[dpdk-dev] [PATCH] librte_eal: add APIs to speedup virt2iova/phys

[Li Feng <fengli@smartx.com>]

Using pread to replace lseek + read.
And add new APIs to reduce open/close/lseek system call frequency when the
user needs to convert a large range of virtual address space.
    - rte_mem_virt2iova_with_fd
    - rte_mem_virt2phy_with_fd

Currently it will be used by spdk in spdk_mem_register.

Signed-off-by: Li Feng <fengli@smartx.com>
---
 lib/librte_eal/freebsd/eal_memory.c | 18 ++++++++++++++
 lib/librte_eal/include/rte_memory.h | 36 +++++++++++++++++++++++++++
 lib/librte_eal/linux/eal_memory.c   | 49 +++++++++++++++++++++++--------------
 lib/librte_eal/rte_eal_version.map  |  3 +++
 4 files changed, 88 insertions(+), 18 deletions(-)

diff --git a/lib/librte_eal/freebsd/eal_memory.c b/lib/librte_eal/freebsd/eal_memory.c
index a97d8f0f0..fc0debf23 100644
--- a/lib/librte_eal/freebsd/eal_memory.c
+++ b/lib/librte_eal/freebsd/eal_memory.c
@@ -44,12 +44,30 @@ rte_mem_virt2phy(const void *virtaddr)
 	(void)virtaddr;
 	return RTE_BAD_IOVA;
 }
+
 rte_iova_t
 rte_mem_virt2iova(const void *virtaddr)
 {
 	return rte_mem_virt2phy(virtaddr);
 }
 
+phys_addr_t
+rte_mem_virt2phy_with_fd(int fd, const void *virtaddr)
+{
+	/*
+	 * XXX not implemented. This function is only used by
+	 * rte_mempool_virt2iova_with_fd() when hugepages are disabled.
+	 */
+	(void)virtaddr;
+	return RTE_BAD_IOVA;
+}
+
+rte_iova_t
+rte_mem_virt2iova_with_fd(int fd, const void *virtaddr)
+{
+	return rte_mem_virt2phy_with_fd(fd, virtaddr);
+}
+
 int
 rte_eal_hugepage_init(void)
 {
diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
index 3d8d0bd69..c75782fa7 100644
--- a/lib/librte_eal/include/rte_memory.h
+++ b/lib/librte_eal/include/rte_memory.h
@@ -108,6 +108,23 @@ int rte_mem_lock_page(const void *virt);
 phys_addr_t rte_mem_virt2phy(const void *virt);
 
 /**
+ * Get physical address of any mapped virtual address in the current process.
+ * It is found by reading fd which is the opened /proc/self/pagemap special file
+ * descriptor. This is a optimization of rte_mem_virt2phy when the
+ * rte_mem_virt2phy is needed to be called many times.
+ * The page must be locked.
+ *
+ * @param fd
+ *   The opened fd of /proc/self/pagemap.
+ * @param virt
+ *   The virtual address.
+ * @return
+ *   The physical address or RTE_BAD_IOVA on error.
+ */
+__rte_experimental
+phys_addr_t rte_mem_virt2phy_with_fd(int fd, const void *virt);
+
+/**
  * Get IO virtual address of any mapped virtual address in the current process.
  *
  * @note This function will not check internal page table. Instead, in IOVA as
@@ -123,6 +140,25 @@ phys_addr_t rte_mem_virt2phy(const void *virt);
 rte_iova_t rte_mem_virt2iova(const void *virt);
 
 /**
+ * Get IO virtual address of any mapped virtual address in the current process.
+ *
+ * @note This function will not check internal page table. Instead, in IOVA as
+ *       PA mode, it will fall back to getting real physical address (which may
+ *       not match the expected IOVA, such as what was specified for external
+ *       memory).
+ *
+ * @param virt
+ *   The virtual address.
+ * @param fd
+ *   The opened fd of /proc/self/pagemap.
+ * @return
+ *   The IO address or RTE_BAD_IOVA on error.
+ */
+__rte_experimental
+rte_iova_t rte_mem_virt2iova_with_fd(int fd, const void *virt);
+
+
+/**
  * Get virtual memory address corresponding to iova address.
  *
  * @note This function read-locks the memory hotplug subsystem, and thus cannot
diff --git a/lib/librte_eal/linux/eal_memory.c b/lib/librte_eal/linux/eal_memory.c
index 7a9c97ff8..918796700 100644
--- a/lib/librte_eal/linux/eal_memory.c
+++ b/lib/librte_eal/linux/eal_memory.c
@@ -91,11 +91,11 @@ uint64_t eal_get_baseaddr(void)
 
 /*
  * Get physical address of any mapped virtual address in the current process.
+ * fd is used to avoid open/close pagemap repeatly.
  */
 phys_addr_t
-rte_mem_virt2phy(const void *virtaddr)
-{
-	int fd, retval;
+rte_mem_virt2phy_with_fd(int fd, const void *virtaddr) {
+	int retval;
 	uint64_t page, physaddr;
 	unsigned long virt_pfn;
 	int page_size;
@@ -107,24 +107,10 @@ rte_mem_virt2phy(const void *virtaddr)
 	/* standard page size */
 	page_size = getpagesize();
 
-	fd = open("/proc/self/pagemap", O_RDONLY);
-	if (fd < 0) {
-		RTE_LOG(INFO, EAL, "%s(): cannot open /proc/self/pagemap: %s\n",
-			__func__, strerror(errno));
-		return RTE_BAD_IOVA;
-	}
-
 	virt_pfn = (unsigned long)virtaddr / page_size;
 	offset = sizeof(uint64_t) * virt_pfn;
-	if (lseek(fd, offset, SEEK_SET) == (off_t) -1) {
-		RTE_LOG(INFO, EAL, "%s(): seek error in /proc/self/pagemap: %s\n",
-				__func__, strerror(errno));
-		close(fd);
-		return RTE_BAD_IOVA;
-	}
 
-	retval = read(fd, &page, PFN_MASK_SIZE);
-	close(fd);
+	retval = pread(fd, &page, PFN_MASK_SIZE, offset);
 	if (retval < 0) {
 		RTE_LOG(INFO, EAL, "%s(): cannot read /proc/self/pagemap: %s\n",
 				__func__, strerror(errno));
@@ -149,6 +135,33 @@ rte_mem_virt2phy(const void *virtaddr)
 	return physaddr;
 }
 
+/*
+ * Get physical address of any mapped virtual address in the current process.
+ */
+phys_addr_t
+rte_mem_virt2phy(const void *virtaddr)
+{
+	uint64_t physaddr;
+	int fd;
+	fd = open("/proc/self/pagemap", O_RDONLY);
+	if (fd < 0) {
+		RTE_LOG(INFO, EAL, "%s(): cannot open /proc/self/pagemap: %s\n",
+			__func__, strerror(errno));
+		return RTE_BAD_IOVA;
+	}
+	physaddr = rte_mem_virt2phy_with_fd(fd, virtaddr);
+	close(fd);
+	return physaddr;
+}
+
+rte_iova_t
+rte_mem_virt2iova_with_fd(int fd, const void *virtaddr)
+{
+	if (rte_eal_iova_mode() == RTE_IOVA_VA)
+		return (uintptr_t)virtaddr;
+	return rte_mem_virt2phy_with_fd(fd, virtaddr);
+}
+
 rte_iova_t
 rte_mem_virt2iova(const void *virtaddr)
 {
diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
index f9ede5b41..fc3a436e7 100644
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -338,4 +338,7 @@ EXPERIMENTAL {
 
 	# added in 20.05
 	rte_log_can_log;
+
+	rte_mem_virt2iova_with_fd;
+	rte_mem_virt2phy_with_fd;
 };
-- 
2.11.0


-- 
The SmartX email address is only for business purpose. Any sent message 
that is not related to the business is not authorized or permitted by 
SmartX.
本邮箱为北京志凌海纳科技有限公司（SmartX）工作邮箱. 如本邮箱发出的邮件与工作无关,该邮件未得到本公司任何的明示或默示的授权.