From 130f1b8f35f14d27c43da755f3c9226318c17f57 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 26 Dec 2012 10:39:23 -0700 Subject: PCI: Add PCIe Link Capability link speed and width names Add standard #defines for the Supported Link Speeds field in the PCIe Link Capabilities register. Note that prior to PCIe spec r3.0, these encodings were defined: 0001b 2.5GT/s Link speed supported 0010b 5.0GT/s and 2.5GT/s Link speed supported Starting with spec r3.0, these encodings refer to bits 0 and 1 in the Supported Link Speeds Vector in the Link Capabilities 2 register, and bits 0 and 1 there mean 2.5 GT/s and 5.0 GT/s, respectively. Therefore, code that followed r2.0 and interpreted 0x1 as 2.5GT/s and 0x2 as 5.0GT/s will continue to work, and we can identify a device using the new encodings because it will have a non-zero Link Capabilities 2 register. Signed-off-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 6b7b6f1e2fd6..ebfadc56d1b4 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -458,6 +458,8 @@ #define PCI_EXP_DEVSTA_TRPND 0x20 /* Transactions Pending */ #define PCI_EXP_LNKCAP 12 /* Link Capabilities */ #define PCI_EXP_LNKCAP_SLS 0x0000000f /* Supported Link Speeds */ +#define PCI_EXP_LNKCAP_SLS_2_5GB 0x1 /* LNKCAP2 SLS Vector bit 0 (2.5GT/s) */ +#define PCI_EXP_LNKCAP_SLS_5_0GB 0x2 /* LNKCAP2 SLS Vector bit 1 (5.0GT/s) */ #define PCI_EXP_LNKCAP_MLW 0x000003f0 /* Maximum Link Width */ #define PCI_EXP_LNKCAP_ASPMS 0x00000c00 /* ASPM Support */ #define PCI_EXP_LNKCAP_L0SEL 0x00007000 /* L0s Exit Latency */ -- cgit v1.2.3 From 4a674f34ba04a002244edaf891b5da7fc1473ae8 Mon Sep 17 00:00:00 2001 From: Stanislav Kinsbursky Date: Fri, 4 Jan 2013 15:34:55 -0800 Subject: ipc: introduce message queue copy feature This patch is required for checkpoint/restore in userspace. c/r requires some way to get all pending IPC messages without deleting them from the queue (checkpoint can fail and in this case tasks will be resumed, so queue have to be valid). To achive this, new operation flag MSG_COPY for sys_msgrcv() system call was introduced. If this flag was specified, then mtype is interpreted as number of the message to copy. If MSG_COPY is set, then kernel will allocate dummy message with passed size, and then use new copy_msg() helper function to copy desired message (instead of unlinking it from the queue). Notes: 1) Return -ENOSYS if MSG_COPY is specified, but CONFIG_CHECKPOINT_RESTORE is not set. Signed-off-by: Stanislav Kinsbursky Cc: Serge Hallyn Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Al Viro Cc: KOSAKI Motohiro Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/msg.h | 1 + ipc/msg.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++-- ipc/msgutil.c | 38 ++++++++++++++++++++++++++++ ipc/util.h | 1 + 4 files changed, 102 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/msg.h b/include/uapi/linux/msg.h index 78dbd2f996a3..22d95c6854e0 100644 --- a/include/uapi/linux/msg.h +++ b/include/uapi/linux/msg.h @@ -10,6 +10,7 @@ /* msgrcv options */ #define MSG_NOERROR 010000 /* no error if message is too big */ #define MSG_EXCEPT 020000 /* recv any msg except of specified type.*/ +#define MSG_COPY 040000 /* copy (not remove) all queue messages */ /* Obsolete, used only for backwards compatibility and libc5 compiles */ struct msqid_ds { diff --git a/ipc/msg.c b/ipc/msg.c index cefc24f46e3e..d20ffc7d3f24 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -769,6 +769,45 @@ static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz) return msgsz; } +#ifdef CONFIG_CHECKPOINT_RESTORE +static inline struct msg_msg *fill_copy(unsigned long copy_nr, + unsigned long msg_nr, + struct msg_msg *msg, + struct msg_msg *copy) +{ + if (copy_nr == msg_nr) + return copy_msg(msg, copy); + return NULL; +} + +static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz, + int msgflg, long *msgtyp, + unsigned long *copy_number) +{ + struct msg_msg *copy; + + *copy_number = *msgtyp; + *msgtyp = 0; + /* + * Create dummy message to copy real message to. + */ + copy = load_msg(buf, bufsz); + if (!IS_ERR(copy)) + copy->m_ts = bufsz; + return copy; +} + +static inline void free_copy(int msgflg, struct msg_msg *copy) +{ + if (msgflg & MSG_COPY) + free_msg(copy); +} +#else +#define free_copy(msgflg, copy) do {} while (0) +#define prepare_copy(buf, sz, msgflg, msgtyp, copy_nr) ERR_PTR(-ENOSYS) +#define fill_copy(copy_nr, msg_nr, msg, copy) NULL +#endif + long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg, long (*msg_handler)(void __user *, struct msg_msg *, size_t)) @@ -777,19 +816,29 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, struct msg_msg *msg; int mode; struct ipc_namespace *ns; + struct msg_msg *copy; + unsigned long __maybe_unused copy_number; if (msqid < 0 || (long) bufsz < 0) return -EINVAL; + if (msgflg & MSG_COPY) { + copy = prepare_copy(buf, bufsz, msgflg, &msgtyp, ©_number); + if (IS_ERR(copy)) + return PTR_ERR(copy); + } mode = convert_mode(&msgtyp, msgflg); ns = current->nsproxy->ipc_ns; msq = msg_lock_check(ns, msqid); - if (IS_ERR(msq)) + if (IS_ERR(msq)) { + free_copy(msgflg, copy); return PTR_ERR(msq); + } for (;;) { struct msg_receiver msr_d; struct list_head *tmp; + long msg_counter = 0; msg = ERR_PTR(-EACCES); if (ipcperms(ns, &msq->q_perm, S_IRUGO)) @@ -809,8 +858,15 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, if (mode == SEARCH_LESSEQUAL && walk_msg->m_type != 1) { msgtyp = walk_msg->m_type - 1; + } else if (msgflg & MSG_COPY) { + msg = fill_copy(copy_number, + msg_counter, + walk_msg, copy); + if (msg) + break; } else break; + msg_counter++; } tmp = tmp->next; } @@ -823,6 +879,8 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, msg = ERR_PTR(-E2BIG); goto out_unlock; } + if (msgflg & MSG_COPY) + goto out_unlock; list_del(&msg->m_list); msq->q_qnum--; msq->q_rtime = get_seconds(); @@ -906,8 +964,10 @@ out_unlock: break; } } - if (IS_ERR(msg)) + if (IS_ERR(msg)) { + free_copy(msgflg, copy); return PTR_ERR(msg); + } bufsz = msg_handler(buf, msg, bufsz); free_msg(msg); diff --git a/ipc/msgutil.c b/ipc/msgutil.c index 6471f1bdae96..7eecdad40efc 100644 --- a/ipc/msgutil.c +++ b/ipc/msgutil.c @@ -102,7 +102,45 @@ out_err: free_msg(msg); return ERR_PTR(err); } +#ifdef CONFIG_CHECKPOINT_RESTORE +struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst) +{ + struct msg_msgseg *dst_pseg, *src_pseg; + int len = src->m_ts; + int alen; + + BUG_ON(dst == NULL); + if (src->m_ts > dst->m_ts) + return ERR_PTR(-EINVAL); + + alen = len; + if (alen > DATALEN_MSG) + alen = DATALEN_MSG; + + dst->next = NULL; + dst->security = NULL; + memcpy(dst + 1, src + 1, alen); + + len -= alen; + dst_pseg = dst->next; + src_pseg = src->next; + while (len > 0) { + alen = len; + if (alen > DATALEN_SEG) + alen = DATALEN_SEG; + memcpy(dst_pseg + 1, src_pseg + 1, alen); + dst_pseg = dst_pseg->next; + len -= alen; + src_pseg = src_pseg->next; + } + + dst->m_type = src->m_type; + dst->m_ts = src->m_ts; + + return dst; +} +#endif int store_msg(void __user *dest, struct msg_msg *msg, int len) { int alen; diff --git a/ipc/util.h b/ipc/util.h index a61e0ca2bffd..eeb79a1fbd83 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -140,6 +140,7 @@ int ipc_parse_version (int *cmd); extern void free_msg(struct msg_msg *msg); extern struct msg_msg *load_msg(const void __user *src, int len); +extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst); extern int store_msg(void __user *dest, struct msg_msg *msg, int len); extern void recompute_msgmni(struct ipc_namespace *); -- cgit v1.2.3 From 7b9205bd775afc4439ed86d617f9042ee9e76a71 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 11 Jan 2013 14:32:05 -0800 Subject: audit: create explicit AUDIT_SECCOMP event type The seccomp path was using AUDIT_ANOM_ABEND from when seccomp mode 1 could only kill a process. While we still want to make sure an audit record is forced on a kill, this should use a separate record type since seccomp mode 2 introduces other behaviors. In the case of "handled" behaviors (process wasn't killed), only emit a record if the process is under inspection. This change also fixes userspace examination of seccomp audit events, since it was considered malformed due to missing fields of the AUDIT_ANOM_ABEND event type. Signed-off-by: Kees Cook Cc: Al Viro Cc: Eric Paris Cc: Jeff Layton Cc: "Eric W. Biederman" Cc: Julien Tinnes Acked-by: Will Drewry Acked-by: Steve Grubb Cc: Andrea Arcangeli Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/audit.h | 3 ++- include/uapi/linux/audit.h | 1 + kernel/auditsc.c | 14 +++++++++++--- 3 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index bce729afbcf9..9d5104d7aba9 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -157,7 +157,8 @@ void audit_core_dumps(long signr); static inline void audit_seccomp(unsigned long syscall, long signr, int code) { - if (unlikely(!audit_dummy_context())) + /* Force a record to be reported if a signal was delivered. */ + if (signr || unlikely(!audit_dummy_context())) __audit_seccomp(syscall, signr, code); } diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 76352ac45f24..09a2d94ab113 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -106,6 +106,7 @@ #define AUDIT_MMAP 1323 /* Record showing descriptor and flags in mmap */ #define AUDIT_NETFILTER_PKT 1324 /* Packets traversing netfilter chains */ #define AUDIT_NETFILTER_CFG 1325 /* Netfilter chain modifications */ +#define AUDIT_SECCOMP 1326 /* Secure Computing event */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index e37e6a12c5e3..3e46d1dec613 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2675,7 +2675,7 @@ void __audit_mmap_fd(int fd, int flags) context->type = AUDIT_MMAP; } -static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr) +static void audit_log_task(struct audit_buffer *ab) { kuid_t auid, uid; kgid_t gid; @@ -2693,6 +2693,11 @@ static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr) audit_log_task_context(ab); audit_log_format(ab, " pid=%d comm=", current->pid); audit_log_untrustedstring(ab, current->comm); +} + +static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr) +{ + audit_log_task(ab); audit_log_format(ab, " reason="); audit_log_string(ab, reason); audit_log_format(ab, " sig=%ld", signr); @@ -2723,8 +2728,11 @@ void __audit_seccomp(unsigned long syscall, long signr, int code) { struct audit_buffer *ab; - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); - audit_log_abend(ab, "seccomp", signr); + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_SECCOMP); + if (unlikely(!ab)) + return; + audit_log_task(ab); + audit_log_format(ab, " sig=%ld", signr); audit_log_format(ab, " syscall=%ld", syscall); audit_log_format(ab, " compat=%d", is_compat_task()); audit_log_format(ab, " ip=0x%lx", KSTK_EIP(current)); -- cgit v1.2.3 From c0a3a20b6c4b5229ef5d26fd9b1c4b1957632aa7 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Fri, 11 Jan 2013 14:32:13 -0800 Subject: linux/audit.h: move ptrace.h include to kernel header While the kernel internals want pt_regs (and so it includes linux/ptrace.h), the user version of audit.h does not need it. So move the include out of the uapi version. This avoids issues where people want the audit defines and userland ptrace api. Including both the kernel ptrace and the userland ptrace headers can easily lead to failure. Signed-off-by: Mike Frysinger Cc: Eric Paris Cc: Al Viro Reviewed-by: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/audit.h | 1 + include/uapi/linux/audit.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 9d5104d7aba9..5a6d718adf34 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -24,6 +24,7 @@ #define _LINUX_AUDIT_H_ #include +#include #include struct audit_sig_info { diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 09a2d94ab113..9f096f1c0907 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -26,7 +26,6 @@ #include #include -#include /* The netlink messages for the audit system is divided into blocks: * 1000 - 1099 are for commanding the audit system -- cgit v1.2.3