From 97a70e548bd97d5a46ae9d44f24aafcc013fd701 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 12 Nov 2008 23:22:35 +0100 Subject: x86, hibernate: fix breakage on x86_32 with CONFIG_NUMA set Impact: fix crash during hibernation on 32-bit NUMA The NUMA code on x86_32 creates special memory mapping that allows each node's pgdat to be located in this node's memory. For this purpose it allocates a memory area at the end of each node's memory and maps this area so that it is accessible with virtual addresses belonging to low memory. As a result, if there is high memory, these NUMA-allocated areas are physically located in high memory, although they are mapped to low memory addresses. Our hibernation code does not take that into account and for this reason hibernation fails on all x86_32 systems with CONFIG_NUMA=y and with high memory present. Fix this by adding a special mapping for the NUMA-allocated memory areas to the temporary page tables created during the last phase of resume. Signed-off-by: Rafael J. Wysocki Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmzone_32.h | 4 ++++ arch/x86/mm/numa_32.c | 35 +++++++++++++++++++++++++++++++++++ arch/x86/power/hibernate_32.c | 4 ++++ 3 files changed, 43 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 485bdf059ff..07f1af494ca 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -34,10 +34,14 @@ static inline void get_memcfg_numa(void) extern int early_pfn_to_nid(unsigned long pfn); +extern void resume_map_numa_kva(pgd_t *pgd); + #else /* !CONFIG_NUMA */ #define get_memcfg_numa get_memcfg_numa_flat +static inline void resume_map_numa_kva(pgd_t *pgd) {} + #endif /* CONFIG_NUMA */ #ifdef CONFIG_DISCONTIGMEM diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 847c164725f..8518c678d83 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -222,6 +222,41 @@ static void __init remap_numa_kva(void) } } +#ifdef CONFIG_HIBERNATION +/** + * resume_map_numa_kva - add KVA mapping to the temporary page tables created + * during resume from hibernation + * @pgd_base - temporary resume page directory + */ +void resume_map_numa_kva(pgd_t *pgd_base) +{ + int node; + + for_each_online_node(node) { + unsigned long start_va, start_pfn, size, pfn; + + start_va = (unsigned long)node_remap_start_vaddr[node]; + start_pfn = node_remap_start_pfn[node]; + size = node_remap_size[node]; + + printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node); + + for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) { + unsigned long vaddr = start_va + (pfn << PAGE_SHIFT); + pgd_t *pgd = pgd_base + pgd_index(vaddr); + pud_t *pud = pud_offset(pgd, vaddr); + pmd_t *pmd = pmd_offset(pud, vaddr); + + set_pmd(pmd, pfn_pmd(start_pfn + pfn, + PAGE_KERNEL_LARGE_EXEC)); + + printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n", + __FUNCTION__, vaddr, start_pfn + pfn); + } + } +} +#endif + static unsigned long calculate_numa_remap_pages(void) { int nid; diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index f2b6e3f11bf..81197c62d5b 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -12,6 +12,7 @@ #include #include #include +#include /* Defined in hibernate_asm_32.S */ extern int restore_image(void); @@ -127,6 +128,9 @@ static int resume_physical_mapping_init(pgd_t *pgd_base) } } } + + resume_map_numa_kva(pgd_base); + return 0; } -- cgit v1.2.3-18-g5258 From 604d20554883cf03f888440d58ea7c6d36899839 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 12 Nov 2008 23:26:14 +0100 Subject: x86: make NUMA on 32-bit depend on EXPERIMENTAL again My previous patch to make CONFIG_NUMA on x86_32 depend on BROKEN turned out to be unnecessary, after all, since the source of the hibernation vs CONFIG_NUMA problem turned out to be the fact that we didn't take the NUMA KVA remapping into account in the hibernation code. Signed-off-by: Rafael J. Wysocki Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 93224b56918..4cf0ab13d18 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -957,7 +957,7 @@ config ARCH_PHYS_ADDR_T_64BIT config NUMA bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)" depends on SMP - depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && BROKEN) + depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL) default n if X86_PC default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP) help -- cgit v1.2.3-18-g5258 From de11defebf00007677fb7ee91d9b089b78786fbb Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 19 Nov 2008 15:36:14 -0800 Subject: reintroduce accept4 Introduce a new accept4() system call. The addition of this system call matches analogous changes in 2.6.27 (dup3(), evenfd2(), signalfd4(), inotify_init1(), epoll_create1(), pipe2()) which added new system calls that differed from analogous traditional system calls in adding a flags argument that can be used to access additional functionality. The accept4() system call is exactly the same as accept(), except that it adds a flags bit-mask argument. Two flags are initially implemented. (Most of the new system calls in 2.6.27 also had both of these flags.) SOCK_CLOEXEC causes the close-on-exec (FD_CLOEXEC) flag to be enabled for the new file descriptor returned by accept4(). This is a useful security feature to avoid leaking information in a multithreaded program where one thread is doing an accept() at the same time as another thread is doing a fork() plus exec(). More details here: http://udrepper.livejournal.com/20407.html "Secure File Descriptor Handling", Ulrich Drepper). The other flag is SOCK_NONBLOCK, which causes the O_NONBLOCK flag to be enabled on the new open file description created by accept4(). (This flag is merely a convenience, saving the use of additional calls fcntl(F_GETFL) and fcntl (F_SETFL) to achieve the same result. Here's a test program. Works on x86-32. Should work on x86-64, but I (mtk) don't have a system to hand to test with. It tests accept4() with each of the four possible combinations of SOCK_CLOEXEC and SOCK_NONBLOCK set/clear in 'flags', and verifies that the appropriate flags are set on the file descriptor/open file description returned by accept4(). I tested Ulrich's patch in this thread by applying against 2.6.28-rc2, and it passes according to my test program. /* test_accept4.c Copyright (C) 2008, Linux Foundation, written by Michael Kerrisk Licensed under the GNU GPLv2 or later. */ #define _GNU_SOURCE #include #include #include #include #include #include #include #include #define PORT_NUM 33333 #define die(msg) do { perror(msg); exit(EXIT_FAILURE); } while (0) /**********************************************************************/ /* The following is what we need until glibc gets a wrapper for accept4() */ /* Flags for socket(), socketpair(), accept4() */ #ifndef SOCK_CLOEXEC #define SOCK_CLOEXEC O_CLOEXEC #endif #ifndef SOCK_NONBLOCK #define SOCK_NONBLOCK O_NONBLOCK #endif #ifdef __x86_64__ #define SYS_accept4 288 #elif __i386__ #define USE_SOCKETCALL 1 #define SYS_ACCEPT4 18 #else #error "Sorry -- don't know the syscall # on this architecture" #endif static int accept4(int fd, struct sockaddr *sockaddr, socklen_t *addrlen, int flags) { printf("Calling accept4(): flags = %x", flags); if (flags != 0) { printf(" ("); if (flags & SOCK_CLOEXEC) printf("SOCK_CLOEXEC"); if ((flags & SOCK_CLOEXEC) && (flags & SOCK_NONBLOCK)) printf(" "); if (flags & SOCK_NONBLOCK) printf("SOCK_NONBLOCK"); printf(")"); } printf("\n"); #if USE_SOCKETCALL long args[6]; args[0] = fd; args[1] = (long) sockaddr; args[2] = (long) addrlen; args[3] = flags; return syscall(SYS_socketcall, SYS_ACCEPT4, args); #else return syscall(SYS_accept4, fd, sockaddr, addrlen, flags); #endif } /**********************************************************************/ static int do_test(int lfd, struct sockaddr_in *conn_addr, int closeonexec_flag, int nonblock_flag) { int connfd, acceptfd; int fdf, flf, fdf_pass, flf_pass; struct sockaddr_in claddr; socklen_t addrlen; printf("=======================================\n"); connfd = socket(AF_INET, SOCK_STREAM, 0); if (connfd == -1) die("socket"); if (connect(connfd, (struct sockaddr *) conn_addr, sizeof(struct sockaddr_in)) == -1) die("connect"); addrlen = sizeof(struct sockaddr_in); acceptfd = accept4(lfd, (struct sockaddr *) &claddr, &addrlen, closeonexec_flag | nonblock_flag); if (acceptfd == -1) { perror("accept4()"); close(connfd); return 0; } fdf = fcntl(acceptfd, F_GETFD); if (fdf == -1) die("fcntl:F_GETFD"); fdf_pass = ((fdf & FD_CLOEXEC) != 0) == ((closeonexec_flag & SOCK_CLOEXEC) != 0); printf("Close-on-exec flag is %sset (%s); ", (fdf & FD_CLOEXEC) ? "" : "not ", fdf_pass ? "OK" : "failed"); flf = fcntl(acceptfd, F_GETFL); if (flf == -1) die("fcntl:F_GETFD"); flf_pass = ((flf & O_NONBLOCK) != 0) == ((nonblock_flag & SOCK_NONBLOCK) !=0); printf("nonblock flag is %sset (%s)\n", (flf & O_NONBLOCK) ? "" : "not ", flf_pass ? "OK" : "failed"); close(acceptfd); close(connfd); printf("Test result: %s\n", (fdf_pass && flf_pass) ? "PASS" : "FAIL"); return fdf_pass && flf_pass; } static int create_listening_socket(int port_num) { struct sockaddr_in svaddr; int lfd; int optval; memset(&svaddr, 0, sizeof(struct sockaddr_in)); svaddr.sin_family = AF_INET; svaddr.sin_addr.s_addr = htonl(INADDR_ANY); svaddr.sin_port = htons(port_num); lfd = socket(AF_INET, SOCK_STREAM, 0); if (lfd == -1) die("socket"); optval = 1; if (setsockopt(lfd, SOL_SOCKET, SO_REUSEADDR, &optval, sizeof(optval)) == -1) die("setsockopt"); if (bind(lfd, (struct sockaddr *) &svaddr, sizeof(struct sockaddr_in)) == -1) die("bind"); if (listen(lfd, 5) == -1) die("listen"); return lfd; } int main(int argc, char *argv[]) { struct sockaddr_in conn_addr; int lfd; int port_num; int passed; passed = 1; port_num = (argc > 1) ? atoi(argv[1]) : PORT_NUM; memset(&conn_addr, 0, sizeof(struct sockaddr_in)); conn_addr.sin_family = AF_INET; conn_addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK); conn_addr.sin_port = htons(port_num); lfd = create_listening_socket(port_num); if (!do_test(lfd, &conn_addr, 0, 0)) passed = 0; if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, 0)) passed = 0; if (!do_test(lfd, &conn_addr, 0, SOCK_NONBLOCK)) passed = 0; if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, SOCK_NONBLOCK)) passed = 0; close(lfd); exit(passed ? EXIT_SUCCESS : EXIT_FAILURE); } [mtk.manpages@gmail.com: rewrote changelog, updated test program] Signed-off-by: Ulrich Drepper Tested-by: Michael Kerrisk Acked-by: Michael Kerrisk Cc: Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/unistd_64.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 834b2c1d89f..d2e415e6666 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -639,8 +639,8 @@ __SYSCALL(__NR_fallocate, sys_fallocate) __SYSCALL(__NR_timerfd_settime, sys_timerfd_settime) #define __NR_timerfd_gettime 287 __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime) -#define __NR_paccept 288 -__SYSCALL(__NR_paccept, sys_paccept) +#define __NR_accept4 288 +__SYSCALL(__NR_accept4, sys_accept4) #define __NR_signalfd4 289 __SYSCALL(__NR_signalfd4, sys_signalfd4) #define __NR_eventfd2 290 -- cgit v1.2.3-18-g5258 From 0ca4b6b00113b064c080d26d803d0d7c80fb5dc8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 20 Nov 2008 14:09:33 -0700 Subject: x86: Fix interrupt leak due to migration When we migrate an interrupt from one CPU to another, we set the move_in_progress flag and clean up the vectors later once they're not being used. If you're unlucky and call destroy_irq() before the vectors become un-used, the move_in_progress flag is never cleared, which causes the interrupt to become unusable. This was discovered by Jesse Brandeburg for whom it manifested as an MSI-X device refusing to use MSI-X mode when the driver was unloaded and reloaded repeatedly. Signed-off-by: Matthew Wilcox Signed-off-by: Linus Torvalds --- arch/x86/kernel/io_apic.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index 7a3f2028e2e..c9513e1ff28 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -1140,6 +1140,20 @@ static void __clear_irq_vector(int irq) cfg->vector = 0; cpus_clear(cfg->domain); + + if (likely(!cfg->move_in_progress)) + return; + cpus_and(mask, cfg->old_domain, cpu_online_map); + for_each_cpu_mask_nr(cpu, mask) { + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; + vector++) { + if (per_cpu(vector_irq, cpu)[vector] != irq) + continue; + per_cpu(vector_irq, cpu)[vector] = -1; + break; + } + } + cfg->move_in_progress = 0; } void __setup_vector_irq(int cpu) -- cgit v1.2.3-18-g5258