[PATCH v4] eal: make hugetlb initialization more robust

[Jianfeng Tan <jianfeng.tan@intel.com>]

This patch adds an option, --huge-trybest, to use a recover mechanism to
the case that there are not so many hugepages (declared in sysfs), which
can be used. It relys on a mem access to fault-in hugepages, and if fails
with SIGBUS, recover to previously saved stack environment with
siglongjmp().

Besides, this solution fixes an issue when hugetlbfs is specified with an
option of size. Currently DPDK does not respect the quota of a hugetblfs
mount. It fails to init the EAL because it tries to map the number of free
hugepages in the system rather than using the number specified in the quota
for that mount.

It's still an open issue with CONFIG_RTE_EAL_SINGLE_FILE_SEGMENTS. Under
this case (such as IVSHMEM target), having hugetlbfs mounts with quota will
fail to remap hugepages as it relies on having mapped all free hugepages
in the system.

Test example:
  a. cgcreate -g hugetlb:/test-subgroup
  b. cgset -r hugetlb.1GB.limit_in_bytes=2147483648 test-subgroup
  c. cgexec -g hugetlb:test-subgroup \
	  ./examples/helloworld/build/helloworld -c 0x2 -n 4 --huge-trybest

Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
---
v4:
 - Change map_all_hugepages to return unsigned instead of int.
v3:
 - Reword commit message to include it fixes the hugetlbfs quota issue.
 - setjmp -> sigsetjmp.
 - Fix RTE_LOG complaint from ERR to DEBUG as it does not mean init error
   so far.
 - Fix the second map_all_hugepages's return value check.
v2:
 - Address the compiling error by move setjmp into a wrap method.

 lib/librte_eal/common/eal_common_options.c |   4 +
 lib/librte_eal/common/eal_internal_cfg.h   |   1 +
 lib/librte_eal/common/eal_options.h        |   2 +
 lib/librte_eal/linuxapp/eal/eal.c          |   1 +
 lib/librte_eal/linuxapp/eal/eal_memory.c   | 118 +++++++++++++++++++++++++----
 5 files changed, 112 insertions(+), 14 deletions(-)

diff --git a/lib/librte_eal/common/eal_common_options.c b/lib/librte_eal/common/eal_common_options.c
index 3efc90f..e9a111d 100644
--- a/lib/librte_eal/common/eal_common_options.c
+++ b/lib/librte_eal/common/eal_common_options.c
@@ -95,6 +95,7 @@ eal_long_options[] = {
 	{OPT_VFIO_INTR,         1, NULL, OPT_VFIO_INTR_NUM        },
 	{OPT_VMWARE_TSC_MAP,    0, NULL, OPT_VMWARE_TSC_MAP_NUM   },
 	{OPT_XEN_DOM0,          0, NULL, OPT_XEN_DOM0_NUM         },
+	{OPT_HUGE_TRYBEST,      0, NULL, OPT_HUGE_TRYBEST_NUM     },
 	{0,                     0, NULL, 0                        }
 };
 
@@ -899,6 +900,9 @@ eal_parse_common_option(int opt, const char *optarg,
 			return -1;
 		}
 		break;
+	case OPT_HUGE_TRYBEST_NUM:
+		internal_config.huge_trybest = 1;
+		break;
 
 	/* don't know what to do, leave this to caller */
 	default:
diff --git a/lib/librte_eal/common/eal_internal_cfg.h b/lib/librte_eal/common/eal_internal_cfg.h
index 5f1367e..90a3533 100644
--- a/lib/librte_eal/common/eal_internal_cfg.h
+++ b/lib/librte_eal/common/eal_internal_cfg.h
@@ -64,6 +64,7 @@ struct internal_config {
 	volatile unsigned force_nchannel; /**< force number of channels */
 	volatile unsigned force_nrank;    /**< force number of ranks */
 	volatile unsigned no_hugetlbfs;   /**< true to disable hugetlbfs */
+	volatile unsigned huge_trybest;   /**< try best to allocate hugepages */
 	unsigned hugepage_unlink;         /**< true to unlink backing files */
 	volatile unsigned xen_dom0_support; /**< support app running on Xen Dom0*/
 	volatile unsigned no_pci;         /**< true to disable PCI */
diff --git a/lib/librte_eal/common/eal_options.h b/lib/librte_eal/common/eal_options.h
index a881c62..02397c5 100644
--- a/lib/librte_eal/common/eal_options.h
+++ b/lib/librte_eal/common/eal_options.h
@@ -83,6 +83,8 @@ enum {
 	OPT_VMWARE_TSC_MAP_NUM,
 #define OPT_XEN_DOM0          "xen-dom0"
 	OPT_XEN_DOM0_NUM,
+#define OPT_HUGE_TRYBEST      "huge-trybest"
+	OPT_HUGE_TRYBEST_NUM,
 	OPT_LONG_MAX_NUM
 };
 
diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
index 8aafd51..eeb1d4e 100644
--- a/lib/librte_eal/linuxapp/eal/eal.c
+++ b/lib/librte_eal/linuxapp/eal/eal.c
@@ -343,6 +343,7 @@ eal_usage(const char *prgname)
 	       "  --"OPT_CREATE_UIO_DEV"    Create /dev/uioX (usually done by hotplug)\n"
 	       "  --"OPT_VFIO_INTR"         Interrupt mode for VFIO (legacy|msi|msix)\n"
 	       "  --"OPT_XEN_DOM0"          Support running on Xen dom0 without hugetlbfs\n"
+	       "  --"OPT_HUGE_TRYBEST"      Try best to accommodate hugepages\n"
 	       "\n");
 	/* Allow the application to print its usage message too if hook is set */
 	if ( rte_application_usage_hook ) {
diff --git a/lib/librte_eal/linuxapp/eal/eal_memory.c b/lib/librte_eal/linuxapp/eal/eal_memory.c
index 5b9132c..8c77010 100644
--- a/lib/librte_eal/linuxapp/eal/eal_memory.c
+++ b/lib/librte_eal/linuxapp/eal/eal_memory.c
@@ -80,6 +80,8 @@
 #include <errno.h>
 #include <sys/ioctl.h>
 #include <sys/time.h>
+#include <signal.h>
+#include <setjmp.h>
 
 #include <rte_log.h>
 #include <rte_memory.h>
@@ -309,6 +311,21 @@ get_virtual_area(size_t *size, size_t hugepage_sz)
 	return addr;
 }
 
+static sigjmp_buf jmpenv;
+
+static void sigbus_handler(int signo __rte_unused)
+{
+	siglongjmp(jmpenv, 1);
+}
+
+/* Put setjmp into a wrap method to avoid compiling error. Any non-volatile,
+ * non-static local variable in the stack frame calling sigsetjmp might be
+ * clobbered by a call to longjmp.
+ */
+static int wrap_sigsetjmp(void)
+{
+	return sigsetjmp(jmpenv, 1);
+}
 /*
  * Mmap all hugepages of hugepage table: it first open a file in
  * hugetlbfs, then mmap() hugepage_sz data in it. If orig is set, the
@@ -316,7 +333,7 @@ get_virtual_area(size_t *size, size_t hugepage_sz)
  * in hugepg_tbl[i].final_va. The second mapping (when orig is 0) tries to
  * map continguous physical blocks in contiguous virtual blocks.
  */
-static int
+static unsigned
 map_all_hugepages(struct hugepage_file *hugepg_tbl,
 		struct hugepage_info *hpi, int orig)
 {
@@ -394,9 +411,9 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl,
 		/* try to create hugepage file */
 		fd = open(hugepg_tbl[i].filepath, O_CREAT | O_RDWR, 0755);
 		if (fd < 0) {
-			RTE_LOG(ERR, EAL, "%s(): open failed: %s\n", __func__,
+			RTE_LOG(DEBUG, EAL, "%s(): open failed: %s\n", __func__,
 					strerror(errno));
-			return -1;
+			return i;
 		}
 
 		/* map the segment, and populate page tables,
@@ -404,10 +421,10 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl,
 		virtaddr = mmap(vma_addr, hugepage_sz, PROT_READ | PROT_WRITE,
 				MAP_SHARED | MAP_POPULATE, fd, 0);
 		if (virtaddr == MAP_FAILED) {
-			RTE_LOG(ERR, EAL, "%s(): mmap failed: %s\n", __func__,
+			RTE_LOG(DEBUG, EAL, "%s(): mmap failed: %s\n", __func__,
 					strerror(errno));
 			close(fd);
-			return -1;
+			return i;
 		}
 
 		if (orig) {
@@ -417,12 +434,33 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl,
 			hugepg_tbl[i].final_va = virtaddr;
 		}
 
+		if (orig && internal_config.huge_trybest) {
+			/* In linux, hugetlb limitations, like cgroup, are
+			 * enforced at fault time instead of mmap(), even
+			 * with the option of MAP_POPULATE. Kernel will send
+			 * a SIGBUS signal. To avoid to be killed, save stack
+			 * environment here, if SIGBUS happens, we can jump
+			 * back here.
+			 */
+			if (wrap_sigsetjmp()) {
+				RTE_LOG(DEBUG, EAL, "SIGBUS: Cannot mmap more "
+					"hugepages of size %u MB\n",
+					(unsigned)(hugepage_sz / 0x100000));
+				munmap(virtaddr, hugepage_sz);
+				close(fd);
+				unlink(hugepg_tbl[i].filepath);
+				return i;
+			}
+			*(int *)virtaddr = 0;
+		}
+
+
 		/* set shared flock on the file. */
 		if (flock(fd, LOCK_SH | LOCK_NB) == -1) {
-			RTE_LOG(ERR, EAL, "%s(): Locking file failed:%s \n",
+			RTE_LOG(DEBUG, EAL, "%s(): Locking file failed:%s \n",
 				__func__, strerror(errno));
 			close(fd);
-			return -1;
+			return i;
 		}
 
 		close(fd);
@@ -430,7 +468,8 @@ map_all_hugepages(struct hugepage_file *hugepg_tbl,
 		vma_addr = (char *)vma_addr + hugepage_sz;
 		vma_len -= hugepage_sz;
 	}
-	return 0;
+
+	return i;
 }
 
 #ifdef RTE_EAL_SINGLE_FILE_SEGMENTS
@@ -1036,6 +1075,33 @@ calc_num_pages_per_socket(uint64_t * memory,
 	return total_num_pages;
 }
 
+static struct sigaction action_old;
+static int need_recover;
+
+static void
+register_sigbus(void)
+{
+	sigset_t mask;
+	struct sigaction action;
+
+	sigemptyset(&mask);
+	sigaddset(&mask, SIGBUS);
+	action.sa_flags = 0;
+	action.sa_mask = mask;
+	action.sa_handler = sigbus_handler;
+
+	need_recover = !sigaction(SIGBUS, &action, &action_old);
+}
+
+static void
+recover_sigbus(void)
+{
+	if (need_recover) {
+		sigaction(SIGBUS, &action_old, NULL);
+		need_recover = 0;
+	}
+}
+
 /*
  * Prepare physical memory mapping: fill configuration structure with
  * these infos, return 0 on success.
@@ -1122,8 +1188,12 @@ rte_eal_hugepage_init(void)
 
 	hp_offset = 0; /* where we start the current page size entries */
 
+	if (internal_config.huge_trybest)
+		register_sigbus();
+
 	/* map all hugepages and sort them */
 	for (i = 0; i < (int)internal_config.num_hugepage_sizes; i ++){
+		unsigned pages_old, pages_new;
 		struct hugepage_info *hpi;
 
 		/*
@@ -1137,10 +1207,24 @@ rte_eal_hugepage_init(void)
 			continue;
 
 		/* map all hugepages available */
-		if (map_all_hugepages(&tmp_hp[hp_offset], hpi, 1) < 0){
-			RTE_LOG(DEBUG, EAL, "Failed to mmap %u MB hugepages\n",
-					(unsigned)(hpi->hugepage_sz / 0x100000));
-			goto fail;
+		pages_old = hpi->num_pages[0];
+		pages_new = map_all_hugepages(&tmp_hp[hp_offset], hpi, 1);
+		if (pages_new < pages_old) {
+			RTE_LOG(DEBUG, EAL,
+				"%d not %d hugepages of size %u MB allocated\n",
+				pages_new, pages_old,
+				(unsigned)(hpi->hugepage_sz / 0x100000));
+			if (internal_config.huge_trybest) {
+				int pages = pages_old - pages_new;
+
+				internal_config.memory -=
+					hpi->hugepage_sz * pages;
+				nr_hugepages -= pages;
+				hpi->num_pages[0] = pages_new;
+				if (pages_new == 0)
+					continue;
+			} else
+				goto fail;
 		}
 
 		/* find physical addresses and sockets for each hugepage */
@@ -1172,8 +1256,9 @@ rte_eal_hugepage_init(void)
 		hp_offset += new_pages_count[i];
 #else
 		/* remap all hugepages */
-		if (map_all_hugepages(&tmp_hp[hp_offset], hpi, 0) < 0){
-			RTE_LOG(DEBUG, EAL, "Failed to remap %u MB pages\n",
+		if (map_all_hugepages(&tmp_hp[hp_offset], hpi, 0) !=
+		    hpi->num_pages[0]) {
+			RTE_LOG(ERR, EAL, "Failed to remap %u MB pages\n",
 					(unsigned)(hpi->hugepage_sz / 0x100000));
 			goto fail;
 		}
@@ -1187,6 +1272,9 @@ rte_eal_hugepage_init(void)
 #endif
 	}
 
+	if (internal_config.huge_trybest)
+		recover_sigbus();
+
 #ifdef RTE_EAL_SINGLE_FILE_SEGMENTS
 	nr_hugefiles = 0;
 	for (i = 0; i < (int) internal_config.num_hugepage_sizes; i++) {
@@ -1373,6 +1461,8 @@ rte_eal_hugepage_init(void)
 	return 0;
 
 fail:
+	if (internal_config.huge_trybest)
+		recover_sigbus();
 	free(tmp_hp);
 	return -1;
 }
-- 
2.1.4