Linux 5.15.37

index d89cf802d9aa..6568823cf306 100644
@@ -669,7 +669,8 @@ static void __init kvm_use_magic_page(void)
 	on_each_cpu(kvm_map_magic_page, &features, 1);
 
 	/* Quick self-test to see if the mapping works */
-	if (fault_in_pages_readable((const char *)KVM_MAGIC_PAGE, sizeof(u32))) {
+	if (fault_in_readable((const char __user *)KVM_MAGIC_PAGE,
+			      sizeof(u32))) {
 		kvm_patching_worked = false;
 		return;
 	}

index f2da879264bc..3e053e2fd6b6 100644
@@ -1048,7 +1048,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 	if (new_ctx == NULL)
 		return 0;
 	if (!access_ok(new_ctx, ctx_size) ||
-	    fault_in_pages_readable((u8 __user *)new_ctx, ctx_size))
+	    fault_in_readable((char __user *)new_ctx, ctx_size))
 		return -EFAULT;
 
 	/*

@@ -1239,7 +1239,7 @@ SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx,
 #endif
 
 	if (!access_ok(ctx, sizeof(*ctx)) ||
-	    fault_in_pages_readable((u8 __user *)ctx, sizeof(*ctx)))
+	    fault_in_readable((char __user *)ctx, sizeof(*ctx)))
 		return -EFAULT;
 
 	/*

index bb9c077ac132..d1e1fc0acbea 100644
@@ -688,7 +688,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 	if (new_ctx == NULL)
 		return 0;
 	if (!access_ok(new_ctx, ctx_size) ||
-	    fault_in_pages_readable((u8 __user *)new_ctx, ctx_size))
+	    fault_in_readable((char __user *)new_ctx, ctx_size))
 		return -EFAULT;
 
 	/*

index 831b25c5e705..7f71bd4dcd0d 100644
@@ -205,7 +205,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 	fpregs_unlock();
 
 	if (ret) {
-		if (!fault_in_pages_writeable(buf_fx, fpu_user_xstate_size))
+		if (!fault_in_writeable(buf_fx, fpu_user_xstate_size))
 			goto retry;
 		return -EFAULT;
 	}

@@ -278,10 +278,9 @@ static int restore_fpregs_from_user(void __user *buf, u64 xrestore,
 		if (ret != -EFAULT)
 			return -EINVAL;
 
-		ret = fault_in_pages_readable(buf, size);
-		if (!ret)
+		if (!fault_in_readable(buf, size))
 			goto retry;
-		return ret;
+		return -EFAULT;
 	}
 
 	/*

67 lines not on this page · raw message

index 21909642ee4c..8fbb25913327 100644
@@ -336,7 +336,7 @@ int armada_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 	struct drm_armada_gem_pwrite *args = data;
 	struct armada_gem_object *dobj;
 	char __user *ptr;
-	int ret;
+	int ret = 0;
 
 	DRM_DEBUG_DRIVER("handle %u off %u size %u ptr 0x%llx\n",
 		args->handle, args->offset, args->size, args->ptr);

@@ -349,9 +349,8 @@ int armada_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 	if (!access_ok(ptr, args->size))
 		return -EFAULT;
 
-	ret = fault_in_pages_readable(ptr, args->size);
-	if (ret)
-		return ret;
+	if (fault_in_readable(ptr, args->size))
+		return -EFAULT;
 
 	dobj = armada_gem_object_lookup(file, args->handle);
 	if (dobj == NULL)

index 75680eecd2f7..2714ba02b176 100644
@@ -36,6 +36,7 @@
 /* Quirks */
 #define CQSPI_NEEDS_WR_DELAY		BIT(0)
 #define CQSPI_DISABLE_DAC_MODE		BIT(1)
+#define CQSPI_NO_SUPPORT_WR_COMPLETION	BIT(3)
 
 /* Capabilities */
 #define CQSPI_SUPPORTS_OCTAL		BIT(0)

@@ -83,6 +84,7 @@ struct cqspi_st {
 	u32			wr_delay;
 	bool			use_direct_mode;
 	struct cqspi_flash_pdata f_pdata[CQSPI_MAX_CHIPSELECT];
+	bool			wr_completion;
 };
 
 struct cqspi_driver_platdata {

@@ -797,9 +799,11 @@ static int cqspi_write_setup(struct cqspi_flash_pdata *f_pdata,
 	 * polling on the controller's side. spinand and spi-nor will take
 	 * care of polling the status register.
 	 */
-	reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
-	reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
-	writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+	if (cqspi->wr_completion) {
+		reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+		reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
+		writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+	}
 
 	reg = readl(reg_base + CQSPI_REG_SIZE);
 	reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;

@@ -1532,6 +1536,10 @@ static int cqspi_probe(struct platform_device *pdev)
 
 	cqspi->master_ref_clk_hz = clk_get_rate(cqspi->clk);
 	master->max_speed_hz = cqspi->master_ref_clk_hz;
+
+	/* write completion is supported by default */
+	cqspi->wr_completion = true;
+
 	ddata  = of_device_get_match_data(dev);
 	if (ddata) {
 		if (ddata->quirks & CQSPI_NEEDS_WR_DELAY)

@@ -1541,6 +1549,8 @@ static int cqspi_probe(struct platform_device *pdev)
 			master->mode_bits |= SPI_RX_OCTAL | SPI_TX_OCTAL;
 		if (!(ddata->quirks & CQSPI_DISABLE_DAC_MODE))
 			cqspi->use_direct_mode = true;
+		if (ddata->quirks & CQSPI_NO_SUPPORT_WR_COMPLETION)
+			cqspi->wr_completion = false;
 	}
 
 	ret = devm_request_irq(dev, irq, cqspi_irq_handler, 0,

@@ -1649,6 +1659,10 @@ static const struct cqspi_driver_platdata intel_lgm_qspi = {
 	.quirks = CQSPI_DISABLE_DAC_MODE,
 };
 
+static const struct cqspi_driver_platdata socfpga_qspi = {
+	.quirks = CQSPI_NO_SUPPORT_WR_COMPLETION,
+};
+
 static const struct of_device_id cqspi_dt_ids[] = {
 	{
 		.compatible = "cdns,qspi-nor",

@@ -1666,6 +1680,10 @@ static const struct of_device_id cqspi_dt_ids[] = {
 		.compatible = "intel,lgm-qspi",
 		.data = &intel_lgm_qspi,
 	},
+	{
+		.compatible = "intel,socfpga-qspi",
+		.data = (void *)&socfpga_qspi,
+	},
 	{ /* end of table */ }
 };
 

193 lines not on this page · raw message

index 6266a706bff7..044d584c3467 100644
@@ -7961,6 +7961,34 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	}
 
 	len = min(len, em->len - (start - em->start));
+
+	/*
+	 * If we have a NOWAIT request and the range contains multiple extents
+	 * (or a mix of extents and holes), then we return -EAGAIN to make the
+	 * caller fallback to a context where it can do a blocking (without
+	 * NOWAIT) request. This way we avoid doing partial IO and returning
+	 * success to the caller, which is not optimal for writes and for reads
+	 * it can result in unexpected behaviour for an application.
+	 *
+	 * When doing a read, because we use IOMAP_DIO_PARTIAL when calling
+	 * iomap_dio_rw(), we can end up returning less data then what the caller
+	 * asked for, resulting in an unexpected, and incorrect, short read.
+	 * That is, the caller asked to read N bytes and we return less than that,
+	 * which is wrong unless we are crossing EOF. This happens if we get a
+	 * page fault error when trying to fault in pages for the buffer that is
+	 * associated to the struct iov_iter passed to iomap_dio_rw(), and we
+	 * have previously submitted bios for other extents in the range, in
+	 * which case iomap_dio_rw() may return us EIOCBQUEUED if not all of
+	 * those bios have completed by the time we get the page fault error,
+	 * which we return back to our caller - we should only return EIOCBQUEUED
+	 * after we have submitted bios for all the extents in the range.
+	 */
+	if ((flags & IOMAP_NOWAIT) && len < length) {
+		free_extent_map(em);
+		ret = -EAGAIN;
+		goto unlock_err;
+	}
+
 	if (write) {
 		ret = btrfs_get_blocks_direct_write(&em, inode, dio_data,
 						    start, len);

index 6a863b3f6de0..bf53af8694f8 100644
@@ -2258,9 +2258,8 @@ static noinline int search_ioctl(struct inode *inode,
 	key.offset = sk->min_offset;
 
 	while (1) {
-		ret = fault_in_pages_writeable(ubuf + sk_offset,
-					       *buf_size - sk_offset);
-		if (ret)
+		ret = -EFAULT;
+		if (fault_in_writeable(ubuf + sk_offset, *buf_size - sk_offset))
 			break;
 
 		ret = btrfs_search_forward(root, &key, path, sk->min_transid);

index 9db829715652..16a41d0db55a 100644
@@ -287,7 +287,7 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 		if (!err)
 			return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
-					    NULL, 0);
+					    NULL, 0, 0);
 		if (err < 0)
 			return err;
 	}

index ac0e11bbb445..b25c1f8f7c4f 100644
@@ -74,7 +74,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		return generic_file_read_iter(iocb, to);
 	}
 
-	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, 0);
 	inode_unlock_shared(inode);
 
 	file_accessed(iocb->ki_filp);

@@ -566,7 +566,8 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ilock_shared)
 		iomap_ops = &ext4_iomap_overwrite_ops;
 	ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
-			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0);
+			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0,
+			   0);
 	if (ret == -ENOTBLK)
 		ret = 0;
 

index 0e14dc41ed4e..8ef92719c679 100644
@@ -4279,7 +4279,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		size_t target_size = 0;
 		int err;
 
-		if (iov_iter_fault_in_readable(from, iov_iter_count(from)))
+		if (fault_in_iov_iter_readable(from, iov_iter_count(from)))
 			set_inode_flag(inode, FI_NO_PREALLOC);
 
 		if ((iocb->ki_flags & IOCB_NOWAIT)) {

index bc50a9fa84a0..71e9e301e569 100644
@@ -1164,7 +1164,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 
  again:
 		err = -EFAULT;
-		if (iov_iter_fault_in_readable(ii, bytes))
+		if (fault_in_iov_iter_readable(ii, bytes))
 			break;
 
 		err = -ENOMEM;

95 lines not on this page · raw message

344 lines not on this page · raw message

450 lines not on this page · raw message

index 31a8f2f649b5..9012487da4c6 100644
@@ -150,6 +150,8 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *
 	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
 		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
 			break;
+		if (test_bit(HIF_MAY_DEMOTE, &gh->gh_iflags))
+			continue;
 		if (gh->gh_owner_pid == pid)
 			goto out;
 	}

@@ -325,6 +327,24 @@ static inline void glock_clear_object(struct gfs2_glock *gl, void *object)
 	spin_unlock(&gl->gl_lockref.lock);
 }
 
+static inline void gfs2_holder_allow_demote(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+
+	spin_lock(&gl->gl_lockref.lock);
+	set_bit(HIF_MAY_DEMOTE, &gh->gh_iflags);
+	spin_unlock(&gl->gl_lockref.lock);
+}
+
+static inline void gfs2_holder_disallow_demote(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+
+	spin_lock(&gl->gl_lockref.lock);
+	clear_bit(HIF_MAY_DEMOTE, &gh->gh_iflags);
+	spin_unlock(&gl->gl_lockref.lock);
+}
+
 extern void gfs2_inode_remember_delete(struct gfs2_glock *gl, u64 generation);
 extern bool gfs2_inode_already_deleted(struct gfs2_glock *gl, u64 generation);
 

index 0fe49770166e..ca42d310fd4d 100644
@@ -252,6 +252,7 @@ struct gfs2_lkstats {
 
 enum {
 	/* States */
+	HIF_MAY_DEMOTE		= 1,
 	HIF_HOLDER		= 6,  /* Set for gh that "holds" the glock */
 	HIF_WAIT		= 10,
 };

@@ -386,9 +387,8 @@ struct gfs2_inode {
 	u64 i_generation;
 	u64 i_eattr;
 	unsigned long i_flags;		/* GIF_... */
-	struct gfs2_glock *i_gl; /* Move into i_gh? */
+	struct gfs2_glock *i_gl;
 	struct gfs2_holder i_iopen_gh;
-	struct gfs2_holder i_gh; /* for prepare/commit_write only */
 	struct gfs2_qadata *i_qadata; /* quota allocation data */
 	struct gfs2_holder i_rgd_gh;
 	struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */

index 97119ec3b850..fe10d8a30f6b 100644
@@ -757,7 +757,7 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
 		 */
-		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+		if (unlikely(fault_in_iov_iter_readable(i, bytes))) {
 			status = -EFAULT;
 			break;
 		}

index 4ecd255e0511..468dcbba45bc 100644
@@ -31,6 +31,7 @@ struct iomap_dio {
 	atomic_t		ref;
 	unsigned		flags;
 	int			error;
+	size_t			done_before;
 	bool			wait_for_completion;
 
 	union {

@@ -124,6 +125,9 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
 		ret = generic_write_sync(iocb, ret);
 
+	if (ret > 0)
+		ret += dio->done_before;
+
 	kfree(dio);
 
 	return ret;

@@ -371,6 +375,8 @@ static loff_t iomap_dio_hole_iter(const struct iomap_iter *iter,
 	loff_t length = iov_iter_zero(iomap_length(iter), dio->submit.iter);
 
 	dio->size += length;
+	if (!length)
+		return -EFAULT;
 	return length;
 }
 

@@ -402,6 +408,8 @@ static loff_t iomap_dio_inline_iter(const struct iomap_iter *iomi,
 		copied = copy_to_iter(inline_data, length, iter);
 	}
 	dio->size += copied;
+	if (!copied)
+		return -EFAULT;
 	return copied;
 }
 

@@ -446,13 +454,21 @@ static loff_t iomap_dio_iter(const struct iomap_iter *iter,
  * may be pure data writes. In that case, we still need to do a full data sync
  * completion.
  *
+ * When page faults are disabled and @dio_flags includes IOMAP_DIO_PARTIAL,
+ * __iomap_dio_rw can return a partial result if it encounters a non-resident
+ * page in @iter after preparing a transfer.  In that case, the non-resident
+ * pages can be faulted in and the request resumed with @done_before set to the
+ * number of bytes previously transferred.  The request will then complete with
+ * the correct total number of bytes transferred; this is essential for
+ * completing partial requests asynchronously.
+ *
  * Returns -ENOTBLK In case of a page invalidation invalidation failure for
  * writes.  The callers needs to fall back to buffered I/O in this case.
  */
 struct iomap_dio *
 __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags)
+		unsigned int dio_flags, size_t done_before)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);

@@ -482,6 +498,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->dops = dops;
 	dio->error = 0;
 	dio->flags = 0;
+	dio->done_before = done_before;
 
 	dio->submit.iter = iter;
 	dio->submit.waiter = current;

@@ -577,6 +594,12 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (iov_iter_rw(iter) == READ && iomi.pos >= dio->i_size)
 		iov_iter_revert(iter, iomi.pos - dio->i_size);
 
+	if (ret == -EFAULT && dio->size && (dio_flags & IOMAP_DIO_PARTIAL)) {
+		if (!(iocb->ki_flags & IOCB_NOWAIT))
+			wait_for_completion = true;
+		ret = 0;
+	}
+
 	/* magic error code to fall back to buffered I/O */
 	if (ret == -ENOTBLK) {
 		wait_for_completion = true;

@@ -642,11 +665,11 @@ EXPORT_SYMBOL_GPL(__iomap_dio_rw);
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags)
+		unsigned int dio_flags, size_t done_before)
 {
 	struct iomap_dio *dio;
 
-	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags);
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, done_before);
 	if (IS_ERR_OR_NULL(dio))
 		return PTR_ERR_OR_ZERO(dio);
 	return iomap_dio_complete(dio);

index ab4f3362466d..a43adeacd930 100644
@@ -1829,7 +1829,7 @@ static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i,
 		 * pages being swapped out between us bringing them into memory
 		 * and doing the actual copying.
 		 */
-		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+		if (unlikely(fault_in_iov_iter_readable(i, bytes))) {
 			status = -EFAULT;
 			break;
 		}

index 43b1451bff53..54b9599640ef 100644
@@ -989,7 +989,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 		frame_vbo = pos & ~(frame_size - 1);
 		index = frame_vbo >> PAGE_SHIFT;
 
-		if (unlikely(iov_iter_fault_in_readable(from, bytes))) {
+		if (unlikely(fault_in_iov_iter_readable(from, bytes))) {
 			err = -EFAULT;
 			goto out;
 		}

index 7aa943edfc02..240eb932c014 100644
@@ -259,7 +259,7 @@ xfs_file_dio_read(
 	ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED);
 	if (ret)
 		return ret;
-	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0, 0);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	return ret;

@@ -569,7 +569,7 @@ xfs_file_dio_write_aligned(
 	}
 	trace_xfs_file_direct_write(iocb, from);
 	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, 0);
+			   &xfs_dio_write_ops, 0, 0);
 out_unlock:
 	if (iolock)
 		xfs_iunlock(ip, iolock);

@@ -647,7 +647,7 @@ xfs_file_dio_write_unaligned(
 
 	trace_xfs_file_direct_write(iocb, from);
 	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, flags);
+			   &xfs_dio_write_ops, flags, 0);
 
 	/*
 	 * Retry unaligned I/O with exclusive blocking semantics if the DIO

index 807f33553a8e..bced33b76bea 100644
@@ -852,7 +852,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 		ret = zonefs_file_dio_append(iocb, from);
 	else
 		ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
-				   &zonefs_write_dio_ops, 0);
+				   &zonefs_write_dio_ops, 0, 0);
 	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
 	    (ret > 0 || ret == -EIOCBQUEUED)) {
 		if (ret > 0)

@@ -987,7 +987,7 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		}
 		file_accessed(iocb->ki_filp);
 		ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
-				   &zonefs_read_dio_ops, 0);
+				   &zonefs_read_dio_ops, 0, 0);
 	} else {
 		ret = generic_file_read_iter(iocb, to);
 		if (ret == -EIO)

174 lines not on this page · raw message

index 364550dd19c4..bb1cc3fbc4ba 100644
@@ -18,6 +18,8 @@
  * that converting umax_value to int cannot overflow.
  */
 #define BPF_MAX_VAR_SIZ	(1 << 29)
+/* size of type_str_buf in bpf_verifier. */
+#define TYPE_STR_BUF_LEN 64
 
 /* Liveness marks, used for registers and spilled-regs (in stack slots).
  * Read marks propagate upwards until they find a write mark; they record that

@@ -474,6 +476,8 @@ struct bpf_verifier_env {
 	/* longest register parentage chain walked for liveness marking */
 	u32 longest_mark_read_walk;
 	bpfptr_t fd_array;
+	/* buffer used in reg_type_str() to generate reg_type string */
+	char type_str_buf[TYPE_STR_BUF_LEN];
 };
 
 __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,

@@ -535,4 +539,18 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			    u32 btf_id,
 			    struct bpf_attach_target_info *tgt_info);
 
+#define BPF_BASE_TYPE_MASK	GENMASK(BPF_BASE_TYPE_BITS - 1, 0)
+
+/* extract base type from bpf_{arg, return, reg}_type. */
+static inline u32 base_type(u32 type)
+{
+	return type & BPF_BASE_TYPE_MASK;
+}
+
+/* extract flags from an extended type. See bpf_type_flag in bpf.h. */
+static inline u32 type_flag(u32 type)
+{
+	return type & ~BPF_BASE_TYPE_MASK;
+}
+
 #endif /* _LINUX_BPF_VERIFIER_H */

index 24f8489583ca..829f2325ecba 100644
@@ -330,12 +330,19 @@ struct iomap_dio_ops {
   */
 #define IOMAP_DIO_OVERWRITE_ONLY	(1 << 1)
 
+/*
+ * When a page fault occurs, return a partial synchronous result and allow
+ * the caller to retry the rest of the operation after dealing with the page
+ * fault.
+ */
+#define IOMAP_DIO_PARTIAL		(1 << 2)
+
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags);
+		unsigned int dio_flags, size_t done_before);
 struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags);
+		unsigned int dio_flags, size_t done_before);
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 

index 90c2d7f3c7a8..04345ff97f8c 100644
@@ -2858,7 +2858,8 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_FORCE	0x10	/* get_user_pages read/write w/o permission */
 #define FOLL_NOWAIT	0x20	/* if a disk transfer is needed, start the IO
 				 * and return without waiting upon it */
-#define FOLL_POPULATE	0x40	/* fault in page */
+#define FOLL_POPULATE	0x40	/* fault in pages (with FOLL_MLOCK) */
+#define FOLL_NOFAULT	0x80	/* do not fault in pages */
 #define FOLL_HWPOISON	0x100	/* check page is hwpoisoned */
 #define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */

65 lines not on this page · raw message

index 207101a9c5c3..6350354f97e9 100644
@@ -35,6 +35,7 @@ struct iov_iter_state {
 
 struct iov_iter {
 	u8 iter_type;
+	bool nofault;
 	bool data_source;
 	size_t iov_offset;
 	size_t count;

@@ -133,7 +134,8 @@ size_t copy_page_from_iter_atomic(struct page *page, unsigned offset,
 				  size_t bytes, struct iov_iter *i);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 void iov_iter_revert(struct iov_iter *i, size_t bytes);
-int iov_iter_fault_in_readable(const struct iov_iter *i, size_t bytes);
+size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes);
+size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes);
 size_t iov_iter_single_seg_count(const struct iov_iter *i);
 size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);

index 09406b0e215e..40df35088cdb 100644
@@ -4800,10 +4800,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	/* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */
 	for (i = 0; i < prog->aux->ctx_arg_info_size; i++) {
 		const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i];
+		u32 type, flag;
 
-		if (ctx_arg_info->offset == off &&
-		    (ctx_arg_info->reg_type == PTR_TO_RDONLY_BUF_OR_NULL ||
-		     ctx_arg_info->reg_type == PTR_TO_RDWR_BUF_OR_NULL)) {
+		type = base_type(ctx_arg_info->reg_type);
+		flag = type_flag(ctx_arg_info->reg_type);
+		if (ctx_arg_info->offset == off && type == PTR_TO_BUF &&
+		    (flag & PTR_MAYBE_NULL)) {
 			info->reg_type = ctx_arg_info->reg_type;
 			return true;
 		}

@@ -5508,9 +5510,9 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 			if (reg->type == PTR_TO_BTF_ID) {
 				reg_btf = reg->btf;
 				reg_ref_id = reg->btf_id;
-			} else if (reg2btf_ids[reg->type]) {
+			} else if (reg2btf_ids[base_type(reg->type)]) {
 				reg_btf = btf_vmlinux;
-				reg_ref_id = *reg2btf_ids[reg->type];
+				reg_ref_id = *reg2btf_ids[base_type(reg->type)];
 			} else {
 				bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d is not a pointer to btf_id\n",
 					func_name, i,

@@ -5717,7 +5719,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 				return -EINVAL;
 			}
 
-			reg->type = PTR_TO_MEM_OR_NULL;
+			reg->type = PTR_TO_MEM | PTR_MAYBE_NULL;
 			reg->id = ++env->id_gen;
 
 			continue;

@@ -6229,7 +6231,7 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = {
 	.func		= bpf_btf_find_by_name_kind,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_ANYTHING,

index 7dbd68195a2b..fe053ffd8932 100644
@@ -1753,7 +1753,7 @@ static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE,
 };
 

index 6f600cc95ccd..a711ffe23893 100644
@@ -530,7 +530,7 @@ const struct bpf_func_proto bpf_strtol_proto = {
 	.func		= bpf_strtol,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_LONG,

@@ -558,7 +558,7 @@ const struct bpf_func_proto bpf_strtoul_proto = {
 	.func		= bpf_strtoul,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_LONG,

@@ -630,7 +630,7 @@ const struct bpf_func_proto bpf_event_output_data_proto =  {
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_CONST_MAP_PTR,
 	.arg3_type      = ARG_ANYTHING,
-	.arg4_type      = ARG_PTR_TO_MEM,
+	.arg4_type      = ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
 };
 

@@ -667,7 +667,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu)
 const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
 	.func		= bpf_per_cpu_ptr,
 	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL | MEM_RDONLY,
 	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
 	.arg2_type	= ARG_ANYTHING,
 };

@@ -680,7 +680,7 @@ BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr)
 const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
 	.func		= bpf_this_cpu_ptr,
 	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID | MEM_RDONLY,
 	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
 };
 

@@ -1013,7 +1013,7 @@ const struct bpf_func_proto bpf_snprintf_proto = {
 	.arg1_type	= ARG_PTR_TO_MEM_OR_NULL,
 	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_PTR_TO_CONST_STR,
-	.arg4_type	= ARG_PTR_TO_MEM_OR_NULL,
+	.arg4_type	= ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 

index 6a9542af4212..b0fa190b0979 100644
@@ -174,9 +174,9 @@ static const struct bpf_iter_reg bpf_map_elem_reg_info = {
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map_elem, key),
-		  PTR_TO_RDONLY_BUF_OR_NULL },
+		  PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY },
 		{ offsetof(struct bpf_iter__bpf_map_elem, value),
-		  PTR_TO_RDWR_BUF_OR_NULL },
+		  PTR_TO_BUF | PTR_MAYBE_NULL },
 	},
 };
 

index f1c51c45667d..710ba9de12ce 100644
@@ -444,7 +444,7 @@ const struct bpf_func_proto bpf_ringbuf_output_proto = {
 	.func		= bpf_ringbuf_output,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 };

index 42490c39dfbf..48e02a725563 100644
@@ -4753,7 +4753,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE,
 };
 

918 lines not on this page · raw message

index 5a18b861fcf7..c289010b0964 100644
@@ -345,7 +345,7 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = {
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
-	.arg2_type	= ARG_PTR_TO_MEM,
[… more lines in the raw message]

Lines of this file are not shown. View the raw message.

98 lines not on this page · raw message

index 1293c3409e42..00e391e75880 100644

Lines of this file are not shown. View the raw message.

120 lines not on this page · raw message

index 86260e8f2830..66076d8742b7 100644

Lines of this file are not shown. View the raw message.

index 92bf6eff6060..600f2e2431d6 100644

Lines of this file are not shown. View the raw message.

index 68d2cbf8331a..ea61dfe19c86 100644

Lines of this file are not shown. View the raw message.

64 lines not on this page · raw message

index 8288b5382f08..6351b6af7aca 100644

Lines of this file are not shown. View the raw message.

index cf3acfa5a91d..69455fe90ac3 100644

Lines of this file are not shown. View the raw message.

new file mode 100644
index 000000000000..2180c41cd890

Lines of this file are not shown. View the raw message.

index 336a749673d1..2e701e7f6968 100644

Lines of this file are not shown. View the raw message.