diff --git a/Makefile b/Makefile index e1a94c8d278e..71968b4bb313 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 4 -SUBLEVEL = 86 +SUBLEVEL = 87 EXTRAVERSION = NAME = Kleptomaniac Octopus

diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 603aed229af7..46338f236004 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -217,15 +217,34 @@ static __inline__ void __clear_bit_unlock(int nr, volatile unsigned long *addr) */ static __inline__ int fls(unsigned int x) { - return 32 - __builtin_clz(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 32 - __builtin_clz(x) : 0; + asm("cntlzw %0,%1" : "=r" (lz) : "r" (x)); + return 32 - lz; }

#include <asm-generic/bitops/builtin-__fls.h>

+/* + * 64-bit can do this using one cntlzd (count leading zeroes doubleword) + * instruction; for 32-bit we use the generic version, which does two + * 32-bit fls calls. + */ +#ifdef CONFIG_PPC64 static __inline__ int fls64(__u64 x) { - return 64 - __builtin_clzll(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 64 - __builtin_clzll(x) : 0; + asm("cntlzd %0,%1" : "=r" (lz) : "r" (x)); + return 64 - lz; } +#else +#include <asm-generic/bitops/fls64.h> +#endif

#ifdef CONFIG_PPC64 unsigned int __arch_hweight8(unsigned int w); diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c index f6b253e2be40..36ec0bdd8b63 100644 --- a/arch/powerpc/sysdev/mpic_msgr.c +++ b/arch/powerpc/sysdev/mpic_msgr.c @@ -191,7 +191,7 @@ static int mpic_msgr_probe(struct platform_device *dev)

/* IO map the message register block. */ of_address_to_resource(np, 0, &rsrc); - msgr_block_addr = ioremap(rsrc.start, resource_size(&rsrc)); + msgr_block_addr = devm_ioremap(&dev->dev, rsrc.start, resource_size(&rsrc)); if (!msgr_block_addr) { dev_err(&dev->dev, "Failed to iomap MPIC message registers"); return -EFAULT; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 0f5d0a699a49..4e59ab817d3e 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -47,18 +47,25 @@ /* Max request size is determined by sector mask - 32K */ #define UBD_MAX_REQUEST (8 * sizeof(long))

+struct io_desc { + char *buffer; + unsigned long length; + unsigned long sector_mask; + unsigned long long cow_offset; + unsigned long bitmap_words[2]; +}; + struct io_thread_req { struct request *req; int fds[2]; unsigned long offsets[2]; unsigned long long offset; - unsigned long length; - char *buffer; int sectorsize; - unsigned long sector_mask; - unsigned long long cow_offset; - unsigned long bitmap_words[2]; int error; + + int desc_cnt; + /* io_desc has to be the last element of the struct */ + struct io_desc io_desc[]; };

@@ -524,12 +531,7 @@ static void ubd_handler(void) blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); blk_queue_flag_clear(QUEUE_FLAG_DISCARD, io_req->req->q); } - if ((io_req->error) || (io_req->buffer == NULL)) - blk_mq_end_request(io_req->req, io_req->error); - else { - if (!blk_update_request(io_req->req, io_req->error, io_req->length)) - __blk_mq_end_request(io_req->req, io_req->error); - } + blk_mq_end_request(io_req->req, io_req->error); kfree(io_req); } } @@ -945,6 +947,7 @@ static int ubd_add(int n, char **error_out) blk_queue_write_cache(ubd_dev->queue, true, false);

blk_queue_max_segments(ubd_dev->queue, MAX_SG); + blk_queue_segment_boundary(ubd_dev->queue, PAGE_SIZE - 1); err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, &ubd_gendisk[n]); if(err){ *error_out = "Failed to register device"; @@ -1288,37 +1291,74 @@ static void cowify_bitmap(__u64 io_offset, int length, unsigned long *cow_mask, *cow_offset += bitmap_offset; }

-static void cowify_req(struct io_thread_req *req, unsigned long *bitmap, +static void cowify_req(struct io_thread_req *req, struct io_desc *segment, + unsigned long offset, unsigned long *bitmap, __u64 bitmap_offset, __u64 bitmap_len) { - __u64 sector = req->offset >> SECTOR_SHIFT; + __u64 sector = offset >> SECTOR_SHIFT; int i;

- if (req->length > (sizeof(req->sector_mask) * 8) << SECTOR_SHIFT) + if (segment->length > (sizeof(segment->sector_mask) * 8) << SECTOR_SHIFT) panic("Operation too long");

if (req_op(req->req) == REQ_OP_READ) { - for (i = 0; i < req->length >> SECTOR_SHIFT; i++) { + for (i = 0; i < segment->length >> SECTOR_SHIFT; i++) { if(ubd_test_bit(sector + i, (unsigned char *) bitmap)) ubd_set_bit(i, (unsigned char *) - &req->sector_mask); + &segment->sector_mask); + } + } else { + cowify_bitmap(offset, segment->length, &segment->sector_mask, + &segment->cow_offset, bitmap, bitmap_offset, + segment->bitmap_words, bitmap_len); + } +} + +static void ubd_map_req(struct ubd *dev, struct io_thread_req *io_req, + struct request *req) +{ + struct bio_vec bvec; + struct req_iterator iter; + int i = 0; + unsigned long byte_offset = io_req->offset; + int op = req_op(req); + + if (op == REQ_OP_WRITE_ZEROES || op == REQ_OP_DISCARD) { + io_req->io_desc[0].buffer = NULL; + io_req->io_desc[0].length = blk_rq_bytes(req); + } else { + rq_for_each_segment(bvec, req, iter) { + BUG_ON(i >= io_req->desc_cnt); + + io_req->io_desc[i].buffer = + page_address(bvec.bv_page) + bvec.bv_offset; + io_req->io_desc[i].length = bvec.bv_len; + i++; + } + } + + if (dev->cow.file) { + for (i = 0; i < io_req->desc_cnt; i++) { + cowify_req(io_req, &io_req->io_desc[i], byte_offset, + dev->cow.bitmap, dev->cow.bitmap_offset, + dev->cow.bitmap_len); + byte_offset += io_req->io_desc[i].length; } + } - else cowify_bitmap(req->offset, req->length, &req->sector_mask, - &req->cow_offset, bitmap, bitmap_offset, - req->bitmap_words, bitmap_len); }

-static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, - u64 off, struct bio_vec *bvec) +static struct io_thread_req *ubd_alloc_req(struct ubd *dev, struct request *req, + int desc_cnt) { - struct ubd *dev = hctx->queue->queuedata; struct io_thread_req *io_req; - int ret; + int i;

- io_req = kmalloc(sizeof(struct io_thread_req), GFP_ATOMIC); + io_req = kmalloc(sizeof(*io_req) + + (desc_cnt * sizeof(struct io_desc)), + GFP_ATOMIC); if (!io_req) - return -ENOMEM; + return NULL;

io_req->req = req; if (dev->cow.file) @@ -1326,26 +1366,41 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, else io_req->fds[0] = dev->fd; io_req->error = 0; - - if (bvec != NULL) { - io_req->buffer = page_address(bvec->bv_page) + bvec->bv_offset; - io_req->length = bvec->bv_len; - } else { - io_req->buffer = NULL; - io_req->length = blk_rq_bytes(req); - } - io_req->sectorsize = SECTOR_SIZE; io_req->fds[1] = dev->fd; - io_req->cow_offset = -1; - io_req->offset = off; - io_req->sector_mask = 0; + io_req->offset = (u64) blk_rq_pos(req) << SECTOR_SHIFT; io_req->offsets[0] = 0; io_req->offsets[1] = dev->cow.data_offset;

- if (dev->cow.file) - cowify_req(io_req, dev->cow.bitmap, - dev->cow.bitmap_offset, dev->cow.bitmap_len); + for (i = 0 ; i < desc_cnt; i++) { + io_req->io_desc[i].sector_mask = 0; + io_req->io_desc[i].cow_offset = -1; + } + + return io_req; +} + +static int ubd_submit_request(struct ubd *dev, struct request *req) +{ + int segs = 0; + struct io_thread_req *io_req; + int ret; + int op = req_op(req); + + if (op == REQ_OP_FLUSH) + segs = 0; + else if (op == REQ_OP_WRITE_ZEROES || op == REQ_OP_DISCARD) + segs = 1; + else + segs = blk_rq_nr_phys_segments(req); + + io_req = ubd_alloc_req(dev, req, segs); + if (!io_req) + return -ENOMEM; + + io_req->desc_cnt = segs; + if (segs) + ubd_map_req(dev, io_req, req);

ret = os_write_file(thread_fd, &io_req, sizeof(io_req)); if (ret != sizeof(io_req)) { @@ -1356,22 +1411,6 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, return ret; }

-static int queue_rw_req(struct blk_mq_hw_ctx *hctx, struct request *req) -{ - struct req_iterator iter; - struct bio_vec bvec; - int ret; - u64 off = (u64)blk_rq_pos(req) << SECTOR_SHIFT; - - rq_for_each_segment(bvec, req, iter) { - ret = ubd_queue_one_vec(hctx, req, off, &bvec); - if (ret < 0) - return ret; - off += bvec.bv_len; - } - return 0; -} - static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -1384,17 +1423,12 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, spin_lock_irq(&ubd_dev->lock);

switch (req_op(req)) { - /* operations with no lentgth/offset arguments */ case REQ_OP_FLUSH: - ret = ubd_queue_one_vec(hctx, req, 0, NULL); - break; case REQ_OP_READ: case REQ_OP_WRITE: - ret = queue_rw_req(hctx, req); - break; case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: - ret = ubd_queue_one_vec(hctx, req, (u64)blk_rq_pos(req) << 9, NULL); + ret = ubd_submit_request(ubd_dev, req); break; default: WARN_ON_ONCE(1); @@ -1482,22 +1516,22 @@ static int map_error(int error_code) * will result in unpredictable behaviour and/or crashes. */

-static int update_bitmap(struct io_thread_req *req) +static int update_bitmap(struct io_thread_req *req, struct io_desc *segment) { int n;

- if(req->cow_offset == -1) + if (segment->cow_offset == -1) return map_error(0);

- n = os_pwrite_file(req->fds[1], &req->bitmap_words, - sizeof(req->bitmap_words), req->cow_offset); - if (n != sizeof(req->bitmap_words)) + n = os_pwrite_file(req->fds[1], &segment->bitmap_words, + sizeof(segment->bitmap_words), segment->cow_offset); + if (n != sizeof(segment->bitmap_words)) return map_error(-n);

return map_error(0); }

-static void do_io(struct io_thread_req *req) +static void do_io(struct io_thread_req *req, struct io_desc *desc) { char *buf = NULL; unsigned long len; @@ -1512,21 +1546,20 @@ static void do_io(struct io_thread_req *req) return; }

- nsectors = req->length / req->sectorsize; + nsectors = desc->length / req->sectorsize; start = 0; do { - bit = ubd_test_bit(start, (unsigned char *) &req->sector_mask); + bit = ubd_test_bit(start, (unsigned char *) &desc->sector_mask); end = start; while((end < nsectors) && - (ubd_test_bit(end, (unsigned char *) - &req->sector_mask) == bit)) + (ubd_test_bit(end, (unsigned char *) &desc->sector_mask) == bit)) end++;

off = req->offset + req->offsets[bit] + start * req->sectorsize; len = (end - start) * req->sectorsize; - if (req->buffer != NULL) - buf = &req->buffer[start * req->sectorsize]; + if (desc->buffer != NULL) + buf = &desc->buffer[start * req->sectorsize];

switch (req_op(req->req)) { case REQ_OP_READ: @@ -1566,7 +1599,8 @@ static void do_io(struct io_thread_req *req) start = end; } while(start < nsectors);

- req->error = update_bitmap(req); + req->offset += len; + req->error = update_bitmap(req, desc); }

/* Changed in start_io_thread, which is serialized by being called only @@ -1599,8 +1633,13 @@ int io_thread(void *arg) }

for (count = 0; count < n/sizeof(struct io_thread_req *); count++) { + struct io_thread_req *req = (*io_req_buffer)[count]; + int i; + io_count++; - do_io((*io_req_buffer)[count]); + for (i = 0; !req->error && i < req->desc_cnt; i++) + do_io(req, &(req->io_desc[i])); + }

written = 0; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index d78a61408243..7dec43b2c420 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -154,6 +154,20 @@ static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) return x86_stepping(best->eax); }

+static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu) +{ + return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)); +} + +static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu) +{ + return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)); +} + static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu) { return vcpu->arch.msr_platform_info & MSR_PLATFORM_INFO_CPUID_FAULT; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c79c1a07f44b..2b506904be02 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -4233,8 +4233,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) + !guest_has_spec_ctrl_msr(vcpu)) return 1;

msr_info->data = svm->spec_ctrl; @@ -4318,16 +4317,13 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_SPEC_CTRL: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) + !guest_has_spec_ctrl_msr(vcpu)) return 1;

- /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) + if (data & ~kvm_spec_ctrl_valid_bits(vcpu)) return 1;

svm->spec_ctrl = data; - if (!data) break;

@@ -4346,18 +4342,17 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_PRED_CMD: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) + !guest_has_pred_cmd_msr(vcpu)) return 1;

if (data & ~PRED_CMD_IBPB) return 1; - + if (!boot_cpu_has(X86_FEATURE_IBPB)) + return 1; if (!data) break;

wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - if (is_guest_mode(vcpu)) - break; set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); break; case MSR_AMD64_VIRT_SPEC_CTRL: diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 2a1ed3aae100..e7fd2f00edc1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1788,7 +1788,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + !guest_has_spec_ctrl_msr(vcpu)) return 1;

msr_info->data = to_vmx(vcpu)->spec_ctrl; @@ -1971,15 +1971,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + !guest_has_spec_ctrl_msr(vcpu)) return 1;

- /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) + if (data & ~kvm_spec_ctrl_valid_bits(vcpu)) return 1;

vmx->spec_ctrl = data; - if (!data) break;

@@ -2001,12 +1999,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + !guest_has_pred_cmd_msr(vcpu)) return 1;

if (data & ~PRED_CMD_IBPB) return 1; - + if (!boot_cpu_has(X86_FEATURE_IBPB)) + return 1; if (!data) break;

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b7f86acb8c91..72990c3c6faf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10369,6 +10369,28 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_arch_no_poll);

+u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu) +{ + uint64_t bits = SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS)) + bits &= ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP); + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL) && + !boot_cpu_has(X86_FEATURE_AMD_IBRS)) + bits &= ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP); + + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL_SSBD) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) + bits &= ~SPEC_CTRL_SSBD; + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) && + !boot_cpu_has(X86_FEATURE_AMD_SSBD)) + bits &= ~SPEC_CTRL_SSBD; + + return bits; +} +EXPORT_SYMBOL_GPL(kvm_spec_ctrl_valid_bits);

EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index de6b55484876..301286d92432 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -368,5 +368,6 @@ static inline bool kvm_pat_valid(u64 data)

void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); +u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu);

#endif diff --git a/block/blk-pm.c b/block/blk-pm.c index 1adc1cd748b4..2ccf88dbaa40 100644 --- a/block/blk-pm.c +++ b/block/blk-pm.c @@ -67,6 +67,10 @@ int blk_pre_runtime_suspend(struct request_queue *q)

WARN_ON_ONCE(q->rpm_status != RPM_ACTIVE);

+ spin_lock_irq(&q->queue_lock); + q->rpm_status = RPM_SUSPENDING; + spin_unlock_irq(&q->queue_lock); + /* * Increase the pm_only counter before checking whether any * non-PM blk_queue_enter() calls are in progress to avoid that any @@ -89,15 +93,14 @@ int blk_pre_runtime_suspend(struct request_queue *q) /* Switch q_usage_counter back to per-cpu mode. */ blk_mq_unfreeze_queue(q);

- spin_lock_irq(&q->queue_lock); - if (ret < 0) + if (ret < 0) { + spin_lock_irq(&q->queue_lock); + q->rpm_status = RPM_ACTIVE; pm_runtime_mark_last_busy(q->dev); - else - q->rpm_status = RPM_SUSPENDING; - spin_unlock_irq(&q->queue_lock); + spin_unlock_irq(&q->queue_lock);

- if (ret) blk_clear_pm_only(q); + }

return ret; } diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index 2553e05e0725..5f1376578ea3 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -2,8 +2,7 @@ #include <linux/vmalloc.h> #include "null_blk.h"

-/* zone_size in MBs to sectors. */ -#define ZONE_SIZE_SHIFT 11 +#define MB_TO_SECTS(mb) (((sector_t)mb * SZ_1M) >> SECTOR_SHIFT)

static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect) { @@ -12,7 +11,7 @@ static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)

int null_zone_init(struct nullb_device *dev) { - sector_t dev_size = (sector_t)dev->size * 1024 * 1024; + sector_t dev_capacity_sects; sector_t sector = 0; unsigned int i;

@@ -25,9 +24,12 @@ int null_zone_init(struct nullb_device *dev) return -EINVAL; }

- dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT; - dev->nr_zones = dev_size >> - (SECTOR_SHIFT + ilog2(dev->zone_size_sects)); + dev_capacity_sects = MB_TO_SECTS(dev->size); + dev->zone_size_sects = MB_TO_SECTS(dev->zone_size); + dev->nr_zones = dev_capacity_sects >> ilog2(dev->zone_size_sects); + if (dev_capacity_sects & (dev->zone_size_sects - 1)) + dev->nr_zones++; + dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct blk_zone), GFP_KERNEL | __GFP_ZERO); if (!dev->zones) @@ -55,7 +57,10 @@ int null_zone_init(struct nullb_device *dev) struct blk_zone *zone = &dev->zones[i];

zone->start = zone->wp = sector; - zone->len = dev->zone_size_sects; + if (zone->start + dev->zone_size_sects > dev_capacity_sects) + zone->len = dev_capacity_sects - zone->start; + else + zone->len = dev->zone_size_sects; zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ; zone->cond = BLK_ZONE_COND_EMPTY;

diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index e11af747395d..17b0f1b793ec 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -250,8 +250,12 @@ static int h5_close(struct hci_uart *hu) if (h5->vnd && h5->vnd->close) h5->vnd->close(h5);

- if (!hu->serdev) - kfree(h5); + if (hu->serdev) + serdev_device_close(hu->serdev); + + kfree_skb(h5->rx_skb); + kfree(h5); + h5 = NULL;

return 0; } diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 6cc71c90f85e..19337aed9f23 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -2492,7 +2492,7 @@ int i3c_master_register(struct i3c_master_controller *master,

ret = i3c_master_bus_init(master); if (ret) - goto err_put_dev; + goto err_destroy_wq;

ret = device_add(&master->dev); if (ret) @@ -2523,6 +2523,9 @@ int i3c_master_register(struct i3c_master_controller *master, err_cleanup_bus: i3c_master_bus_cleanup(master);

+err_destroy_wq: + destroy_workqueue(master->wq); + err_put_dev: put_device(&master->dev);

diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 4fb33e7562c5..2aeb922e2365 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -533,6 +533,15 @@ static int verity_verify_io(struct dm_verity_io *io) return 0; }

+/* + * Skip verity work in response to I/O error when system is shutting down. + */ +static inline bool verity_is_system_shutting_down(void) +{ + return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF + || system_state == SYSTEM_RESTART; +} + /* * End one "io" structure with a given error. */ @@ -560,7 +569,8 @@ static void verity_end_io(struct bio *bio) { struct dm_verity_io *io = bio->bi_private;

- if (bio->bi_status && !verity_fec_is_enabled(io->v)) { + if (bio->bi_status && + (!verity_fec_is_enabled(io->v) || verity_is_system_shutting_down())) { verity_finish_io(io, bio->bi_status); return; } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index ec136e44aef7..a195a85cc366 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1145,7 +1145,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, struct md_rdev *err_rdev = NULL; gfp_t gfp = GFP_NOIO;

- if (r10_bio->devs[slot].rdev) { + if (slot >= 0 && r10_bio->devs[slot].rdev) { /* * This is an error retry, but we cannot * safely dereference the rdev in the r10_bio, @@ -1510,6 +1510,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors) r10_bio->mddev = mddev; r10_bio->sector = bio->bi_iter.bi_sector; r10_bio->state = 0; + r10_bio->read_slot = -1; memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->copies);

if (bio_data_dir(bio) == READ) diff --git a/drivers/media/usb/dvb-usb/gp8psk.c b/drivers/media/usb/dvb-usb/gp8psk.c index 1282f701f185..ac8b8bf6ee1d 100644 --- a/drivers/media/usb/dvb-usb/gp8psk.c +++ b/drivers/media/usb/dvb-usb/gp8psk.c @@ -182,7 +182,7 @@ static int gp8psk_load_bcm4500fw(struct dvb_usb_device *d)

static int gp8psk_power_ctrl(struct dvb_usb_device *d, int onoff) { - u8 status, buf; + u8 status = 0, buf; int gp_product_id = le16_to_cpu(d->udev->descriptor.idProduct);

if (onoff) { diff --git a/drivers/misc/vmw_vmci/vmci_context.c b/drivers/misc/vmw_vmci/vmci_context.c index 16695366ec92..26ff49fdf0f7 100644 --- a/drivers/misc/vmw_vmci/vmci_context.c +++ b/drivers/misc/vmw_vmci/vmci_context.c @@ -743,7 +743,7 @@ static int vmci_ctx_get_chkpt_doorbells(struct vmci_ctx *context, return VMCI_ERROR_MORE_DATA; }

- dbells = kmalloc(data_size, GFP_ATOMIC); + dbells = kzalloc(data_size, GFP_ATOMIC); if (!dbells) return VMCI_ERROR_NO_MEM;

diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c index 180caebbd355..9566958476df 100644 --- a/drivers/rtc/rtc-pl031.c +++ b/drivers/rtc/rtc-pl031.c @@ -379,8 +379,10 @@ static int pl031_probe(struct amba_device *adev, const struct amba_id *id)

device_init_wakeup(&adev->dev, true); ldata->rtc = devm_rtc_allocate_device(&adev->dev); - if (IS_ERR(ldata->rtc)) - return PTR_ERR(ldata->rtc); + if (IS_ERR(ldata->rtc)) { + ret = PTR_ERR(ldata->rtc); + goto out; + }

ldata->rtc->ops = ops;

diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index fc32be687606..c41bc8084d7c 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -276,7 +276,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, 300000000); if (IS_ERR(rtc->int_osc)) { pr_crit("Couldn't register the internal oscillator\n"); - return; + goto err; }

parents[0] = clk_hw_get_name(rtc->int_osc); @@ -292,7 +292,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, rtc->losc = clk_register(NULL, &rtc->hw); if (IS_ERR(rtc->losc)) { pr_crit("Couldn't register the LOSC clock\n"); - return; + goto err_register; }

of_property_read_string_index(node, "clock-output-names", 1, @@ -303,7 +303,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, &rtc->lock); if (IS_ERR(rtc->ext_losc)) { pr_crit("Couldn't register the LOSC external gate\n"); - return; + goto err_register; }

clk_data->num = 2; @@ -316,6 +316,8 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); return;

+err_register: + clk_hw_unregister_fixed_rate(rtc->int_osc); err: kfree(clk_data); } diff --git a/drivers/scsi/cxgbi/cxgb4i/Kconfig b/drivers/scsi/cxgbi/cxgb4i/Kconfig index d1f1baba3285..d1bdd754c6a4 100644 --- a/drivers/scsi/cxgbi/cxgb4i/Kconfig +++ b/drivers/scsi/cxgbi/cxgb4i/Kconfig @@ -4,6 +4,7 @@ config SCSI_CXGB4_ISCSI depends on PCI && INET && (IPV6 || IPV6=n) depends on THERMAL || !THERMAL depends on ETHERNET + depends on TLS || TLS=n select NET_VENDOR_CHELSIO select CHELSIO_T4 select CHELSIO_LIB diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index c37886a26712..9d24bc05df0d 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -320,6 +320,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, unsigned long state) { struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; + int ret;

/* Request state should be less than max_level */ if (WARN_ON(state > cpufreq_cdev->max_level)) @@ -329,10 +330,12 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, if (cpufreq_cdev->cpufreq_state == state) return 0;

- cpufreq_cdev->cpufreq_state = state; + ret = freq_qos_update_request(&cpufreq_cdev->qos_req, + cpufreq_cdev->freq_table[state].frequency); + if (ret > 0) + cpufreq_cdev->cpufreq_state = state;

- return freq_qos_update_request(&cpufreq_cdev->qos_req, - cpufreq_cdev->freq_table[state].frequency); + return ret; }

/** diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 632653cd70e3..2372e161cd5e 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -114,8 +114,6 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_device *vdev) int bar; struct vfio_pci_dummy_resource *dummy_res;

- INIT_LIST_HEAD(&vdev->dummy_resources_list); - for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) { res = vdev->pdev->resource + bar;

@@ -1606,6 +1604,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) mutex_init(&vdev->igate); spin_lock_init(&vdev->irqlock); mutex_init(&vdev->ioeventfds_lock); + INIT_LIST_HEAD(&vdev->dummy_resources_list); INIT_LIST_HEAD(&vdev->ioeventfds_list); mutex_init(&vdev->vma_lock); INIT_LIST_HEAD(&vdev->vma_list); diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index f8ce1368218b..1a8f3c8ab32c 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -351,7 +351,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)

info->si_lasti = (le32_to_cpu(bfs_sb->s_start) - BFS_BSIZE) / sizeof(struct bfs_inode) + BFS_ROOT_INO - 1; if (info->si_lasti == BFS_MAX_LASTI) - printf("WARNING: filesystem %s was created with 512 inodes, the real maximum is 511, mounting anyway\n", s->s_id); + printf("NOTE: filesystem %s was created with 512 inodes, the real maximum is 511, mounting anyway\n", s->s_id); else if (info->si_lasti > BFS_MAX_LASTI) { printf("Impossible last inode number %lu > %d on %s\n", info->si_lasti, BFS_MAX_LASTI, s->s_id); goto out1; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index f58e03d1775d..8ed71b3b2546 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1256,6 +1256,7 @@ static int cluster_pages_for_defrag(struct inode *inode, u64 page_end; u64 page_cnt; u64 start = (u64)start_index << PAGE_SHIFT; + u64 search_start; int ret; int i; int i_done; @@ -1352,6 +1353,40 @@ static int cluster_pages_for_defrag(struct inode *inode,

lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end - 1, &cached_state); + + /* + * When defragmenting we skip ranges that have holes or inline extents, + * (check should_defrag_range()), to avoid unnecessary IO and wasting + * space. At btrfs_defrag_file(), we check if a range should be defragged + * before locking the inode and then, if it should, we trigger a sync + * page cache readahead - we lock the inode only after that to avoid + * blocking for too long other tasks that possibly want to operate on + * other file ranges. But before we were able to get the inode lock, + * some other task may have punched a hole in the range, or we may have + * now an inline extent, in which case we should not defrag. So check + * for that here, where we have the inode and the range locked, and bail + * out if that happened. + */ + search_start = page_start; + while (search_start < page_end) { + struct extent_map *em; + + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, search_start, + page_end - search_start, 0); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto out_unlock_range; + } + if (em->block_start >= EXTENT_MAP_LAST_BYTE) { + free_extent_map(em); + /* Ok, 0 means we did not defrag anything */ + ret = 0; + goto out_unlock_range; + } + search_start = extent_map_end(em); + free_extent_map(em); + } + clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end - 1, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, &cached_state); @@ -1382,6 +1417,10 @@ static int cluster_pages_for_defrag(struct inode *inode, btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return i_done; + +out_unlock_range: + unlock_extent_cached(&BTRFS_I(inode)->io_tree, + page_start, page_end - 1, &cached_state); out: for (i = 0; i < i_done; i++) { unlock_page(pages[i]); diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index e84efc01512e..ec7387266190 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -23,6 +23,9 @@ #define FSCRYPT_CONTEXT_V1 1 #define FSCRYPT_CONTEXT_V2 2

+/* Keep this in sync with include/uapi/linux/fscrypt.h */ +#define FSCRYPT_MODE_MAX FSCRYPT_MODE_ADIANTUM + struct fscrypt_context_v1 { u8 version; /* FSCRYPT_CONTEXT_V1 */ u8 contents_encryption_mode; @@ -387,7 +390,7 @@ struct fscrypt_master_key { spinlock_t mk_decrypted_inodes_lock;

/* Per-mode tfms for DIRECT_KEY policies, allocated on-demand */ - struct crypto_skcipher *mk_mode_keys[__FSCRYPT_MODE_MAX + 1]; + struct crypto_skcipher *mk_mode_keys[FSCRYPT_MODE_MAX + 1];

} __randomize_layout;

diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index bb3b7fcfdd48..a5a40a76b8ed 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -58,8 +58,8 @@ int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, if (err) return err;

- /* ... in case we looked up ciphertext name before key was added */ - if (dentry->d_flags & DCACHE_ENCRYPTED_NAME) + /* ... in case we looked up no-key name before key was added */ + if (fscrypt_is_nokey_name(dentry)) return -ENOKEY;

if (!fscrypt_has_permitted_context(dir, inode)) @@ -83,9 +83,9 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) return err;

- /* ... in case we looked up ciphertext name(s) before key was added */ - if ((old_dentry->d_flags | new_dentry->d_flags) & - DCACHE_ENCRYPTED_NAME) + /* ... in case we looked up no-key name(s) before key was added */ + if (fscrypt_is_nokey_name(old_dentry) || + fscrypt_is_nokey_name(new_dentry)) return -ENOKEY;

if (old_dir != new_dir) { diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 75898340eb46..3e86f75b532a 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -55,6 +55,8 @@ static struct fscrypt_mode * select_encryption_mode(const union fscrypt_policy *policy, const struct inode *inode) { + BUILD_BUG_ON(ARRAY_SIZE(available_modes) != FSCRYPT_MODE_MAX + 1); + if (S_ISREG(inode->i_mode)) return &available_modes[fscrypt_policy_contents_mode(policy)];

diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 4072ba644595..8e1b10861c10 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -55,7 +55,8 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, return false; }

- if (policy->flags & ~FSCRYPT_POLICY_FLAGS_VALID) { + if (policy->flags & ~(FSCRYPT_POLICY_FLAGS_PAD_MASK | + FSCRYPT_POLICY_FLAG_DIRECT_KEY)) { fscrypt_warn(inode, "Unsupported encryption flags (0x%02x)", policy->flags); @@ -76,7 +77,8 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, return false; }

- if (policy->flags & ~FSCRYPT_POLICY_FLAGS_VALID) { + if (policy->flags & ~(FSCRYPT_POLICY_FLAGS_PAD_MASK | + FSCRYPT_POLICY_FLAG_DIRECT_KEY)) { fscrypt_warn(inode, "Unsupported encryption flags (0x%02x)", policy->flags); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 36a81b57012a..59038e361337 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2192,6 +2192,9 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, if (!dentry->d_name.len) return -EINVAL;

+ if (fscrypt_is_nokey_name(dentry)) + return -ENOKEY; + #ifdef CONFIG_UNICODE if (ext4_has_strict_mode(sbi) && IS_CASEFOLDED(dir) && sbi->s_encoding && utf8_validate(sbi->s_encoding, &dentry->d_name)) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 920658ca8777..06568467b0c2 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -455,19 +455,17 @@ static bool system_going_down(void)

static void ext4_handle_error(struct super_block *sb) { + journal_t *journal = EXT4_SB(sb)->s_journal; + if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1);

- if (sb_rdonly(sb)) + if (sb_rdonly(sb) || test_opt(sb, ERRORS_CONT)) return;

- if (!test_opt(sb, ERRORS_CONT)) { - journal_t *journal = EXT4_SB(sb)->s_journal; - - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; - if (journal) - jbd2_journal_abort(journal, -EIO); - } + EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; + if (journal) + jbd2_journal_abort(journal, -EIO); /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index c966ccc44c15..a57219c51c01 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1596,7 +1596,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) goto out; }

- if (NM_I(sbi)->dirty_nat_cnt == 0 && + if (NM_I(sbi)->nat_cnt[DIRTY_NAT] == 0 && SIT_I(sbi)->dirty_sentries == 0 && prefree_segments(sbi) == 0) { f2fs_flush_sit_entries(sbi, cpc); diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 9b0bedd82581..d8d64447bc94 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -107,8 +107,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->node_pages = NODE_MAPPING(sbi)->nrpages; if (sbi->meta_inode) si->meta_pages = META_MAPPING(sbi)->nrpages; - si->nats = NM_I(sbi)->nat_cnt; - si->dirty_nats = NM_I(sbi)->dirty_nat_cnt; + si->nats = NM_I(sbi)->nat_cnt[TOTAL_NAT]; + si->dirty_nats = NM_I(sbi)->nat_cnt[DIRTY_NAT]; si->sits = MAIN_SEGS(sbi); si->dirty_sits = SIT_I(sbi)->dirty_sentries; si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID]; @@ -254,9 +254,10 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID] + NM_I(sbi)->nid_cnt[PREALLOC_NID]) * sizeof(struct free_nid); - si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry); - si->cache_mem += NM_I(sbi)->dirty_nat_cnt * - sizeof(struct nat_entry_set); + si->cache_mem += NM_I(sbi)->nat_cnt[TOTAL_NAT] * + sizeof(struct nat_entry); + si->cache_mem += NM_I(sbi)->nat_cnt[DIRTY_NAT] * + sizeof(struct nat_entry_set); si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages); for (i = 0; i < MAX_INO_ENTRY; i++) si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 63440abe58c4..4ca3c2a0a0f5 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -797,6 +797,13 @@ enum nid_state { MAX_NID_STATE, };

+enum nat_state { + TOTAL_NAT, + DIRTY_NAT, + RECLAIMABLE_NAT, + MAX_NAT_STATE, +}; + struct f2fs_nm_info { block_t nat_blkaddr; /* base disk address of NAT */ nid_t max_nid; /* maximum possible node ids */ @@ -812,8 +819,7 @@ struct f2fs_nm_info { struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ struct list_head nat_entries; /* cached nat entry list (clean) */ spinlock_t nat_list_lock; /* protect clean nat entry list */ - unsigned int nat_cnt; /* the # of cached nat entries */ - unsigned int dirty_nat_cnt; /* total num of nat entries in set */ + unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */ unsigned int nat_blocks; /* # of nat blocks */

/* free node ids management */ @@ -2998,6 +3004,8 @@ bool f2fs_empty_dir(struct inode *dir);

static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) { + if (fscrypt_is_nokey_name(dentry)) + return -ENOKEY; return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name, inode, inode->i_ino, inode->i_mode); } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 3ac2a4b32375..7ce33698ae38 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -62,8 +62,8 @@ bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type) sizeof(struct free_nid)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == NAT_ENTRIES) { - mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> - PAGE_SHIFT; + mem_size = (nm_i->nat_cnt[TOTAL_NAT] * + sizeof(struct nat_entry)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); if (excess_cached_nats(sbi)) res = false; @@ -177,7 +177,8 @@ static struct nat_entry *__init_nat_entry(struct f2fs_nm_info *nm_i, list_add_tail(&ne->list, &nm_i->nat_entries); spin_unlock(&nm_i->nat_list_lock);

- nm_i->nat_cnt++; + nm_i->nat_cnt[TOTAL_NAT]++; + nm_i->nat_cnt[RECLAIMABLE_NAT]++; return ne; }

@@ -207,7 +208,8 @@ static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i, static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e) { radix_tree_delete(&nm_i->nat_root, nat_get_nid(e)); - nm_i->nat_cnt--; + nm_i->nat_cnt[TOTAL_NAT]--; + nm_i->nat_cnt[RECLAIMABLE_NAT]--; __free_nat_entry(e); }

@@ -253,7 +255,8 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, if (get_nat_flag(ne, IS_DIRTY)) goto refresh_list;

- nm_i->dirty_nat_cnt++; + nm_i->nat_cnt[DIRTY_NAT]++; + nm_i->nat_cnt[RECLAIMABLE_NAT]--; set_nat_flag(ne, IS_DIRTY, true); refresh_list: spin_lock(&nm_i->nat_list_lock); @@ -273,7 +276,8 @@ static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,

set_nat_flag(ne, IS_DIRTY, false); set->entry_cnt--; - nm_i->dirty_nat_cnt--; + nm_i->nat_cnt[DIRTY_NAT]--; + nm_i->nat_cnt[RECLAIMABLE_NAT]++; }

static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i, @@ -2881,14 +2885,17 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) LIST_HEAD(sets); int err = 0;

- /* during unmount, let's flush nat_bits before checking dirty_nat_cnt */ + /* + * during unmount, let's flush nat_bits before checking + * nat_cnt[DIRTY_NAT]. + */ if (enabled_nat_bits(sbi, cpc)) { down_write(&nm_i->nat_tree_lock); remove_nats_in_journal(sbi); up_write(&nm_i->nat_tree_lock); }

- if (!nm_i->dirty_nat_cnt) + if (!nm_i->nat_cnt[DIRTY_NAT]) return 0;

down_write(&nm_i->nat_tree_lock); @@ -2899,7 +2906,8 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) * into nat entry set. */ if (enabled_nat_bits(sbi, cpc) || - !__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL)) + !__has_cursum_space(journal, + nm_i->nat_cnt[DIRTY_NAT], NAT_JOURNAL)) remove_nats_in_journal(sbi);

while ((found = __gang_lookup_nat_set(nm_i, @@ -3023,7 +3031,6 @@ static int init_node_manager(struct f2fs_sb_info *sbi) F2FS_RESERVED_NODE_NUM; nm_i->nid_cnt[FREE_NID] = 0; nm_i->nid_cnt[PREALLOC_NID] = 0; - nm_i->nat_cnt = 0; nm_i->ram_thresh = DEF_RAM_THRESHOLD; nm_i->ra_nid_pages = DEF_RA_NID_PAGES; nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD; @@ -3160,7 +3167,7 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) __del_from_nat_cache(nm_i, natvec[idx]); } } - f2fs_bug_on(sbi, nm_i->nat_cnt); + f2fs_bug_on(sbi, nm_i->nat_cnt[TOTAL_NAT]);

/* destroy nat set cache */ nid = 0; diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index e05af5df5648..4a2e7eaf2b02 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -123,13 +123,13 @@ static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,

static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi) { - return NM_I(sbi)->dirty_nat_cnt >= NM_I(sbi)->max_nid * + return NM_I(sbi)->nat_cnt[DIRTY_NAT] >= NM_I(sbi)->max_nid * NM_I(sbi)->dirty_nats_ratio / 100; }

static inline bool excess_cached_nats(struct f2fs_sb_info *sbi) { - return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD; + return NM_I(sbi)->nat_cnt[TOTAL_NAT] >= DEF_NAT_CACHE_THRESHOLD; }

static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index a467aca29cfe..3ceebaaee384 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -18,9 +18,7 @@ static unsigned int shrinker_run_no;

static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi) { - long count = NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt; - - return count > 0 ? count : 0; + return NM_I(sbi)->nat_cnt[RECLAIMABLE_NAT]; }

static unsigned long __count_free_nids(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index fa461db696e7..a9a083232bcf 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2523,7 +2523,6 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, block_t total_sections, blocks_per_seg; struct f2fs_super_block *raw_super = (struct f2fs_super_block *) (bh->b_data + F2FS_SUPER_OFFSET); - unsigned int blocksize; size_t crc_offset = 0; __u32 crc = 0;

@@ -2557,10 +2556,10 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, }

/* Currently, support only 4KB block size */ - blocksize = 1 << le32_to_cpu(raw_super->log_blocksize); - if (blocksize != F2FS_BLKSIZE) { - f2fs_info(sbi, "Invalid blocksize (%u), supports only 4KB", - blocksize); + if (le32_to_cpu(raw_super->log_blocksize) != F2FS_BLKSIZE_BITS) { + f2fs_info(sbi, "Invalid log_blocksize (%u), supports only %u", + le32_to_cpu(raw_super->log_blocksize), + F2FS_BLKSIZE_BITS); return -EFSCORRUPTED; }

diff --git a/fs/fcntl.c b/fs/fcntl.c index 3d40771e8e7c..3dc90e5293e6 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -779,9 +779,10 @@ void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; + unsigned long flags; struct pid *pid; - read_lock(&fown->lock); + read_lock_irqsave(&fown->lock, flags);

type = fown->pid_type; pid = fown->pid; @@ -802,7 +803,7 @@ void send_sigio(struct fown_struct *fown, int fd, int band) read_unlock(&tasklist_lock); } out_unlock_fown: - read_unlock(&fown->lock); + read_unlock_irqrestore(&fown->lock, flags); }

static void send_sigurg_to_task(struct task_struct *p, @@ -817,9 +818,10 @@ int send_sigurg(struct fown_struct *fown) struct task_struct *p; enum pid_type type; struct pid *pid; + unsigned long flags; int ret = 0; - read_lock(&fown->lock); + read_lock_irqsave(&fown->lock, flags);

type = fown->pid_type; pid = fown->pid; @@ -842,7 +844,7 @@ int send_sigurg(struct fown_struct *fown) read_unlock(&tasklist_lock); } out_unlock_fown: - read_unlock(&fown->lock); + read_unlock_irqrestore(&fown->lock, flags); return ret; }

diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h index 778275f48a87..5a7091746f68 100644 --- a/fs/jffs2/jffs2_fs_sb.h +++ b/fs/jffs2/jffs2_fs_sb.h @@ -38,6 +38,7 @@ struct jffs2_mount_opts { * users. This is implemented simply by means of not allowing the * latter users to write to the file system if the amount if the * available space is less then 'rp_size'. */ + bool set_rp_size; unsigned int rp_size; };

diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 60636b2e35ea..6839a61e8ff1 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -88,7 +88,7 @@ static int jffs2_show_options(struct seq_file *s, struct dentry *root)

if (opts->override_compr) seq_printf(s, ",compr=%s", jffs2_compr_name(opts->compr)); - if (opts->rp_size) + if (opts->set_rp_size) seq_printf(s, ",rp_size=%u", opts->rp_size / 1024);

return 0; @@ -208,11 +208,8 @@ static int jffs2_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_rp_size: if (result.uint_32 > UINT_MAX / 1024) return invalf(fc, "jffs2: rp_size unrepresentable"); - opt = result.uint_32 * 1024; - if (opt > c->mtd->size) - return invalf(fc, "jffs2: Too large reserve pool specified, max is %llu KB", - c->mtd->size / 1024); - c->mount_opts.rp_size = opt; + c->mount_opts.rp_size = result.uint_32 * 1024; + c->mount_opts.set_rp_size = true; break; default: return -EINVAL; @@ -231,8 +228,10 @@ static inline void jffs2_update_mount_opts(struct fs_context *fc) c->mount_opts.override_compr = new_c->mount_opts.override_compr; c->mount_opts.compr = new_c->mount_opts.compr; } - if (new_c->mount_opts.rp_size) + if (new_c->mount_opts.set_rp_size) { + c->mount_opts.set_rp_size = new_c->mount_opts.set_rp_size; c->mount_opts.rp_size = new_c->mount_opts.rp_size; + } mutex_unlock(&c->alloc_sem); }

@@ -272,6 +271,10 @@ static int jffs2_fill_super(struct super_block *sb, struct fs_context *fc) c->mtd = sb->s_mtd; c->os_priv = sb;

+ if (c->mount_opts.rp_size > c->mtd->size) + return invalf(fc, "jffs2: Too large reserve pool specified, max is %llu KB", + c->mtd->size / 1024); + /* Initialize JFFS2 superblock locks, the further initialization will * be done later */ mutex_init(&c->alloc_sem); diff --git a/fs/namespace.c b/fs/namespace.c index 2adfe7b166a3..76ea92994d26 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -156,10 +156,10 @@ static inline void mnt_add_count(struct mount *mnt, int n) /* * vfsmount lock must be held for write */ -unsigned int mnt_get_count(struct mount *mnt) +int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP - unsigned int count = 0; + int count = 0; int cpu;

for_each_possible_cpu(cpu) { @@ -1123,6 +1123,7 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); + int count;

rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { @@ -1146,7 +1147,9 @@ static void mntput_no_expire(struct mount *mnt) */ smp_mb(); mnt_add_count(mnt, -1); - if (mnt_get_count(mnt)) { + count = mnt_get_count(mnt); + if (count != 0) { + WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 04c57066a11a..b90642b022eb 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -96,7 +96,7 @@ static void nfs4_evict_inode(struct inode *inode) nfs_inode_return_delegation_noreclaim(inode); /* Note that above delegreturn would trigger pnfs return-on-close */ pnfs_return_layout(inode); - pnfs_destroy_layout(NFS_I(inode)); + pnfs_destroy_layout_final(NFS_I(inode)); /* First call standard NFS clear_inode() code */ nfs_clear_inode(inode); } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 9c2b07ce57b2..9fd115c4d0a2 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -294,6 +294,7 @@ void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) { struct inode *inode; + unsigned long i_state;

if (!lo) return; @@ -304,8 +305,12 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) if (!list_empty(&lo->plh_segs)) WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n"); pnfs_detach_layout_hdr(lo); + i_state = inode->i_state; spin_unlock(&inode->i_lock); pnfs_free_layout_hdr(lo); + /* Notify pnfs_destroy_layout_final() that we're done */ + if (i_state & (I_FREEING | I_CLEAR)) + wake_up_var(lo); } }

@@ -723,8 +728,7 @@ pnfs_free_lseg_list(struct list_head *free_me) } }

-void -pnfs_destroy_layout(struct nfs_inode *nfsi) +static struct pnfs_layout_hdr *__pnfs_destroy_layout(struct nfs_inode *nfsi) { struct pnfs_layout_hdr *lo; LIST_HEAD(tmp_list); @@ -742,9 +746,34 @@ pnfs_destroy_layout(struct nfs_inode *nfsi) pnfs_put_layout_hdr(lo); } else spin_unlock(&nfsi->vfs_inode.i_lock); + return lo; +} + +void pnfs_destroy_layout(struct nfs_inode *nfsi) +{ + __pnfs_destroy_layout(nfsi); } EXPORT_SYMBOL_GPL(pnfs_destroy_layout);

+static bool pnfs_layout_removed(struct nfs_inode *nfsi, + struct pnfs_layout_hdr *lo) +{ + bool ret; + + spin_lock(&nfsi->vfs_inode.i_lock); + ret = nfsi->layout != lo; + spin_unlock(&nfsi->vfs_inode.i_lock); + return ret; +} + +void pnfs_destroy_layout_final(struct nfs_inode *nfsi) +{ + struct pnfs_layout_hdr *lo = __pnfs_destroy_layout(nfsi); + + if (lo) + wait_var_event(lo, pnfs_layout_removed(nfsi, lo)); +} + static bool pnfs_layout_add_bulk_destroy_list(struct inode *inode, struct list_head *layout_list) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index f8a38065c7e4..63da33a92d83 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -255,6 +255,7 @@ struct pnfs_layout_segment *pnfs_layout_process(struct nfs4_layoutget *lgp); void pnfs_layoutget_free(struct nfs4_layoutget *lgp); void pnfs_free_lseg_list(struct list_head *tmp_list); void pnfs_destroy_layout(struct nfs_inode *); +void pnfs_destroy_layout_final(struct nfs_inode *); void pnfs_destroy_all_layouts(struct nfs_client *); int pnfs_destroy_layouts_byfsid(struct nfs_client *clp, struct nfs_fsid *fsid, @@ -651,6 +652,10 @@ static inline void pnfs_destroy_layout(struct nfs_inode *nfsi) { }

+static inline void pnfs_destroy_layout_final(struct nfs_inode *nfsi) +{ +} + static inline struct pnfs_layout_segment * pnfs_get_lseg(struct pnfs_layout_segment *lseg) { diff --git a/fs/pnode.h b/fs/pnode.h index 49a058c73e4c..26f74e092bd9 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -44,7 +44,7 @@ int propagate_mount_busy(struct mount *, int); void propagate_mount_unlock(struct mount *); void mnt_release_group_id(struct mount *); int get_dominating_id(struct mount *mnt, const struct path *root); -unsigned int mnt_get_count(struct mount *mnt); +int mnt_get_count(struct mount *mnt); void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *); void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c index a6f856f341dc..c5562c871c8b 100644 --- a/fs/quota/quota_tree.c +++ b/fs/quota/quota_tree.c @@ -62,7 +62,7 @@ static ssize_t read_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf)

memset(buf, 0, info->dqi_usable_bs); return sb->s_op->quota_read(sb, info->dqi_type, buf, - info->dqi_usable_bs, blk << info->dqi_blocksize_bits); + info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits); }

static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) @@ -71,7 +71,7 @@ static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) ssize_t ret;

ret = sb->s_op->quota_write(sb, info->dqi_type, buf, - info->dqi_usable_bs, blk << info->dqi_blocksize_bits); + info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits); if (ret != info->dqi_usable_bs) { quota_error(sb, "dquota write failed"); if (ret >= 0) @@ -284,7 +284,7 @@ static uint find_free_dqentry(struct qtree_mem_dqinfo *info, blk); goto out_buf; } - dquot->dq_off = (blk << info->dqi_blocksize_bits) + + dquot->dq_off = ((loff_t)blk << info->dqi_blocksize_bits) + sizeof(struct qt_disk_dqdbheader) + i * info->dqi_entry_size; kfree(buf); @@ -559,7 +559,7 @@ static loff_t find_block_dqentry(struct qtree_mem_dqinfo *info, ret = -EIO; goto out_buf; } else { - ret = (blk << info->dqi_blocksize_bits) + sizeof(struct + ret = ((loff_t)blk << info->dqi_blocksize_bits) + sizeof(struct qt_disk_dqdbheader) + i * info->dqi_entry_size; } out_buf: diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index bb4973aefbb1..9e64e23014e8 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -454,6 +454,12 @@ static int is_leaf(char *buf, int blocksize, struct buffer_head *bh) "(second one): %h", ih); return 0; } + if (is_direntry_le_ih(ih) && (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE))) { + reiserfs_warning(NULL, "reiserfs-5093", + "item entry count seems wrong %h", + ih); + return 0; + } prev_location = ih_location(ih); }

diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 6c0e19f7a21f..a5e5e9b9d4e3 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -278,6 +278,15 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry, return d_splice_alias(inode, dentry); }

+static int ubifs_prepare_create(struct inode *dir, struct dentry *dentry, + struct fscrypt_name *nm) +{ + if (fscrypt_is_nokey_name(dentry)) + return -ENOKEY; + + return fscrypt_setup_filename(dir, &dentry->d_name, 0, nm); +} + static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { @@ -301,7 +310,7 @@ static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode, if (err) return err;

- err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) goto out_budg;

@@ -961,7 +970,7 @@ static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (err) return err;

- err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) goto out_budg;

@@ -1046,7 +1055,7 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, return err; }

- err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) { kfree(dev); goto out_budg; @@ -1130,7 +1139,7 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, if (err) return err;

- err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) goto out_budg;

diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index f622f7460ed8..032e5bcf9701 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -100,6 +100,35 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry) dentry->d_flags &= ~DCACHE_ENCRYPTED_NAME; }

+/** + * fscrypt_is_nokey_name() - test whether a dentry is a no-key name + * @dentry: the dentry to check + * + * This returns true if the dentry is a no-key dentry. A no-key dentry is a + * dentry that was created in an encrypted directory that hasn't had its + * encryption key added yet. Such dentries may be either positive or negative. + * + * When a filesystem is asked to create a new filename in an encrypted directory + * and the new filename's dentry is a no-key dentry, it must fail the operation + * with ENOKEY. This includes ->create(), ->mkdir(), ->mknod(), ->symlink(), + * ->rename(), and ->link(). (However, ->rename() and ->link() are already + * handled by fscrypt_prepare_rename() and fscrypt_prepare_link().) + * + * This is necessary because creating a filename requires the directory's + * encryption key, but just checking for the key on the directory inode during + * the final filesystem operation doesn't guarantee that the key was available + * during the preceding dentry lookup. And the key must have already been + * available during the dentry lookup in order for it to have been checked + * whether the filename already exists in the directory and for the new file's + * dentry not to be invalidated due to it incorrectly having the no-key flag. + * + * Return: %true if the dentry is a no-key name + */ +static inline bool fscrypt_is_nokey_name(const struct dentry *dentry) +{ + return dentry->d_flags & DCACHE_ENCRYPTED_NAME; +} + /* crypto.c */ extern void fscrypt_enqueue_decrypt_work(struct work_struct *); extern struct fscrypt_ctx *fscrypt_get_ctx(gfp_t); @@ -290,6 +319,11 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry) { }

+static inline bool fscrypt_is_nokey_name(const struct dentry *dentry) +{ + return false; +} + /* crypto.c */ static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) { diff --git a/include/linux/of.h b/include/linux/of.h index 844f89e1b039..a7621e2b440a 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1282,6 +1282,7 @@ static inline int of_get_available_child_count(const struct device_node *np) #define _OF_DECLARE(table, name, compat, fn, fn_type) \ static const struct of_device_id __of_table_##name \ __used __section(__##table##_of_table) \ + __aligned(__alignof__(struct of_device_id)) \ = { .compatible = compat, \ .data = (fn == (fn_type)NULL) ? fn : fn } #else diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index 5ed721ad5b19..af2a44c08683 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -28,4 +28,9 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x))

+#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) + +#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) + #endif /* _UAPI_LINUX_CONST_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 8938b76c4ee3..7857aa413627 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -14,7 +14,7 @@ #ifndef _UAPI_LINUX_ETHTOOL_H #define _UAPI_LINUX_ETHTOOL_H

-#include <linux/kernel.h> +#include <linux/const.h> #include <linux/types.h> #include <linux/if_ether.h>

diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index 39ccfe9311c3..b14f436f4ebd 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -17,7 +17,6 @@ #define FSCRYPT_POLICY_FLAGS_PAD_32 0x03 #define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 -#define FSCRYPT_POLICY_FLAGS_VALID 0x07

/* Encryption algorithms */ #define FSCRYPT_MODE_AES_256_XTS 1 @@ -25,7 +24,7 @@ #define FSCRYPT_MODE_AES_128_CBC 5 #define FSCRYPT_MODE_AES_128_CTS 6 #define FSCRYPT_MODE_ADIANTUM 9 -#define __FSCRYPT_MODE_MAX 9 +/* If adding a mode number > 9, update FSCRYPT_MODE_MAX in fscrypt_private.h */

/* * Legacy policy version; ad-hoc KDF and no key verification. @@ -162,7 +161,7 @@ struct fscrypt_get_key_status_arg { #define FS_POLICY_FLAGS_PAD_32 FSCRYPT_POLICY_FLAGS_PAD_32 #define FS_POLICY_FLAGS_PAD_MASK FSCRYPT_POLICY_FLAGS_PAD_MASK #define FS_POLICY_FLAG_DIRECT_KEY FSCRYPT_POLICY_FLAG_DIRECT_KEY -#define FS_POLICY_FLAGS_VALID FSCRYPT_POLICY_FLAGS_VALID +#define FS_POLICY_FLAGS_VALID 0x07 /* contains old flags only */ #define FS_ENCRYPTION_MODE_INVALID 0 /* never used */ #define FS_ENCRYPTION_MODE_AES_256_XTS FSCRYPT_MODE_AES_256_XTS #define FS_ENCRYPTION_MODE_AES_256_GCM 2 /* never used */ diff --git a/include/uapi/linux/kernel.h b/include/uapi/linux/kernel.h index 0ff8f7477847..fadf2db71fe8 100644 --- a/include/uapi/linux/kernel.h +++ b/include/uapi/linux/kernel.h @@ -3,13 +3,6 @@ #define _UAPI_LINUX_KERNEL_H

#include <linux/sysinfo.h> - -/* - * 'kernel.h' contains some often-used function prototypes etc - */ -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) -#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) - -#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) +#include <linux/const.h>

#endif /* _UAPI_LINUX_KERNEL_H */ diff --git a/include/uapi/linux/lightnvm.h b/include/uapi/linux/lightnvm.h index f9a1be7fc696..ead2e72e5c88 100644 --- a/include/uapi/linux/lightnvm.h +++ b/include/uapi/linux/lightnvm.h @@ -21,7 +21,7 @@ #define _UAPI_LINUX_LIGHTNVM_H

#ifdef __KERNEL__ -#include <linux/kernel.h> +#include <linux/const.h> #include <linux/ioctl.h> #else /* __KERNEL__ */ #include <stdio.h> diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h index c36177a86516..a1fd6173e2db 100644 --- a/include/uapi/linux/mroute6.h +++ b/include/uapi/linux/mroute6.h @@ -2,7 +2,7 @@ #ifndef _UAPI__LINUX_MROUTE6_H #define _UAPI__LINUX_MROUTE6_H

-#include <linux/kernel.h> +#include <linux/const.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/in6.h> /* For struct sockaddr_in6. */ diff --git a/include/uapi/linux/netfilter/x_tables.h b/include/uapi/linux/netfilter/x_tables.h index a8283f7dbc51..b8c6bb233ac1 100644 --- a/include/uapi/linux/netfilter/x_tables.h +++ b/include/uapi/linux/netfilter/x_tables.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_X_TABLES_H #define _UAPI_X_TABLES_H -#include <linux/kernel.h> +#include <linux/const.h> #include <linux/types.h>

#define XT_FUNCTION_MAXNAMELEN 30 diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 0a4d73317759..622c78c821aa 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -2,7 +2,7 @@ #ifndef _UAPI__LINUX_NETLINK_H #define _UAPI__LINUX_NETLINK_H

-#include <linux/kernel.h> +#include <linux/const.h> #include <linux/socket.h> /* for __kernel_sa_family_t */ #include <linux/types.h>

diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 87aa2a6d9125..cc453ed0e65e 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -23,7 +23,7 @@ #ifndef _UAPI_LINUX_SYSCTL_H #define _UAPI_LINUX_SYSCTL_H

-#include <linux/kernel.h> +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h>

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index f684c82efc2e..79682c23407c 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -914,6 +914,8 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) opt = fs_parse(fc, &cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { if (strcmp(param->key, "source") == 0) { + if (fc->source) + return invalf(fc, "Multiple sources not supported"); fc->source = param->string; param->string = NULL; return 0; diff --git a/kernel/module.c b/kernel/module.c index 45513909b01d..9e9af40698ff 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1863,7 +1863,6 @@ static int mod_sysfs_init(struct module *mod) if (err) mod_kobject_put(mod);

- /* delay uevent until full sysfs population */ out: return err; } @@ -1900,7 +1899,6 @@ static int mod_sysfs_setup(struct module *mod, add_sect_attrs(mod, info); add_notes_attrs(mod, info);

- kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD); return 0;

out_unreg_modinfo_attrs: @@ -3608,6 +3606,9 @@ static noinline int do_init_module(struct module *mod) blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_LIVE, mod);

+ /* Delay uevent until module has finished its init routine */ + kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD); + /* * We need to finish all async code before the module init sequence * is done. This has potential to deadlock. For example, a newly @@ -3953,6 +3954,7 @@ static int load_module(struct load_info *info, const char __user *uargs, MODULE_STATE_GOING, mod); klp_module_going(mod); bug_cleanup: + mod->state = MODULE_STATE_GOING; /* module_bug_cleanup needs module_mutex protection */ mutex_lock(&module_mutex); module_bug_cleanup(mod); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 5c9fcc72460d..4419486d7413 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -916,13 +916,6 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) */ if (tick_do_timer_cpu == cpu) return false; - /* - * Boot safety: make sure the timekeeping duty has been - * assigned before entering dyntick-idle mode, - * tick_do_timer_cpu is TICK_DO_TIMER_BOOT - */ - if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_BOOT)) - return false;

/* Should not happen for nohz-full */ if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 2b797a71e9bd..f2b1305e79d2 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1597,6 +1597,21 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, return err; }

+static void taprio_reset(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int i; + + hrtimer_cancel(&q->advance_timer); + if (q->qdiscs) { + for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++) + qdisc_reset(q->qdiscs[i]); + } + sch->qstats.backlog = 0; + sch->q.qlen = 0; +} + static void taprio_destroy(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); @@ -1607,7 +1622,6 @@ static void taprio_destroy(struct Qdisc *sch) list_del(&q->taprio_list); spin_unlock(&taprio_list_lock);

- hrtimer_cancel(&q->advance_timer);

taprio_disable_offload(dev, q, NULL);

@@ -1954,6 +1968,7 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { .init = taprio_init, .change = taprio_change, .destroy = taprio_destroy, + .reset = taprio_reset, .peek = taprio_peek, .dequeue = taprio_dequeue, .enqueue = taprio_enqueue, diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index ec501fbaabe4..0c5b7a54ca81 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -717,8 +717,13 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream, runtime->boundary *= 2;

/* clear the buffer for avoiding possible kernel info leaks */ - if (runtime->dma_area && !substream->ops->copy_user) - memset(runtime->dma_area, 0, runtime->dma_bytes); + if (runtime->dma_area && !substream->ops->copy_user) { + size_t size = runtime->dma_bytes; + + if (runtime->info & SNDRV_PCM_INFO_MMAP) + size = PAGE_ALIGN(size); + memset(runtime->dma_area, 0, size); + }

snd_pcm_timer_resolution_change(substream); snd_pcm_set_state(substream, SNDRV_PCM_STATE_SETUP); diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 94db4683cfaf..6a3543b8455f 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -72,11 +72,21 @@ static inline unsigned short snd_rawmidi_file_flags(struct file *file) } }

-static inline int snd_rawmidi_ready(struct snd_rawmidi_substream *substream) +static inline bool __snd_rawmidi_ready(struct snd_rawmidi_runtime *runtime) +{ + return runtime->avail >= runtime->avail_min; +} + +static bool snd_rawmidi_ready(struct snd_rawmidi_substream *substream) { struct snd_rawmidi_runtime *runtime = substream->runtime; + unsigned long flags; + bool ready;

- return runtime->avail >= runtime->avail_min; + spin_lock_irqsave(&runtime->lock, flags); + ready = __snd_rawmidi_ready(runtime); + spin_unlock_irqrestore(&runtime->lock, flags); + return ready; }

static inline int snd_rawmidi_ready_append(struct snd_rawmidi_substream *substream, @@ -945,7 +955,7 @@ int snd_rawmidi_receive(struct snd_rawmidi_substream *substream, if (result > 0) { if (runtime->event) schedule_work(&runtime->event_work); - else if (snd_rawmidi_ready(substream)) + else if (__snd_rawmidi_ready(runtime)) wake_up(&runtime->sleep); } spin_unlock_irqrestore(&runtime->lock, flags); @@ -1024,7 +1034,7 @@ static ssize_t snd_rawmidi_read(struct file *file, char __user *buf, size_t coun result = 0; while (count > 0) { spin_lock_irq(&runtime->lock); - while (!snd_rawmidi_ready(substream)) { + while (!__snd_rawmidi_ready(runtime)) { wait_queue_entry_t wait;

if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { @@ -1041,9 +1051,11 @@ static ssize_t snd_rawmidi_read(struct file *file, char __user *buf, size_t coun return -ENODEV; if (signal_pending(current)) return result > 0 ? result : -ERESTARTSYS; - if (!runtime->avail) - return result > 0 ? result : -EIO; spin_lock_irq(&runtime->lock); + if (!runtime->avail) { + spin_unlock_irq(&runtime->lock); + return result > 0 ? result : -EIO; + } } spin_unlock_irq(&runtime->lock); count1 = snd_rawmidi_kernel_read1(substream, @@ -1181,7 +1193,7 @@ int __snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int coun runtime->avail += count; substream->bytes += count; if (count > 0) { - if (runtime->drain || snd_rawmidi_ready(substream)) + if (runtime->drain || __snd_rawmidi_ready(runtime)) wake_up(&runtime->sleep); } return count; @@ -1370,9 +1382,11 @@ static ssize_t snd_rawmidi_write(struct file *file, const char __user *buf, return -ENODEV; if (signal_pending(current)) return result > 0 ? result : -ERESTARTSYS; - if (!runtime->avail && !timeout) - return result > 0 ? result : -EIO; spin_lock_irq(&runtime->lock); + if (!runtime->avail && !timeout) { + spin_unlock_irq(&runtime->lock); + return result > 0 ? result : -EIO; + } } spin_unlock_irq(&runtime->lock); count1 = snd_rawmidi_kernel_write1(substream, buf, NULL, count); @@ -1452,6 +1466,7 @@ static void snd_rawmidi_proc_info_read(struct snd_info_entry *entry, struct snd_rawmidi *rmidi; struct snd_rawmidi_substream *substream; struct snd_rawmidi_runtime *runtime; + unsigned long buffer_size, avail, xruns;

rmidi = entry->private_data; snd_iprintf(buffer, "%s\n\n", rmidi->name); @@ -1470,13 +1485,16 @@ static void snd_rawmidi_proc_info_read(struct snd_info_entry *entry, " Owner PID : %d\n", pid_vnr(substream->pid)); runtime = substream->runtime; + spin_lock_irq(&runtime->lock); + buffer_size = runtime->buffer_size; + avail = runtime->avail; + spin_unlock_irq(&runtime->lock); snd_iprintf(buffer, " Mode : %s\n" " Buffer size : %lu\n" " Avail : %lu\n", runtime->oss ? "OSS compatible" : "native", - (unsigned long) runtime->buffer_size, - (unsigned long) runtime->avail); + buffer_size, avail); } } } @@ -1494,13 +1512,16 @@ static void snd_rawmidi_proc_info_read(struct snd_info_entry *entry, " Owner PID : %d\n", pid_vnr(substream->pid)); runtime = substream->runtime; + spin_lock_irq(&runtime->lock); + buffer_size = runtime->buffer_size; + avail = runtime->avail; + xruns = runtime->xruns; + spin_unlock_irq(&runtime->lock); snd_iprintf(buffer, " Buffer size : %lu\n" " Avail : %lu\n" " Overruns : %lu\n", - (unsigned long) runtime->buffer_size, - (unsigned long) runtime->avail, - (unsigned long) runtime->xruns); + buffer_size, avail, xruns); } } } diff --git a/sound/core/seq/seq_queue.h b/sound/core/seq/seq_queue.h index 9254c8dbe5e3..25d2d6b61007 100644 --- a/sound/core/seq/seq_queue.h +++ b/sound/core/seq/seq_queue.h @@ -26,10 +26,10 @@ struct snd_seq_queue { struct snd_seq_timer *timer; /* time keeper for this queue */ int owner; /* client that 'owns' the timer */ - unsigned int locked:1, /* timer is only accesibble by owner if set */ - klocked:1, /* kernel lock (after START) */ - check_again:1, - check_blocked:1; + bool locked; /* timer is only accesibble by owner if set */ + bool klocked; /* kernel lock (after START) */ + bool check_again; /* concurrent access happened during check */ + bool check_blocked; /* queue being checked */

unsigned int flags; /* status flags */ unsigned int info_flags; /* info for sync */ diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index 5ed721ad5b19..af2a44c08683 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,4 +28,9 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x))

+#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) + +#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) + #endif /* _UAPI_LINUX_CONST_H */