KVM: selftests: Use EPOLL in userfaultfd_util reader threads

With multiple reader threads POLLing a single UFFD, the demand paging test
suffers from the thundering herd problem: performance degrades as the
number of reader threads is increased. Solve this issue [1] by switching
the the polling mechanism to EPOLL + EPOLLEXCLUSIVE.

Also, change the error-handling convention of uffd_handler_thread_fn.
Instead of just printing errors and returning early from the polling
loop, check for them via TEST_ASSERT(). "return NULL" is reserved for a
successful exit from uffd_handler_thread_fn, i.e. one triggered by a
write to the exit pipe.

Performance samples generated by the command in [2] are given below.

Num Reader Threads, Paging Rate (POLL), Paging Rate (EPOLL)
1      249k      185k
2      201k      235k
4      186k      155k
16     150k      217k
32     89k       198k

[1] Single-vCPU performance does suffer somewhat.
[2] ./demand_paging_test -u MINOR -s shmem -v 4 -o -r <num readers>

Signed-off-by: Anish Moorthy <[email protected]>
Acked-by: James Houghton <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Sean Christopherson <[email protected]>

Author: anlsh

tools/testing/selftests/kvm/demand_paging_test.c

@@ -13,7 +13,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <time.h>
-#include <poll.h>
 #include <pthread.h>
 #include <linux/userfaultfd.h>
 #include <sys/syscall.h>

tools/testing/selftests/kvm/lib/userfaultfd_util.c

@@ -16,6 +16,7 @@
 #include <poll.h>
 #include <pthread.h>
 #include <linux/userfaultfd.h>
+#include <sys/epoll.h>
 #include <sys/syscall.h>
 
 #include "kvm_util.h"
@@ -32,69 +33,64 @@ static void *uffd_handler_thread_fn(void *arg)
 	int64_t pages = 0;
 	struct timespec start;
 	struct timespec ts_diff;
+	struct epoll_event evt;
+	int epollfd;
+
+	epollfd = epoll_create(1);
+	TEST_ASSERT(epollfd >= 0, "Failed to create epollfd.");
+
+	evt.events = EPOLLIN | EPOLLEXCLUSIVE;
+	evt.data.u32 = 0;
+	TEST_ASSERT(!epoll_ctl(epollfd, EPOLL_CTL_ADD, uffd, &evt),
+		    "Failed to add uffd to epollfd");
+
+	evt.events = EPOLLIN;
+	evt.data.u32 = 1;
+	TEST_ASSERT(!epoll_ctl(epollfd, EPOLL_CTL_ADD, reader_args->pipe, &evt),
+		    "Failed to add pipe to epollfd");
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
 	while (1) {
 		struct uffd_msg msg;
-		struct pollfd pollfd[2];
-		char tmp_chr;
 		int r;
 
-		pollfd[0].fd = uffd;
-		pollfd[0].events = POLLIN;
-		pollfd[1].fd = reader_args->pipe;
-		pollfd[1].events = POLLIN;
-
-		r = poll(pollfd, 2, -1);
-		switch (r) {
-		case -1:
-			pr_info("poll err");
-			continue;
-		case 0:
-			continue;
-		case 1:
-			break;
-		default:
-			pr_info("Polling uffd returned %d", r);
-			return NULL;
-		}
+		r = epoll_wait(epollfd, &evt, 1, -1);
+		TEST_ASSERT(r == 1,
+			    "Unexpected number of events (%d) from epoll, errno = %d",
+			    r, errno);
 
-		if (pollfd[0].revents & POLLERR) {
-			pr_info("uffd revents has POLLERR");
-			return NULL;
-		}
+		if (evt.data.u32 == 1) {
+			char tmp_chr;
 
-		if (pollfd[1].revents & POLLIN) {
-			r = read(pollfd[1].fd, &tmp_chr, 1);
+			TEST_ASSERT(!(evt.events & (EPOLLERR | EPOLLHUP)),
+				    "Reader thread received EPOLLERR or EPOLLHUP on pipe.");
+			r = read(reader_args->pipe, &tmp_chr, 1);
 			TEST_ASSERT(r == 1,
-				    "Error reading pipefd in UFFD thread");
+				    "Error reading pipefd in uffd reader thread");
 			break;
 		}
 
-		if (!(pollfd[0].revents & POLLIN))
-			continue;
+		TEST_ASSERT(!(evt.events & (EPOLLERR | EPOLLHUP)),
+			    "Reader thread received EPOLLERR or EPOLLHUP on uffd.");
 
 		r = read(uffd, &msg, sizeof(msg));
 		if (r == -1) {
-			if (errno == EAGAIN)
-				continue;
-			pr_info("Read of uffd got errno %d\n", errno);
-			return NULL;
+			TEST_ASSERT(errno == EAGAIN,
+				    "Error reading from UFFD: errno = %d", errno);
+			continue;
 		}
 
-		if (r != sizeof(msg)) {
-			pr_info("Read on uffd returned unexpected size: %d bytes", r);
-			return NULL;
-		}
+		TEST_ASSERT(r == sizeof(msg),
+			    "Read on uffd returned unexpected number of bytes (%d)", r);
 
 		if (!(msg.event & UFFD_EVENT_PAGEFAULT))
 			continue;
 
 		if (reader_args->delay)
 			usleep(reader_args->delay);
 		r = reader_args->handler(reader_args->uffd_mode, uffd, &msg);
-		if (r < 0)
-			return NULL;
+		TEST_ASSERT(r >= 0,
+			    "Reader thread handler fn returned negative value %d", r);
 		pages++;
 	}