty (setsid(2)). Writes are protected by both @@ -162,7 +158,6 @@ struct tty_operations; * them. * @ctrl.pktstatus: packet mode status (bitwise OR of %TIOCPKT_ constants) * @ctrl.packet: packet mode enabled - * @ctrl.unused: alignment for Alpha, see @flow.unused for explanation * @hw_stopped: not controlled by the tty layer, under @driver's control for CTS * handling * @receive_room: bytes permitted to feed to @ldisc without any being lost @@ -217,8 +212,7 @@ struct tty_struct { spinlock_t lock; bool stopped; bool tco_stopped; - unsigned long unused[0]; - } __aligned(sizeof(unsigned long)) flow; + } flow; struct { struct pid *pgrp; @@ -226,8 +220,7 @@ struct tty_struct { spinlock_t lock; unsigned char pktstatus; bool packet; - unsigned long unused[0]; - } __aligned(sizeof(unsigned long)) ctrl; + } ctrl; bool hw_stopped; bool closing; diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index ffe48e69b3f3..457879938fc1 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -135,10 +135,11 @@ static inline void u64_stats_inc(u64_stats_t *p) p->v++; } -static inline void u64_stats_init(struct u64_stats_sync *syncp) -{ - seqcount_init(&syncp->seq); -} +#define u64_stats_init(syncp) \ + do { \ + struct u64_stats_sync *__s = (syncp); \ + seqcount_init(&__s->seq); \ + } while (0) static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { diff --git a/include/linux/udp.h b/include/linux/udp.h index 2d21cdb41ad8..3eb3f2b9a2a0 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -108,7 +108,7 @@ struct udp_sock { #define udp_assign_bit(nr, sk, val) \ assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) @@ -150,6 +150,24 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, } } +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); +#if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +#endif + +static inline bool udp_encap_needed(void) +{ + if (static_branch_unlikely(&udp_encap_needed_key)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (static_branch_unlikely(&udpv6_encap_needed_key)) + return true; +#endif + + return false; +} + static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) @@ -163,6 +181,16 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; + /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still + * land in a tunnel as the socket check in udp_gro_receive cannot be + * foolproof. + */ + if (udp_encap_needed() && + READ_ONCE(udp_sk(sk)->encap_rcv) && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) + return true; + return false; } diff --git a/include/linux/uio.h b/include/linux/uio.h index 00cebe2b70de..7020adedfa08 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -206,6 +206,16 @@ size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) } static __always_inline __must_check +bool copy_to_iter_full(const void *addr, size_t bytes, struct iov_iter *i) +{ + size_t copied = copy_to_iter(addr, bytes, i); + if (likely(copied == bytes)) + return true; + iov_iter_revert(i, copied); + return false; +} + +static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter(addr, bytes, i); diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 47c5962b876b..18238dc8bfd3 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -28,19 +28,26 @@ struct uio_map; * logical, virtual, or physical & phys_addr_t * should always be large enough to handle any of * the address types) + * @dma_addr: DMA handle set by dma_alloc_coherent, used with + * UIO_MEM_DMA_COHERENT only (@addr should be the + * void * returned from the same dma_alloc_coherent call) * @offs: offset of device memory within the page * @size: size of IO (multiple of page size) * @memtype: type of memory addr points to * @internal_addr: ioremap-ped version of addr, for driver internal use + * @dma_device: device struct that was passed to dma_alloc_coherent, + * used with UIO_MEM_DMA_COHERENT only * @map: for use by the UIO core only. */ struct uio_mem { const char *name; phys_addr_t addr; + dma_addr_t dma_addr; unsigned long offs; resource_size_t size; int memtype; void __iomem *internal_addr; + struct device *dma_device; struct uio_map *map; }; @@ -158,6 +165,12 @@ extern int __must_check #define UIO_MEM_LOGICAL 2 #define UIO_MEM_VIRTUAL 3 #define UIO_MEM_IOVA 4 +/* + * UIO_MEM_DMA_COHERENT exists for legacy drivers that had been getting by with + * improperly mapping DMA coherent allocations through the other modes. + * Do not use in new drivers. + */ +#define UIO_MEM_DMA_COHERENT 5 /* defines for uio_port->porttype */ #define UIO_PORT_NONE 0 diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index ca796dc1a984..6e5555610010 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -82,7 +82,7 @@ struct uac_clock_source_descriptor { #define UAC_CLOCK_SOURCE_TYPE_INT_PROG 0x3 #define UAC_CLOCK_SOURCE_SYNCED_TO_SOF (1 << 2) -/* 4.7.2.2 Clock Source Descriptor */ +/* 4.7.2.2 Clock Selector Descriptor */ struct uac_clock_selector_descriptor { __u8 bLength; @@ -91,7 +91,7 @@ struct uac_clock_selector_descriptor { __u8 bClockID; __u8 bNrInPins; __u8 baCSourceID[]; - /* bmControls and iClockSource omitted */ + /* bmControls and iClockSelector omitted */ } __attribute__((packed)); /* 4.7.2.3 Clock Multiplier Descriptor */ diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 6532beb587b1..56dda8e1562d 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -52,6 +52,7 @@ struct usb_ep; * @short_not_ok: When reading data, makes short packets be * treated as errors (queue stops advancing till cleanup). * @dma_mapped: Indicates if request has been mapped to DMA (internal) + * @sg_was_mapped: Set if the scatterlist has been mapped before the request * @complete: Function called when request completes, so this request and * its buffer may be re-used. The function will always be called with * interrupts disabled, and it must not sleep. @@ -111,6 +112,7 @@ struct usb_request { unsigned zero:1; unsigned short_not_ok:1; unsigned dma_mapped:1; + unsigned sg_was_mapped:1; void (*complete)(struct usb_ep *ep, struct usb_request *req); diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index 98487fd7ab11..de42f14bd280 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -6,6 +6,7 @@ #ifndef __LINUX_USB_OF_H #define __LINUX_USB_OF_H +#include <linux/usb.h> #include <linux/usb/ch9.h> #include <linux/usb/otg.h> #include <linux/usb/phy.h> @@ -17,6 +18,7 @@ enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *np, int arg0); bool of_usb_host_tpl_support(struct device_node *np); int of_usb_update_otg_caps(struct device_node *np, struct usb_otg_caps *otg_caps); +enum usb_port_connect_type usb_of_get_connect_type(struct usb_device *hub, int port1); struct device_node *usb_of_get_device_node(struct usb_device *hub, int port1); bool usb_of_has_combined_node(struct usb_device *udev); struct device_node *usb_of_get_interface_node(struct usb_device *udev, @@ -37,6 +39,11 @@ static inline int of_usb_update_otg_caps(struct device_node *np, { return 0; } +static inline enum usb_port_connect_type +usb_of_get_connect_type(const struct usb_device *hub, int port1) +{ + return USB_PORT_CONNECT_TYPE_UNKNOWN; +} static inline struct device_node * usb_of_get_device_node(struct usb_device *hub, int port1) { diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index eb626af0e4e7..d50098fb16b5 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -483,6 +483,7 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_T_BIST_CONT_MODE 50 /* 30 - 60 ms */ #define PD_T_SINK_TX 16 /* 16 - 20 ms */ #define PD_T_CHUNK_NOT_SUPP 42 /* 40 - 50 ms */ +#define PD_T_VCONN_STABLE 50 #define PD_T_DRP_TRY 100 /* 75 - 150 ms */ #define PD_T_DRP_TRYWAIT 600 /* 400 - 800 ms */ diff --git a/include/linux/usb/pd_vdo.h b/include/linux/usb/pd_vdo.h index 3a747938cdab..5c48e8a81403 100644 --- a/include/linux/usb/pd_vdo.h +++ b/include/linux/usb/pd_vdo.h @@ -7,6 +7,7 @@ #define __LINUX_USB_PD_VDO_H #include "pd.h" +#include <linux/bitfield.h> /* * VDO : Vendor Defined Message Object @@ -86,12 +87,15 @@ * * Request is simply properly formatted SVDM header * - * Response is 4 data objects: + * Response is 4 data objects for Power Delivery 2.0 and Passive Cables for + * Power Delivery 3.0. Active Cables in Power Delivery 3.0 have 5 data objects. * [0] :: SVDM header * [1] :: Identitiy header * [2] :: Cert Stat VDO * [3] :: (Product | Cable) VDO + * [4] :: Cable VDO 1 * [4] :: AMA VDO + * [5] :: Cable VDO 2 * */ #define VDO_INDEX_HDR 0 @@ -100,6 +104,8 @@ #define VDO_INDEX_CABLE 3 #define VDO_INDEX_PRODUCT 3 #define VDO_INDEX_AMA 4 +#define VDO_INDEX_CABLE_1 4 +#define VDO_INDEX_CABLE_2 5 /* * SVDM Identity Header @@ -150,6 +156,7 @@ #define PD_IDH_MODAL_SUPP(vdo) ((vdo) & (1 << 26)) #define PD_IDH_DFP_PTYPE(vdo) (((vdo) >> 23) & 0x7) #define PD_IDH_CONN_TYPE(vdo) (((vdo) >> 21) & 0x3) +#define PD_IDH_HOST_SUPP(vdo) ((vdo) & (1 << 31)) /* * Cert Stat VDO @@ -182,7 +189,7 @@ * <5:3> :: Alternate modes * <2:0> :: USB highest speed */ -#define PD_VDO_UFP_DEVCAP(vdo) (((vdo) & GENMASK(27, 24)) >> 24) +#define PD_VDO_UFP_DEVCAP(vdo) FIELD_GET(GENMASK(27, 24), vdo) /* UFP VDO Version */ #define UFP_VDO_VER1_2 2 @@ -241,7 +248,7 @@ * <21:5> :: Reserved * <4:0> :: Port number */ -#define PD_VDO_DFP_HOSTCAP(vdo) (((vdo) & GENMASK(26, 24)) >> 24) +#define PD_VDO_DFP_HOSTCAP(vdo) FIELD_GET(GENMASK(26, 24), vdo) #define DFP_VDO_VER1_1 1 #define HOST_USB2_CAPABLE BIT(0) diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 467e8045e9f8..47a86b8a4a50 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -145,6 +145,7 @@ #define TCPC_RX_BYTE_CNT 0x30 #define TCPC_RX_BUF_FRAME_TYPE 0x31 #define TCPC_RX_BUF_FRAME_TYPE_SOP 0 +#define TCPC_RX_BUF_FRAME_TYPE_SOP1 1 #define TCPC_RX_HDR 0x32 #define TCPC_RX_DATA 0x34 /* through 0x4f */ @@ -198,12 +199,23 @@ struct tcpci; * Chip level drivers are expected to check for contaminant and call * tcpm_clean_port when the port is clean to put the port back into * toggling state. + * @cable_comm_capable + * optional; Set when TCPC can communicate with cable plugs over SOP' + * @attempt_vconn_swap_discovery: + * Optional; The callback is called by the TCPM when the result of + * a Discover Identity request indicates that the port partner is + * a receptacle capable of modal operation. Chip level TCPCI drivers + * can implement their own policy to determine if and when a Vconn + * swap following Discover Identity on SOP' occurs. + * Return true when the TCPM is allowed to request a Vconn swap + * after Discovery Identity on SOP. */ struct tcpci_data { struct regmap *regmap; unsigned char TX_BUF_BYTE_x_hidden:1; unsigned char auto_discharge_disconnect:1; unsigned char vbus_vsafe0v:1; + unsigned char cable_comm_capable:1; int (*init)(struct tcpci *tcpci, struct tcpci_data *data); int (*set_vconn)(struct tcpci *tcpci, struct tcpci_data *data, @@ -215,6 +227,7 @@ struct tcpci_data { void (*set_partner_usb_comm_capable)(struct tcpci *tcpci, struct tcpci_data *data, bool capable); void (*check_contaminant)(struct tcpci *tcpci, struct tcpci_data *data); + bool (*attempt_vconn_swap_discovery)(struct tcpci *tcpci, struct tcpci_data *data); }; struct tcpci *tcpci_register_port(struct device *dev, struct tcpci_data *data); diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index 65fac5e1f317..061da9546a81 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -119,6 +119,17 @@ enum tcpm_transmit_type { * at the end of the deboumce period or when the port is still * toggling. Chip level drivers are expected to check for contaminant * and call tcpm_clean_port when the port is clean. + * @cable_comm_capable + * Optional; Returns whether cable communication over SOP' is supported + * by the tcpc + * @attempt_vconn_swap_discovery: + * Optional; The callback is called by the TCPM when the result of + * a Discover Identity request indicates that the port partner is + * a receptacle capable of modal operation. Chip level TCPCI drivers + * can implement their own policy to determine if and when a Vconn + * swap following Discover Identity on SOP' occurs. + * Return true when the TCPM is allowed to request a Vconn swap + * after Discovery Identity on SOP. */ struct tcpc_dev { struct fwnode_handle *fwnode; @@ -133,6 +144,8 @@ struct tcpc_dev { enum typec_cc_status *cc2); int (*set_polarity)(struct tcpc_dev *dev, enum typec_cc_polarity polarity); + int (*set_orientation)(struct tcpc_dev *dev, + enum typec_orientation orientation); int (*set_vconn)(struct tcpc_dev *dev, bool on); int (*set_vbus)(struct tcpc_dev *dev, bool on, bool charge); int (*set_current_limit)(struct tcpc_dev *dev, u32 max_ma, u32 mv); @@ -154,6 +167,8 @@ struct tcpc_dev { bool (*is_vbus_vsafe0v)(struct tcpc_dev *dev); void (*set_partner_usb_comm_capable)(struct tcpc_dev *dev, bool enable); void (*check_contaminant)(struct tcpc_dev *dev); + bool (*cable_comm_capable)(struct tcpc_dev *dev); + bool (*attempt_vconn_swap_discovery)(struct tcpc_dev *dev); }; struct tcpm_port; @@ -166,7 +181,8 @@ void tcpm_cc_change(struct tcpm_port *port); void tcpm_sink_frs(struct tcpm_port *port); void tcpm_sourcing_vbus(struct tcpm_port *port); void tcpm_pd_receive(struct tcpm_port *port, - const struct pd_message *msg); + const struct pd_message *msg, + enum tcpm_transmit_type rx_sop_type); void tcpm_pd_transmit_complete(struct tcpm_port *port, enum tcpm_transmit_status status); void tcpm_pd_hard_reset(struct tcpm_port *port); diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index a05d6f6f2536..b35b427561ab 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -18,6 +18,7 @@ struct typec_cable; struct typec_plug; struct typec_port; struct typec_altmode_ops; +struct typec_cable_ops; struct fwnode_handle; struct device; @@ -157,6 +158,9 @@ void typec_port_register_altmodes(struct typec_port *port, const struct typec_altmode_ops *ops, void *drvdata, struct typec_altmode **altmodes, size_t n); +void typec_port_register_cable_ops(struct typec_altmode **altmodes, int max_altmodes, + const struct typec_cable_ops *ops); + void typec_unregister_altmode(struct typec_altmode *altmode); struct typec_port *typec_altmode2port(struct typec_altmode *alt); @@ -333,6 +337,9 @@ void typec_partner_set_svdm_version(struct typec_partner *partner, enum usb_pd_svdm_ver svdm_version); int typec_get_negotiated_svdm_version(struct typec_port *port); +int typec_get_cable_svdm_version(struct typec_port *port); +void typec_cable_set_svdm_version(struct typec_cable *cable, enum usb_pd_svdm_ver svdm_version); + struct usb_power_delivery *typec_partner_usb_power_delivery_register(struct typec_partner *partner, struct usb_power_delivery_desc *desc); diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index 28aeef8f9e7b..b3c0866ea70f 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -20,6 +20,7 @@ struct typec_altmode_ops; * @active: Tells has the mode been entered or not * @desc: Optional human readable description of the mode * @ops: Operations vector from the driver + * @cable_ops: Cable operations vector from the driver. */ struct typec_altmode { struct device dev; @@ -30,6 +31,7 @@ struct typec_altmode { char *desc; const struct typec_altmode_ops *ops; + const struct typec_cable_ops *cable_ops; }; #define to_typec_altmode(d) container_of(d, struct typec_altmode, dev) @@ -75,6 +77,34 @@ int typec_altmode_notify(struct typec_altmode *altmode, unsigned long conf, const struct typec_altmode * typec_altmode_get_partner(struct typec_altmode *altmode); +/** + * struct typec_cable_ops - Cable alternate mode operations vector + * @enter: Operations to be executed with Enter Mode Command + * @exit: Operations to be executed with Exit Mode Command + * @vdm: Callback for SVID specific commands + */ +struct typec_cable_ops { + int (*enter)(struct typec_altmode *altmode, enum typec_plug_index sop, u32 *vdo); + int (*exit)(struct typec_altmode *altmode, enum typec_plug_index sop); + int (*vdm)(struct typec_altmode *altmode, enum typec_plug_index sop, + const u32 hdr, const u32 *vdo, int cnt); +}; + +int typec_cable_altmode_enter(struct typec_altmode *altmode, enum typec_plug_index sop, u32 *vdo); +int typec_cable_altmode_exit(struct typec_altmode *altmode, enum typec_plug_index sop); +int typec_cable_altmode_vdm(struct typec_altmode *altmode, enum typec_plug_index sop, + const u32 header, const u32 *vdo, int count); + +/** + * typec_altmode_get_cable_svdm_version - Get negotiated SVDM version for cable plug + * @altmode: Handle to the alternate mode + */ +static inline int +typec_altmode_get_cable_svdm_version(struct typec_altmode *altmode) +{ + return typec_get_cable_svdm_version(typec_altmode2port(altmode)); +} + /* * These are the connector states (USB, Safe and Alt Mode) defined in USB Type-C * Specification. SVID specific connector states are expected to follow and diff --git a/include/linux/usb/typec_dp.h b/include/linux/usb/typec_dp.h index 1f358098522d..f2da264d9c14 100644 --- a/include/linux/usb/typec_dp.h +++ b/include/linux/usb/typec_dp.h @@ -3,6 +3,7 @@ #define __USB_TYPEC_DP_H #include <linux/usb/typec_altmode.h> +#include <linux/bitfield.h> #define USB_TYPEC_DP_SID 0xff01 /* USB IF has not assigned a Standard ID (SID) for VirtualLink, @@ -67,21 +68,21 @@ enum { #define DP_CAP_UFP_D 1 #define DP_CAP_DFP_D 2 #define DP_CAP_DFP_D_AND_UFP_D 3 -#define DP_CAP_DP_SIGNALLING(_cap_) (((_cap_) & GENMASK(5, 2)) >> 2) +#define DP_CAP_DP_SIGNALLING(_cap_) FIELD_GET(GENMASK(5, 2), _cap_) #define DP_CAP_SIGNALLING_HBR3 1 #define DP_CAP_SIGNALLING_UHBR10 2 #define DP_CAP_SIGNALLING_UHBR20 3 #define DP_CAP_RECEPTACLE BIT(6) #define DP_CAP_USB BIT(7) -#define DP_CAP_DFP_D_PIN_ASSIGN(_cap_) (((_cap_) & GENMASK(15, 8)) >> 8) -#define DP_CAP_UFP_D_PIN_ASSIGN(_cap_) (((_cap_) & GENMASK(23, 16)) >> 16) +#define DP_CAP_DFP_D_PIN_ASSIGN(_cap_) FIELD_GET(GENMASK(15, 8), _cap_) +#define DP_CAP_UFP_D_PIN_ASSIGN(_cap_) FIELD_GET(GENMASK(23, 16), _cap_) /* Get pin assignment taking plug & receptacle into consideration */ #define DP_CAP_PIN_ASSIGN_UFP_D(_cap_) ((_cap_ & DP_CAP_RECEPTACLE) ? \ DP_CAP_UFP_D_PIN_ASSIGN(_cap_) : DP_CAP_DFP_D_PIN_ASSIGN(_cap_)) #define DP_CAP_PIN_ASSIGN_DFP_D(_cap_) ((_cap_ & DP_CAP_RECEPTACLE) ? \ DP_CAP_DFP_D_PIN_ASSIGN(_cap_) : DP_CAP_UFP_D_PIN_ASSIGN(_cap_)) #define DP_CAP_UHBR_13_5_SUPPORT BIT(26) -#define DP_CAP_CABLE_TYPE(_cap_) (((_cap_) & GENMASK(29, 28)) >> 28) +#define DP_CAP_CABLE_TYPE(_cap_) FIELD_GET(GENMASK(29, 28), _cap_) #define DP_CAP_CABLE_TYPE_PASSIVE 0 #define DP_CAP_CABLE_TYPE_RE_TIMER 1 #define DP_CAP_CABLE_TYPE_RE_DRIVER 2 @@ -116,7 +117,7 @@ enum { /* Helper for setting/getting the pin assignment value to the configuration */ #define DP_CONF_SET_PIN_ASSIGN(_a_) ((_a_) << 8) -#define DP_CONF_GET_PIN_ASSIGN(_conf_) (((_conf_) & GENMASK(15, 8)) >> 8) +#define DP_CONF_GET_PIN_ASSIGN(_conf_) FIELD_GET(GENMASK(15, 8), _conf_) #define DP_CONF_UHBR13_5_SUPPORT BIT(26) #define DP_CONF_CABLE_TYPE_MASK GENMASK(29, 28) #define DP_CONF_CABLE_TYPE_SHIFT 28 diff --git a/include/linux/usb/typec_tbt.h b/include/linux/usb/typec_tbt.h index c7a2153bd6f5..fa97d7e00f5c 100644 --- a/include/linux/usb/typec_tbt.h +++ b/include/linux/usb/typec_tbt.h @@ -3,6 +3,7 @@ #define __USB_TYPEC_TBT_H #include <linux/usb/typec_altmode.h> +#include <linux/bitfield.h> #define USB_TYPEC_VENDOR_INTEL 0x8087 /* Alias for convenience */ @@ -25,7 +26,7 @@ struct typec_thunderbolt_data { /* TBT3 Device Discover Mode VDO bits */ #define TBT_MODE BIT(0) -#define TBT_ADAPTER(_vdo_) (((_vdo_) & BIT(16)) >> 16) +#define TBT_ADAPTER(_vdo_) FIELD_GET(BIT(16), _vdo_) #define TBT_ADAPTER_LEGACY 0 #define TBT_ADAPTER_TBT3 1 #define TBT_INTEL_SPECIFIC_B0 BIT(26) @@ -35,12 +36,12 @@ struct typec_thunderbolt_data { #define TBT_SET_ADAPTER(a) (((a) & 1) << 16) /* TBT3 Cable Discover Mode VDO bits */ -#define TBT_CABLE_SPEED(_vdo_) (((_vdo_) & GENMASK(18, 16)) >> 16) +#define TBT_CABLE_SPEED(_vdo_) FIELD_GET(GENMASK(18, 16), _vdo_) #define TBT_CABLE_USB3_GEN1 1 #define TBT_CABLE_USB3_PASSIVE 2 #define TBT_CABLE_10_AND_20GBPS 3 -#define TBT_CABLE_ROUNDED_SUPPORT(_vdo_) \ - (((_vdo_) & GENMASK(20, 19)) >> 19) +#define TBT_CABLE_ROUNDED_SUPPORT(_vdo_) FIELD_GET(GENMASK(20, 19), _vdo_) + #define TBT_GEN3_NON_ROUNDED 0 #define TBT_GEN3_GEN4_ROUNDED_NON_ROUNDED 1 #define TBT_CABLE_OPTICAL BIT(21) diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index e4056547fbe6..05d59f74fc88 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -36,6 +36,52 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) +/* + * Start with fault_pending_wqh and fault_wqh so they're more likely + * to be in the same cacheline. + * + * Locking order: + * fd_wqh.lock + * fault_pending_wqh.lock + * fault_wqh.lock + * event_wqh.lock + * + * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, + * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's + * also taken in IRQ context. + */ +struct userfaultfd_ctx { + /* waitqueue head for the pending (i.e. not read) userfaults */ + wait_queue_head_t fault_pending_wqh; + /* waitqueue head for the userfaults */ + wait_queue_head_t fault_wqh; + /* waitqueue head for the pseudo fd to wakeup poll/read */ + wait_queue_head_t fd_wqh; + /* waitqueue head for events */ + wait_queue_head_t event_wqh; + /* a refile sequence protected by fault_pending_wqh lock */ + seqcount_spinlock_t refile_seq; + /* pseudo fd refcounting */ + refcount_t refcount; + /* userfaultfd syscall flags */ + unsigned int flags; + /* features requested from the userspace */ + unsigned int features; + /* released */ + bool released; + /* + * Prevents userfaultfd operations (fill/move/wp) from happening while + * some non-cooperative event(s) is taking place. Increments are done + * in write-mode. Whereas, userfaultfd operations, which includes + * reading mmap_changing, is done under read-mode. + */ + struct rw_semaphore map_changing_lock; + /* memory mappings are changing because of non-cooperative event */ + atomic_t mmap_changing; + /* mm with one ore more vmas attached to this userfaultfd_ctx */ + struct mm_struct *mm; +}; + extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); /* A combined operation mode + behavior flags. */ @@ -74,31 +120,26 @@ extern int mfill_atomic_install_pte(pmd_t *dst_pmd, unsigned long dst_addr, struct page *page, bool newly_allocated, uffd_flags_t flags); -extern ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start, +extern ssize_t mfill_atomic_copy(struct userfaultfd_ctx *ctx, 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, + uffd_flags_t flags); +extern ssize_t mfill_atomic_zeropage(struct userfaultfd_ctx *ctx, 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 ssize_t mfill_atomic_poison(struct mm_struct *dst_mm, unsigned long 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); + unsigned long len); +extern ssize_t mfill_atomic_continue(struct userfaultfd_ctx *ctx, unsigned long dst_start, + unsigned long len, uffd_flags_t flags); +extern ssize_t mfill_atomic_poison(struct userfaultfd_ctx *ctx, unsigned long start, + unsigned long len, uffd_flags_t flags); +extern int mwriteprotect_range(struct userfaultfd_ctx *ctx, unsigned long start, + unsigned long len, bool enable_wp); extern long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); /* move_pages */ void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2); void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2); -ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm, - unsigned long dst_start, unsigned long src_start, - unsigned long len, __u64 flags); +ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, + unsigned long src_start, unsigned long len, __u64 flags); int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index db15ac07f8a6..7977ca03ac7a 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -7,6 +7,7 @@ #include <linux/interrupt.h> #include <linux/vhost_iotlb.h> #include <linux/virtio_net.h> +#include <linux/virtio_blk.h> #include <linux/if_ether.h> /** @@ -195,6 +196,10 @@ struct vdpa_map_file { * @idx: virtqueue index * Returns int: irq number of a virtqueue, * negative number if no irq assigned. + * @get_vq_size: Get the size of a specific virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * Return u16: the size of the virtqueue * @get_vq_align: Get the virtqueue align requirement * for the device * @vdev: vdpa device @@ -386,6 +391,7 @@ struct vdpa_config_ops { (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* vq irq is not expected to be changed once DRIVER_OK is set */ int (*get_vq_irq)(struct vdpa_device *vdev, u16 idx); + u16 (*get_vq_size)(struct vdpa_device *vdev, u16 idx); /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 89b265bc6ec3..8b1a29820409 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -356,6 +356,7 @@ struct virqfd { wait_queue_entry_t wait; poll_table pt; struct work_struct shutdown; + struct work_struct flush_inject; struct virqfd **pvirqfd; }; @@ -363,5 +364,6 @@ int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void (*thread)(void *, void *), void *data, struct virqfd **pvirqfd, int fd); void vfio_virqfd_disable(struct virqfd **pvirqfd); +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd); #endif /* VFIO_H */ diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 85e84b92751b..a2c8b8bba711 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -130,7 +130,15 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar); pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, pci_channel_state_t state); - +ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, + void __iomem *io, char __user *buf, + loff_t off, size_t count, size_t x_start, + size_t x_end, bool iswrite); +bool vfio_pci_core_range_intersect_range(loff_t buf_start, size_t buf_cnt, + loff_t reg_start, size_t reg_cnt, + loff_t *buf_offset, + size_t *intersect_count, + size_t *register_offset); #define VFIO_IOWRITE_DECLATION(size) \ int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev, \ bool test_mem, u##size val, void __iomem *io); diff --git a/include/linux/virtio.h b/include/linux/virtio.h index b0201747a263..96fea920873b 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -126,6 +126,8 @@ struct virtio_admin_cmd { * @vqs: the list of virtqueues for this device. * @features: the features supported by both driver and device. * @priv: private pointer for the driver's use. + * @debugfs_dir: debugfs directory entry. + * @debugfs_filter_features: features to be filtered set by debugfs. */ struct virtio_device { int index; @@ -141,6 +143,10 @@ struct virtio_device { struct list_head vqs; u64 features; void *priv; +#ifdef CONFIG_VIRTIO_DEBUG + struct dentry *debugfs_dir; + u64 debugfs_filter_features; +#endif }; #define dev_to_virtio(_dev) container_of_const(_dev, struct virtio_device, dev) @@ -170,7 +176,7 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev); /** * struct virtio_driver - operations for a virtio I/O driver - * @driver: underlying device driver (populate name and owner). + * @driver: underlying device driver (populate name). * @id_table: the ids serviced by this driver. * @feature_table: an array of feature numbers supported by this driver. * @feature_table_size: number of entries in the feature table array. @@ -208,7 +214,10 @@ static inline struct virtio_driver *drv_to_virtio(struct device_driver *drv) return container_of(drv, struct virtio_driver, driver); } -int register_virtio_driver(struct virtio_driver *drv); +/* use a macro to avoid include chaining to get THIS_MODULE */ +#define register_virtio_driver(drv) \ + __register_virtio_driver(drv, THIS_MODULE) +int __register_virtio_driver(struct virtio_driver *drv, struct module *owner); void unregister_virtio_driver(struct virtio_driver *drv); /* module_virtio_driver() - Helper macro for drivers that don't do @@ -234,4 +243,33 @@ void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq, dma_addr_t a void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq, dma_addr_t addr, unsigned long offset, size_t size, enum dma_data_direction dir); + +#ifdef CONFIG_VIRTIO_DEBUG +void virtio_debug_device_init(struct virtio_device *dev); +void virtio_debug_device_exit(struct virtio_device *dev); +void virtio_debug_device_filter_features(struct virtio_device *dev); +void virtio_debug_init(void); +void virtio_debug_exit(void); +#else +static inline void virtio_debug_device_init(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_device_exit(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_device_filter_features(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_init(void) +{ +} + +static inline void virtio_debug_exit(void) +{ +} +#endif + #endif /* _LINUX_VIRTIO_H */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0f72c85a377b..98ea90e90439 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -258,7 +258,6 @@ extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count); /* * Internals. Don't use.. */ -extern struct list_head vmap_area_list; extern __init void vm_area_add_early(struct vm_struct *vm); extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); diff --git a/include/linux/vmcore_info.h b/include/linux/vmcore_info.h new file mode 100644 index 000000000000..e1dec1a6a749 --- /dev/null +++ b/include/linux/vmcore_info.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_VMCORE_INFO_H +#define LINUX_VMCORE_INFO_H + +#include <linux/linkage.h> +#include <linux/elfcore.h> +#include <linux/elf.h> + +#define CRASH_CORE_NOTE_NAME "CORE" +#define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) +#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4) +#define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4) + +/* + * The per-cpu notes area is a list of notes terminated by a "NULL" + * note header. For kdump, the code in vmcore.c runs in the context + * of the second kernel to combine them into one note. + */ +#define CRASH_CORE_NOTE_BYTES ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ + CRASH_CORE_NOTE_NAME_BYTES + \ + CRASH_CORE_NOTE_DESC_BYTES) + +#define VMCOREINFO_BYTES PAGE_SIZE +#define VMCOREINFO_NOTE_NAME "VMCOREINFO" +#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) +#define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ + VMCOREINFO_NOTE_NAME_BYTES + \ + VMCOREINFO_BYTES) + +typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4]; +/* Per cpu memory for storing cpu states in case of system crash. */ +extern note_buf_t __percpu *crash_notes; + +void crash_update_vmcoreinfo_safecopy(void *ptr); +void crash_save_vmcoreinfo(void); +void arch_crash_save_vmcoreinfo(void); +__printf(1, 2) +void vmcoreinfo_append_str(const char *fmt, ...); +phys_addr_t paddr_vmcoreinfo_note(void); + +#define VMCOREINFO_OSRELEASE(value) \ + vmcoreinfo_append_str("OSRELEASE=%s\n", value) +#define VMCOREINFO_BUILD_ID() \ + ({ \ + static_assert(sizeof(vmlinux_build_id) == 20); \ + vmcoreinfo_append_str("BUILD-ID=%20phN\n", vmlinux_build_id); \ + }) + +#define VMCOREINFO_PAGESIZE(value) \ + vmcoreinfo_append_str("PAGESIZE=%ld\n", value) +#define VMCOREINFO_SYMBOL(name) \ + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) +#define VMCOREINFO_SYMBOL_ARRAY(name) \ + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)name) +#define VMCOREINFO_SIZE(name) \ + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ + (unsigned long)sizeof(name)) +#define VMCOREINFO_STRUCT_SIZE(name) \ + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ + (unsigned long)sizeof(struct name)) +#define VMCOREINFO_OFFSET(name, field) \ + vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ + (unsigned long)offsetof(struct name, field)) +#define VMCOREINFO_TYPE_OFFSET(name, field) \ + vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ + (unsigned long)offsetof(name, field)) +#define VMCOREINFO_LENGTH(name, value) \ + vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) +#define VMCOREINFO_NUMBER(name) \ + vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) +#define VMCOREINFO_CONFIG(name) \ + vmcoreinfo_append_str("CONFIG_%s=y\n", #name) + +extern unsigned char *vmcoreinfo_data; +extern size_t vmcoreinfo_size; +extern u32 *vmcoreinfo_note; + +Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, + void *data, size_t data_len); +void final_note(Elf_Word *buf); +#endif /* LINUX_VMCORE_INFO_H */ diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index c1f5aebef170..d008c3d0a9bb 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -25,7 +25,8 @@ extern int fg_console, last_console, want_console; int vc_allocate(unsigned int console); int vc_cons_allocated(unsigned int console); -int vc_resize(struct vc_data *vc, unsigned int cols, unsigned int lines); +int __vc_resize(struct vc_data *vc, unsigned int cols, unsigned int lines, + bool from_user); struct vc_data *vc_deallocate(unsigned int console); void reset_palette(struct vc_data *vc); void do_blank_screen(int entering_gfx); @@ -42,6 +43,12 @@ void redraw_screen(struct vc_data *vc, int is_switch); #define update_screen(x) redraw_screen(x, 0) #define switch_screen(x) redraw_screen(x, 1) +static inline int vc_resize(struct vc_data *vc, unsigned int cols, + unsigned int lines) +{ + return __vc_resize(vc, cols, lines, false); +} + struct tty_struct; int tioclinux(struct tty_struct *tty, unsigned long arg); @@ -168,7 +175,4 @@ void vt_set_led_state(unsigned int console, int leds); void vt_kbd_con_start(unsigned int console); void vt_kbd_con_stop(unsigned int console); -void vc_scrolldelta_helper(struct vc_data *c, int lines, - unsigned int rolled_over, void *_base, unsigned int size); - #endif /* _VT_KERN_H */ diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 3684487d01e1..29dd5b91dd7d 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -5,10 +5,6 @@ #include <linux/context_tracking_state.h> #include <linux/sched.h> -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -#include <asm/vtime.h> -#endif - /* * Common vtime APIs */ @@ -18,7 +14,6 @@ extern void vtime_account_idle(struct task_struct *tsk); #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void arch_vtime_task_switch(struct task_struct *tsk); extern void vtime_user_enter(struct task_struct *tsk); extern void vtime_user_exit(struct task_struct *tsk); extern void vtime_guest_enter(struct task_struct *tsk); diff --git a/include/linux/win_minmax.h b/include/linux/win_minmax.h index 4ca2842d2842..6a5bb052fcc2 100644 --- a/include/linux/win_minmax.h +++ b/include/linux/win_minmax.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/** - * lib/minmax.c: windowed min/max tracker by Kathleen Nichols. +/* + * win_minmax.h: windowed min/max tracker by Kathleen Nichols. * */ #ifndef MINMAX_H diff --git a/include/linux/wmi.h b/include/linux/wmi.h index 686291b87852..63cca3b58d6d 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -48,7 +48,8 @@ u8 wmidev_instance_count(struct wmi_device *wdev); * struct wmi_driver - WMI driver structure * @driver: Driver model structure * @id_table: List of WMI GUIDs supported by this driver - * @no_notify_data: WMI events provide no event data + * @no_notify_data: Driver supports WMI events which provide no event data + * @no_singleton: Driver can be instantiated multiple times * @probe: Callback for device binding * @remove: Callback for device unbinding * @notify: Callback for receiving WMI events @@ -59,6 +60,7 @@ struct wmi_driver { struct device_driver driver; const struct wmi_device_id *id_table; bool no_notify_data; + bool no_singleton; int (*probe)(struct wmi_device *wdev, const void *context); void (*remove)(struct wmi_device *wdev); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 453736fd1d23..9845cb62e40b 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -11,6 +11,7 @@ #include <linux/flex_proportions.h> #include <linux/backing-dev-defs.h> #include <linux/blk_types.h> +#include <linux/pagevec.h> struct bio; @@ -40,6 +41,7 @@ enum writeback_sync_modes { * in a manner such that unspecified fields are set to zero. */ struct writeback_control { + /* public fields that can be set and/or consumed by the caller: */ long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ @@ -77,6 +79,11 @@ struct writeback_control { */ struct swap_iocb **swap_plug; + /* internal fields used by the ->writepages implementation: */ + struct folio_batch fbatch; + pgoff_t index; + int saved_err; + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ @@ -360,11 +367,12 @@ int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, bool wb_over_bg_thresh(struct bdi_writeback *wb); +struct folio *writeback_iter(struct address_space *mapping, + struct writeback_control *wbc, struct folio *folio, int *error); + typedef int (*writepage_t)(struct folio *folio, struct writeback_control *wbc, void *data); -void tag_pages_for_writeback(struct address_space *mapping, - pgoff_t start, pgoff_t end); int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data); diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 0b709f5bc65f..341aea490070 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -29,8 +29,8 @@ struct zswap_lruvec_state { bool zswap_store(struct folio *folio); bool zswap_load(struct folio *folio); -void zswap_invalidate(int type, pgoff_t offset); -void zswap_swapon(int type); +void zswap_invalidate(swp_entry_t swp); +int zswap_swapon(int type, unsigned long nr_pages); void zswap_swapoff(int type); void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg); void zswap_lruvec_state_init(struct lruvec *lruvec); @@ -50,8 +50,11 @@ static inline bool zswap_load(struct folio *folio) return false; } -static inline void zswap_invalidate(int type, pgoff_t offset) {} -static inline void zswap_swapon(int type) {} +static inline void zswap_invalidate(swp_entry_t swp) {} +static inline int zswap_swapon(int type, unsigned long nr_pages) +{ + return 0; +} static inline void zswap_swapoff(int type) {} static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {} static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {} |