From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB

---
 kernel/drivers/nvme/target/io-cmd-file.c |  261 ++++++++++++++++++++++++++++++++-------------------
 1 files changed, 162 insertions(+), 99 deletions(-)

diff --git a/kernel/drivers/nvme/target/io-cmd-file.c b/kernel/drivers/nvme/target/io-cmd-file.c
index ad6263c..c81690b 100644
--- a/kernel/drivers/nvme/target/io-cmd-file.c
+++ b/kernel/drivers/nvme/target/io-cmd-file.c
@@ -8,10 +8,23 @@
 #include <linux/uio.h>
 #include <linux/falloc.h>
 #include <linux/file.h>
+#include <linux/fs.h>
 #include "nvmet.h"
 
 #define NVMET_MAX_MPOOL_BVEC		16
 #define NVMET_MIN_MPOOL_OBJ		16
+
+int nvmet_file_ns_revalidate(struct nvmet_ns *ns)
+{
+	struct kstat stat;
+	int ret;
+
+	ret = vfs_getattr(&ns->file->f_path, &stat, STATX_SIZE,
+			  AT_STATX_FORCE_SYNC);
+	if (!ret)
+		ns->size = stat.size;
+	return ret;
+}
 
 void nvmet_file_ns_disable(struct nvmet_ns *ns)
 {
@@ -30,7 +43,6 @@
 int nvmet_file_ns_enable(struct nvmet_ns *ns)
 {
 	int flags = O_RDWR | O_LARGEFILE;
-	struct kstat stat;
 	int ret;
 
 	if (!ns->buffered_io)
@@ -45,13 +57,16 @@
 		return ret;
 	}
 
-	ret = vfs_getattr(&ns->file->f_path,
-			&stat, STATX_SIZE, AT_STATX_FORCE_SYNC);
+	ret = nvmet_file_ns_revalidate(ns);
 	if (ret)
 		goto err;
 
-	ns->size = stat.size;
-	ns->blksize_shift = file_inode(ns->file)->i_blkbits;
+	/*
+	 * i_blkbits can be greater than the universally accepted upper bound,
+	 * so make sure we export a sane namespace lba_shift.
+	 */
+	ns->blksize_shift = min_t(u8,
+			file_inode(ns->file)->i_blkbits, 12);
 
 	ns->bvec_cache = kmem_cache_create("nvmet-bvec",
 			NVMET_MAX_MPOOL_BVEC * sizeof(struct bio_vec),
@@ -77,25 +92,24 @@
 	return ret;
 }
 
-static void nvmet_file_init_bvec(struct bio_vec *bv, struct sg_page_iter *iter)
+static void nvmet_file_init_bvec(struct bio_vec *bv, struct scatterlist *sg)
 {
-	bv->bv_page = sg_page_iter_page(iter);
-	bv->bv_offset = iter->sg->offset;
-	bv->bv_len = PAGE_SIZE - iter->sg->offset;
+	bv->bv_page = sg_page(sg);
+	bv->bv_offset = sg->offset;
+	bv->bv_len = sg->length;
 }
 
 static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
-		unsigned long nr_segs, size_t count)
+		unsigned long nr_segs, size_t count, int ki_flags)
 {
 	struct kiocb *iocb = &req->f.iocb;
 	ssize_t (*call_iter)(struct kiocb *iocb, struct iov_iter *iter);
 	struct iov_iter iter;
-	int ki_flags = 0, rw;
-	ssize_t ret;
+	int rw;
 
 	if (req->cmd->rw.opcode == nvme_cmd_write) {
 		if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
-			ki_flags = IOCB_DSYNC;
+			ki_flags |= IOCB_DSYNC;
 		call_iter = req->ns->file->f_op->write_iter;
 		rw = WRITE;
 	} else {
@@ -103,23 +117,19 @@
 		rw = READ;
 	}
 
-	iov_iter_bvec(&iter, ITER_BVEC | rw, req->f.bvec, nr_segs, count);
+	iov_iter_bvec(&iter, rw, req->f.bvec, nr_segs, count);
 
 	iocb->ki_pos = pos;
 	iocb->ki_filp = req->ns->file;
 	iocb->ki_flags = ki_flags | iocb_flags(req->ns->file);
 
-	ret = call_iter(iocb, &iter);
-
-	if (ret != -EIOCBQUEUED && iocb->ki_complete)
-		iocb->ki_complete(iocb, ret, 0);
-
-	return ret;
+	return call_iter(iocb, &iter);
 }
 
 static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
 {
 	struct nvmet_req *req = container_of(iocb, struct nvmet_req, f.iocb);
+	u16 status = NVME_SC_SUCCESS;
 
 	if (req->f.bvec != req->inline_bvec) {
 		if (likely(req->f.mpool_alloc == false))
@@ -128,28 +138,117 @@
 			mempool_free(req->f.bvec, req->ns->bvec_pool);
 	}
 
-	nvmet_req_complete(req, ret != req->data_len ?
-			NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	if (unlikely(ret != req->transfer_len))
+		status = errno_to_nvme_status(req, ret);
+	nvmet_req_complete(req, status);
 }
 
-static void nvmet_file_execute_rw(struct nvmet_req *req)
+static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
 {
-	ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
-	struct sg_page_iter sg_pg_iter;
+	ssize_t nr_bvec = req->sg_cnt;
 	unsigned long bv_cnt = 0;
 	bool is_sync = false;
 	size_t len = 0, total_len = 0;
 	ssize_t ret = 0;
 	loff_t pos;
+	int i;
+	struct scatterlist *sg;
+
+	if (req->f.mpool_alloc && nr_bvec > NVMET_MAX_MPOOL_BVEC)
+		is_sync = true;
+
+	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
+	if (unlikely(pos + req->transfer_len > req->ns->size)) {
+		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
+		return true;
+	}
+
+	memset(&req->f.iocb, 0, sizeof(struct kiocb));
+	for_each_sg(req->sg, sg, req->sg_cnt, i) {
+		nvmet_file_init_bvec(&req->f.bvec[bv_cnt], sg);
+		len += req->f.bvec[bv_cnt].bv_len;
+		total_len += req->f.bvec[bv_cnt].bv_len;
+		bv_cnt++;
+
+		WARN_ON_ONCE((nr_bvec - 1) < 0);
+
+		if (unlikely(is_sync) &&
+		    (nr_bvec - 1 == 0 || bv_cnt == NVMET_MAX_MPOOL_BVEC)) {
+			ret = nvmet_file_submit_bvec(req, pos, bv_cnt, len, 0);
+			if (ret < 0)
+				goto complete;
+
+			pos += len;
+			bv_cnt = 0;
+			len = 0;
+		}
+		nr_bvec--;
+	}
+
+	if (WARN_ON_ONCE(total_len != req->transfer_len)) {
+		ret = -EIO;
+		goto complete;
+	}
+
+	if (unlikely(is_sync)) {
+		ret = total_len;
+		goto complete;
+	}
+
+	/*
+	 * A NULL ki_complete ask for synchronous execution, which we want
+	 * for the IOCB_NOWAIT case.
+	 */
+	if (!(ki_flags & IOCB_NOWAIT))
+		req->f.iocb.ki_complete = nvmet_file_io_done;
+
+	ret = nvmet_file_submit_bvec(req, pos, bv_cnt, total_len, ki_flags);
+
+	switch (ret) {
+	case -EIOCBQUEUED:
+		return true;
+	case -EAGAIN:
+		if (WARN_ON_ONCE(!(ki_flags & IOCB_NOWAIT)))
+			goto complete;
+		return false;
+	case -EOPNOTSUPP:
+		/*
+		 * For file systems returning error -EOPNOTSUPP, handle
+		 * IOCB_NOWAIT error case separately and retry without
+		 * IOCB_NOWAIT.
+		 */
+		if ((ki_flags & IOCB_NOWAIT))
+			return false;
+		break;
+	}
+
+complete:
+	nvmet_file_io_done(&req->f.iocb, ret, 0);
+	return true;
+}
+
+static void nvmet_file_buffered_io_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+
+	nvmet_file_execute_io(req, 0);
+}
+
+static void nvmet_file_submit_buffered_io(struct nvmet_req *req)
+{
+	INIT_WORK(&req->f.work, nvmet_file_buffered_io_work);
+	queue_work(buffered_io_wq, &req->f.work);
+}
+
+static void nvmet_file_execute_rw(struct nvmet_req *req)
+{
+	ssize_t nr_bvec = req->sg_cnt;
+
+	if (!nvmet_check_transfer_len(req, nvmet_rw_data_len(req)))
+		return;
 
 	if (!req->sg_cnt || !nr_bvec) {
 		nvmet_req_complete(req, 0);
-		return;
-	}
-
-	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
-	if (unlikely(pos + req->data_len > req->ns->size)) {
-		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
 		return;
 	}
 
@@ -159,65 +258,26 @@
 	else
 		req->f.bvec = req->inline_bvec;
 
-	req->f.mpool_alloc = false;
 	if (unlikely(!req->f.bvec)) {
 		/* fallback under memory pressure */
 		req->f.bvec = mempool_alloc(req->ns->bvec_pool, GFP_KERNEL);
 		req->f.mpool_alloc = true;
-		if (nr_bvec > NVMET_MAX_MPOOL_BVEC)
-			is_sync = true;
-	}
+	} else
+		req->f.mpool_alloc = false;
 
-	memset(&req->f.iocb, 0, sizeof(struct kiocb));
-	for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) {
-		nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter);
-		len += req->f.bvec[bv_cnt].bv_len;
-		total_len += req->f.bvec[bv_cnt].bv_len;
-		bv_cnt++;
-
-		WARN_ON_ONCE((nr_bvec - 1) < 0);
-
-		if (unlikely(is_sync) &&
-		    (nr_bvec - 1 == 0 || bv_cnt == NVMET_MAX_MPOOL_BVEC)) {
-			ret = nvmet_file_submit_bvec(req, pos, bv_cnt, len);
-			if (ret < 0)
-				goto out;
-			pos += len;
-			bv_cnt = 0;
-			len = 0;
-		}
-		nr_bvec--;
-	}
-
-	if (WARN_ON_ONCE(total_len != req->data_len))
-		ret = -EIO;
-out:
-	if (unlikely(is_sync || ret)) {
-		nvmet_file_io_done(&req->f.iocb, ret < 0 ? ret : total_len, 0);
-		return;
-	}
-	req->f.iocb.ki_complete = nvmet_file_io_done;
-	nvmet_file_submit_bvec(req, pos, bv_cnt, total_len);
-}
-
-static void nvmet_file_buffered_io_work(struct work_struct *w)
-{
-	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
-
-	nvmet_file_execute_rw(req);
-}
-
-static void nvmet_file_execute_rw_buffered_io(struct nvmet_req *req)
-{
-	INIT_WORK(&req->f.work, nvmet_file_buffered_io_work);
-	queue_work(buffered_io_wq, &req->f.work);
+	if (req->ns->buffered_io) {
+		if (likely(!req->f.mpool_alloc) &&
+		    (req->ns->file->f_mode & FMODE_NOWAIT) &&
+		    nvmet_file_execute_io(req, IOCB_NOWAIT))
+			return;
+		nvmet_file_submit_buffered_io(req);
+	} else
+		nvmet_file_execute_io(req, 0);
 }
 
 u16 nvmet_file_flush(struct nvmet_req *req)
 {
-	if (vfs_fsync(req->ns->file, 1) < 0)
-		return NVME_SC_INTERNAL | NVME_SC_DNR;
-	return 0;
+	return errno_to_nvme_status(req, vfs_fsync(req->ns->file, 1));
 }
 
 static void nvmet_file_flush_work(struct work_struct *w)
@@ -229,6 +289,8 @@
 
 static void nvmet_file_execute_flush(struct nvmet_req *req)
 {
+	if (!nvmet_check_transfer_len(req, 0))
+		return;
 	INIT_WORK(&req->f.work, nvmet_file_flush_work);
 	schedule_work(&req->f.work);
 }
@@ -238,30 +300,34 @@
 	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	struct nvme_dsm_range range;
 	loff_t offset, len;
-	u16 ret;
+	u16 status = 0;
+	int ret;
 	int i;
 
 	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
-		ret = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+		status = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
 					sizeof(range));
-		if (ret)
+		if (status)
 			break;
 
 		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
 		len = le32_to_cpu(range.nlb);
 		len <<= req->ns->blksize_shift;
 		if (offset + len > req->ns->size) {
-			ret = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+			req->error_slba = le64_to_cpu(range.slba);
+			status = errno_to_nvme_status(req, -ENOSPC);
 			break;
 		}
 
-		if (vfs_fallocate(req->ns->file, mode, offset, len)) {
-			ret = NVME_SC_INTERNAL | NVME_SC_DNR;
+		ret = vfs_fallocate(req->ns->file, mode, offset, len);
+		if (ret && ret != -EOPNOTSUPP) {
+			req->error_slba = le64_to_cpu(range.slba);
+			status = errno_to_nvme_status(req, ret);
 			break;
 		}
 	}
 
-	nvmet_req_complete(req, ret);
+	nvmet_req_complete(req, status);
 }
 
 static void nvmet_file_dsm_work(struct work_struct *w)
@@ -283,6 +349,8 @@
 
 static void nvmet_file_execute_dsm(struct nvmet_req *req)
 {
+	if (!nvmet_check_data_len_lte(req, nvmet_dsm_len(req)))
+		return;
 	INIT_WORK(&req->f.work, nvmet_file_dsm_work);
 	schedule_work(&req->f.work);
 }
@@ -301,16 +369,18 @@
 			req->ns->blksize_shift);
 
 	if (unlikely(offset + len > req->ns->size)) {
-		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
 		return;
 	}
 
 	ret = vfs_fallocate(req->ns->file, mode, offset, len);
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	nvmet_req_complete(req, ret < 0 ? errno_to_nvme_status(req, ret) : 0);
 }
 
 static void nvmet_file_execute_write_zeroes(struct nvmet_req *req)
 {
+	if (!nvmet_check_transfer_len(req, 0))
+		return;
 	INIT_WORK(&req->f.work, nvmet_file_write_zeroes_work);
 	schedule_work(&req->f.work);
 }
@@ -322,28 +392,21 @@
 	switch (cmd->common.opcode) {
 	case nvme_cmd_read:
 	case nvme_cmd_write:
-		if (req->ns->buffered_io)
-			req->execute = nvmet_file_execute_rw_buffered_io;
-		else
-			req->execute = nvmet_file_execute_rw;
-		req->data_len = nvmet_rw_len(req);
+		req->execute = nvmet_file_execute_rw;
 		return 0;
 	case nvme_cmd_flush:
 		req->execute = nvmet_file_execute_flush;
-		req->data_len = 0;
 		return 0;
 	case nvme_cmd_dsm:
 		req->execute = nvmet_file_execute_dsm;
-		req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
-			sizeof(struct nvme_dsm_range);
 		return 0;
 	case nvme_cmd_write_zeroes:
 		req->execute = nvmet_file_execute_write_zeroes;
-		req->data_len = 0;
 		return 0;
 	default:
 		pr_err("unhandled cmd for file ns %d on qid %d\n",
 				cmd->common.opcode, req->sq->qid);
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 }

--
Gitblit v1.6.2