Merge pobox.com:/garz/repo/linux-2.6

into pobox.com:/garz/repo/libata-2.6

9 files changed, 157 insertions, 87 deletions

diff --git a/include/asm-m32r/bitops.h b/include/asm-m32r/bitops.h
index dd8c7eb7263a..e78443981349 100644
--- a/include/asm-m32r/bitops.h
+++ b/include/asm-m32r/bitops.h
@@ -405,9 +405,10 @@ static __inline__ unsigned long ffz(unsigned long word)
  * @offset: The bitnumber to start searching at
  * @size: The maximum size to search
  */
-static __inline__ int find_next_zero_bit(void *addr, int size, int offset)
+static __inline__ int find_next_zero_bit(const unsigned long *addr,
+					 int size, int offset)
 {
-	unsigned long *p = ((unsigned long *) addr) + (offset >> 5);
+	const unsigned long *p = addr + (offset >> 5);
 	unsigned long result = offset & ~31UL;
 	unsigned long tmp;
 
diff --git a/include/asm-ppc/pgtable.h b/include/asm-ppc/pgtable.h
index fb6af1716074..642c86b74121 100644
--- a/include/asm-ppc/pgtable.h
+++ b/include/asm-ppc/pgtable.h
@@ -560,12 +560,12 @@ extern void flush_hash_one_pte(pte_t *ptep);
 static inline int ptep_test_and_clear_young(pte_t *ptep)
 {
 	unsigned long old;
-	old = (pte_update(ptep, _PAGE_ACCESSED, 0) & _PAGE_ACCESSED);
+	old = pte_update(ptep, _PAGE_ACCESSED, 0);
 #if _PAGE_HASHPTE != 0
 	if (old & _PAGE_HASHPTE)
 		flush_hash_one_pte(ptep);
 #endif
-	return old != 0;
+	return (old & _PAGE_ACCESSED) != 0;
 }
 
 static inline int ptep_test_and_clear_dirty(pte_t *ptep)
diff --git a/include/asm-sparc64/compat.h b/include/asm-sparc64/compat.h
index da9c81a6af5a..2950279dd776 100644
--- a/include/asm-sparc64/compat.h
+++ b/include/asm-sparc64/compat.h
@@ -24,6 +24,7 @@ typedef u16		compat_ipc_pid_t;
 typedef s32		compat_daddr_t;
 typedef u32		compat_caddr_t;
 typedef __kernel_fsid_t	compat_fsid_t;
+typedef s32		compat_key_t;
 
 typedef s32		compat_int_t;
 typedef s32		compat_long_t;
@@ -139,4 +140,62 @@ static __inline__ void __user *compat_alloc_user_space(long len)
 	return (void __user *) (usp - len);
 }
 
+struct compat_ipc64_perm {
+	compat_key_t key;
+	__kernel_uid_t uid;
+	__kernel_gid_t gid;
+	__kernel_uid_t cuid;
+	__kernel_gid_t cgid;
+	unsigned short __pad1;
+	compat_mode_t mode;
+	unsigned short __pad2;
+	unsigned short seq;
+	unsigned long __unused1;	/* yes they really are 64bit pads */
+	unsigned long __unused2;
+};
+
+struct compat_semid64_ds {
+	struct compat_ipc64_perm sem_perm;
+	unsigned int	__pad1;
+	compat_time_t	sem_otime;
+	unsigned int	__pad2;
+	compat_time_t	sem_ctime;
+	u32		sem_nsems;
+	u32		__unused1;
+	u32		__unused2;
+};
+
+struct compat_msqid64_ds {
+	struct compat_ipc64_perm msg_perm;
+	unsigned int	__pad1;
+	compat_time_t	msg_stime;
+	unsigned int	__pad2;
+	compat_time_t	msg_rtime;
+	unsigned int	__pad3;
+	compat_time_t	msg_ctime;
+	unsigned int	msg_cbytes;
+	unsigned int	msg_qnum;
+	unsigned int	msg_qbytes;
+	compat_pid_t	msg_lspid;
+	compat_pid_t	msg_lrpid;
+	unsigned int	__unused1;
+	unsigned int	__unused2;
+};
+
+struct compat_shmid64_ds {
+	struct compat_ipc64_perm shm_perm;
+	unsigned int	__pad1;
+	compat_time_t	shm_atime;
+	unsigned int	__pad2;
+	compat_time_t	shm_dtime;
+	unsigned int	__pad3;
+	compat_time_t	shm_ctime;
+	compat_size_t	shm_segsz;
+	compat_pid_t	shm_cpid;
+	compat_pid_t	shm_lpid;
+	unsigned int	shm_nattch;
+	unsigned int	__unused1;
+	unsigned int	__unused2;
+};
+
 #endif /* _ASM_SPARC64_COMPAT_H */
diff --git a/include/asm-sparc64/uaccess.h b/include/asm-sparc64/uaccess.h
index 28a52769dfc4..56646813a6af 100644
--- a/include/asm-sparc64/uaccess.h
+++ b/include/asm-sparc64/uaccess.h
@@ -49,10 +49,10 @@ do {										\
 	__asm__ __volatile__ ("wr %%g0, %0, %%asi" : : "r" ((val).seg));	\
 } while(0)
 
-#define __user_ok(addr,size) 1
+#define __user_ok(addr,size) ((void)(addr), (void)(size), 1)
 #define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
-#define __access_ok(addr,size) 1
-#define access_ok(type,addr,size) 1
+#define __access_ok(addr,size) ((void)(addr), (void)(size), 1)
+#define access_ok(type,addr,size) ((void)(type), (void)(addr), (void)(size), 1)
 
 static inline int verify_area(int type, const void __user * addr, unsigned long size)
 {
diff --git a/include/linux/compat.h b/include/linux/compat.h
index a62f5c960c75..f67748fda899 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -18,6 +18,8 @@
 #define compat_jiffies_to_clock_t(x)	\
 		(((unsigned long)(x) * COMPAT_USER_HZ) / HZ)
 
+struct rusage;
+
 struct compat_itimerspec { 
 	struct compat_timespec it_interval;
 	struct compat_timespec it_value;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 84b3b114f943..30cb440cb6c8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -7,25 +7,8 @@
  */
 
 #include <linux/config.h>
-#include <linux/linkage.h>
 #include <linux/limits.h>
-#include <linux/wait.h>
-#include <linux/types.h>
-#include <linux/kdev_t.h>
 #include <linux/ioctl.h>
-#include <linux/dcache.h>
-#include <linux/stat.h>
-#include <linux/cache.h>
-#include <linux/kobject.h>
-#include <asm/atomic.h>
-
-struct iovec;
-struct nameidata;
-struct pipe_inode_info;
-struct poll_table_struct;
-struct kstatfs;
-struct vm_area_struct;
-struct vfsmount;
 
 /*
  * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
@@ -216,14 +199,32 @@ extern int dir_notify_enable;
 
 #ifdef __KERNEL__
 
+#include <linux/linkage.h>
+#include <linux/wait.h>
+#include <linux/types.h>
+#include <linux/kdev_t.h>
+#include <linux/dcache.h>
+#include <linux/stat.h>
+#include <linux/cache.h>
+#include <linux/kobject.h>
 #include <linux/list.h>
 #include <linux/radix-tree.h>
 #include <linux/prio_tree.h>
 #include <linux/audit.h>
 #include <linux/init.h>
+
+#include <asm/atomic.h>
 #include <asm/semaphore.h>
 #include <asm/byteorder.h>
 
+struct iovec;
+struct nameidata;
+struct pipe_inode_info;
+struct poll_table_struct;
+struct kstatfs;
+struct vm_area_struct;
+struct vfsmount;
+
 /* Used to be a macro which just called the function, now just a function */
 extern void update_atime (struct inode *);
 
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 06bdf80154fb..33642be4ce00 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -344,6 +344,7 @@ enum
 	NET_TCP_DEFAULT_WIN_SCALE=105,
 	NET_TCP_MODERATE_RCVBUF=106,
 	NET_TCP_TSO_WIN_DIVISOR=107,
+	NET_TCP_BIC_BETA=108,
 };
 
 enum {
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index b31ca0400372..f56e734c1da0 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -210,6 +210,27 @@ enum tcp_congestion_algo {
 	TCP_BIC,
 };
 
+struct tcp_options_received {
+/*	PAWS/RTTM data	*/
+	long	ts_recent_stamp;/* Time we stored ts_recent (for aging) */
+	__u32	ts_recent;	/* Time stamp to echo next		*/
+	__u32	rcv_tsval;	/* Time stamp value             	*/
+	__u32	rcv_tsecr;	/* Time stamp echo reply        	*/
+	char	saw_tstamp;	/* Saw TIMESTAMP on last packet		*/
+	char	tstamp_ok;	/* TIMESTAMP seen on SYN packet		*/
+	char	sack_ok;	/* SACK seen on SYN packet		*/
+	char	wscale_ok;	/* Wscale seen on SYN packet		*/
+	__u8	snd_wscale;	/* Window scaling received from sender	*/
+	__u8	rcv_wscale;	/* Window scaling to send to receiver	*/
+/*	SACKs data	*/
+	__u8	dsack;		/* D-SACK is scheduled			*/
+	__u8	eff_sacks;	/* Size of SACK array to send with next packet */
+	__u8	num_sacks;	/* Number of SACK blocks		*/
+	__u8	__pad;
+	__u16	user_mss;  	/* mss requested by user in ioctl */
+	__u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
+};
+
 struct tcp_sock {
 	/* inet_sock has to be the first member of tcp_sock */
 	struct inet_sock	inet;
@@ -262,22 +283,19 @@ struct tcp_sock {
 	__u32	pmtu_cookie;	/* Last pmtu seen by socket		*/
 	__u32	mss_cache;	/* Cached effective mss, not including SACKS */
 	__u16	mss_cache_std;	/* Like mss_cache, but without TSO */
-	__u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
 	__u16	ext_header_len;	/* Network protocol overhead (IP/IPv6 options) */
 	__u16	ext2_header_len;/* Options depending on route */
 	__u8	ca_state;	/* State of fast-retransmit machine 	*/
 	__u8	retransmits;	/* Number of unrecovered RTO timeouts.	*/
 
+	__u32	frto_highmark;	/* snd_nxt when RTO occurred */
 	__u8	reordering;	/* Packet reordering metric.		*/
 	__u8	frto_counter;	/* Number of new acks after RTO */
-	__u32	frto_highmark;	/* snd_nxt when RTO occurred */
 
 	__u8	adv_cong;	/* Using Vegas, Westwood, or BIC */
 	__u8	defer_accept;	/* User waits for some data after accept() */
-	/* one byte hole, try to pack */
 
 /* RTT measurement */
-	__u8	backoff;	/* backoff				*/
 	__u32	srtt;		/* smoothed round trip time << 3	*/
 	__u32	mdev;		/* medium deviation			*/
 	__u32	mdev_max;	/* maximal mdev for the last rtt period	*/
@@ -288,7 +306,15 @@ struct tcp_sock {
 	__u32	packets_out;	/* Packets which are "in flight"	*/
 	__u32	left_out;	/* Packets which leaved network	*/
 	__u32	retrans_out;	/* Retransmitted packets out		*/
+	__u8	backoff;	/* backoff				*/
+/*
+ *      Options received (usually on last packet, some only on SYN packets).
+ */
+	__u8	nonagle;	/* Disable Nagle algorithm?             */
+	__u8	keepalive_probes; /* num of allowed keep alive probes	*/
 
+	__u8	probes_out;	/* unanswered 0 window probes		*/
+	struct tcp_options_received rx_opt;
 
 /*
  *	Slow start and congestion control (see also Nagle, and Karn & Partridge)
@@ -314,40 +340,19 @@ struct tcp_sock {
 	__u32	write_seq;	/* Tail(+1) of data held in tcp send buffer */
 	__u32	pushed_seq;	/* Last pushed seq, required to talk to windows */
 	__u32	copied_seq;	/* Head of yet unread data		*/
-/*
- *      Options received (usually on last packet, some only on SYN packets).
- */
-	char	tstamp_ok,	/* TIMESTAMP seen on SYN packet		*/
-		wscale_ok,	/* Wscale seen on SYN packet		*/
-		sack_ok;	/* SACK seen on SYN packet		*/
-	char	saw_tstamp;	/* Saw TIMESTAMP on last packet		*/
-        __u8	snd_wscale;	/* Window scaling received from sender	*/
-        __u8	rcv_wscale;	/* Window scaling to send to receiver	*/
-	__u8	nonagle;	/* Disable Nagle algorithm?             */
-	__u8	keepalive_probes; /* num of allowed keep alive probes	*/
-
-/*	PAWS/RTTM data	*/
-        __u32	rcv_tsval;	/* Time stamp value             	*/
-        __u32	rcv_tsecr;	/* Time stamp echo reply        	*/
-        __u32	ts_recent;	/* Time stamp to echo next		*/
-        long	ts_recent_stamp;/* Time we stored ts_recent (for aging) */
 
 /*	SACKs data	*/
-	__u16	user_mss;  	/* mss requested by user in ioctl */
-	__u8	dsack;		/* D-SACK is scheduled			*/
-	__u8	eff_sacks;	/* Size of SACK array to send with next packet */
 	struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */
 	struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/
 
 	__u32	window_clamp;	/* Maximal window to advertise		*/
 	__u32	rcv_ssthresh;	/* Current window clamp			*/
-	__u8	probes_out;	/* unanswered 0 window probes		*/
-	__u8	num_sacks;	/* Number of SACK blocks		*/
 	__u16	advmss;		/* Advertised MSS			*/
 
 	__u8	syn_retries;	/* num of allowed syn retries */
 	__u8	ecn_flags;	/* ECN status bits.			*/
 	__u16	prior_ssthresh; /* ssthresh saved at recovery start	*/
+	__u16	__pad1;
 	__u32	lost_out;	/* Lost packets			*/
 	__u32	sacked_out;	/* SACK'd packets			*/
 	__u32	fackets_out;	/* FACK'd packets			*/
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 1a54cdba14ba..7355606725d4 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -505,9 +505,8 @@ static __inline__ int tcp_sk_listen_hashfn(struct sock *sk)
 # define TCP_TW_RECYCLE_TICK (12+2-TCP_TW_RECYCLE_SLOTS_LOG)
 #endif
 
-#define BICTCP_1_OVER_BETA	8	/*
-					 * Fast recovery
-					 * multiplicative decrease factor
+#define BICTCP_BETA_SCALE    1024	/* Scale factor beta calculation
+					 * max_cwnd = snd_cwnd * beta
 					 */
 #define BICTCP_MAX_INCREMENT 32		/*
 					 * Limit on the amount of
@@ -606,6 +605,7 @@ extern int sysctl_tcp_nometrics_save;
 extern int sysctl_tcp_bic;
 extern int sysctl_tcp_bic_fast_convergence;
 extern int sysctl_tcp_bic_low_window;
+extern int sysctl_tcp_bic_beta;
 extern int sysctl_tcp_moderate_rcvbuf;
 extern int sysctl_tcp_tso_win_divisor;
 
@@ -832,9 +832,9 @@ static __inline__ void tcp_delack_init(struct tcp_sock *tp)
 	memset(&tp->ack, 0, sizeof(tp->ack));
 }
 
-static inline void tcp_clear_options(struct tcp_sock *tp)
+static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 {
- 	tp->tstamp_ok = tp->sack_ok = tp->wscale_ok = tp->snd_wscale = 0;
+ 	rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
 }
 
 enum tcp_tw_status
@@ -883,7 +883,7 @@ extern int			tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
 extern int			tcp_listen_start(struct sock *sk);
 
 extern void			tcp_parse_options(struct sk_buff *skb,
-						  struct tcp_sock *tp,
+						  struct tcp_options_received *opt_rx,
 						  int estab);
 
 /*
@@ -1071,7 +1071,7 @@ static __inline__ void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
 
 static __inline__ void tcp_fast_path_on(struct tcp_sock *tp)
 {
-	__tcp_fast_path_on(tp, tp->snd_wnd>>tp->snd_wscale);
+	__tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
 }
 
 static inline void tcp_fast_path_check(struct sock *sk, struct tcp_sock *tp)
@@ -1244,15 +1244,16 @@ static inline __u32 tcp_recalc_ssthresh(struct tcp_sock *tp)
 	if (tcp_is_bic(tp)) {
 		if (sysctl_tcp_bic_fast_convergence &&
 		    tp->snd_cwnd < tp->bictcp.last_max_cwnd)
-			tp->bictcp.last_max_cwnd
-				= (tp->snd_cwnd * (2*BICTCP_1_OVER_BETA-1))
-				/ (BICTCP_1_OVER_BETA/2);
+			tp->bictcp.last_max_cwnd = (tp->snd_cwnd * 
+						    (BICTCP_BETA_SCALE
+						     + sysctl_tcp_bic_beta))
+				/ (2 * BICTCP_BETA_SCALE);
 		else
 			tp->bictcp.last_max_cwnd = tp->snd_cwnd;
 
 		if (tp->snd_cwnd > sysctl_tcp_bic_low_window)
-			return max(tp->snd_cwnd - (tp->snd_cwnd/BICTCP_1_OVER_BETA),
-				   2U);
+			return max((tp->snd_cwnd * sysctl_tcp_bic_beta)
+				   / BICTCP_BETA_SCALE, 2U);
 	}
 
 	return max(tp->snd_cwnd >> 1U, 2U);
@@ -1322,7 +1323,7 @@ static inline __u32 tcp_current_ssthresh(struct tcp_sock *tp)
 
 static inline void tcp_sync_left_out(struct tcp_sock *tp)
 {
-	if (tp->sack_ok &&
+	if (tp->rx_opt.sack_ok &&
 	    (tp->sacked_out >= tp->packets_out - tp->lost_out))
 		tp->sacked_out = tp->packets_out - tp->lost_out;
 	tp->left_out = tp->sacked_out + tp->lost_out;
@@ -1648,39 +1649,39 @@ static __inline__ void tcp_done(struct sock *sk)
 		tcp_destroy_sock(sk);
 }
 
-static __inline__ void tcp_sack_reset(struct tcp_sock *tp)
+static __inline__ void tcp_sack_reset(struct tcp_options_received *rx_opt)
 {
-	tp->dsack = 0;
-	tp->eff_sacks = 0;
-	tp->num_sacks = 0;
+	rx_opt->dsack = 0;
+	rx_opt->eff_sacks = 0;
+	rx_opt->num_sacks = 0;
 }
 
 static __inline__ void tcp_build_and_update_options(__u32 *ptr, struct tcp_sock *tp, __u32 tstamp)
 {
-	if (tp->tstamp_ok) {
+	if (tp->rx_opt.tstamp_ok) {
 		*ptr++ = __constant_htonl((TCPOPT_NOP << 24) |
 					  (TCPOPT_NOP << 16) |
 					  (TCPOPT_TIMESTAMP << 8) |
 					  TCPOLEN_TIMESTAMP);
 		*ptr++ = htonl(tstamp);
-		*ptr++ = htonl(tp->ts_recent);
+		*ptr++ = htonl(tp->rx_opt.ts_recent);
 	}
-	if (tp->eff_sacks) {
-		struct tcp_sack_block *sp = tp->dsack ? tp->duplicate_sack : tp->selective_acks;
+	if (tp->rx_opt.eff_sacks) {
+		struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks;
 		int this_sack;
 
 		*ptr++ = __constant_htonl((TCPOPT_NOP << 24) |
 					  (TCPOPT_NOP << 16) |
 					  (TCPOPT_SACK << 8) |
 					  (TCPOLEN_SACK_BASE +
-					   (tp->eff_sacks * TCPOLEN_SACK_PERBLOCK)));
-		for(this_sack = 0; this_sack < tp->eff_sacks; this_sack++) {
+					   (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK)));
+		for(this_sack = 0; this_sack < tp->rx_opt.eff_sacks; this_sack++) {
 			*ptr++ = htonl(sp[this_sack].start_seq);
 			*ptr++ = htonl(sp[this_sack].end_seq);
 		}
-		if (tp->dsack) {
-			tp->dsack = 0;
-			tp->eff_sacks--;
+		if (tp->rx_opt.dsack) {
+			tp->rx_opt.dsack = 0;
+			tp->rx_opt.eff_sacks--;
 		}
 	}
 }
@@ -1826,17 +1827,17 @@ static inline void tcp_synq_drop(struct sock *sk, struct open_request *req,
 }
 
 static __inline__ void tcp_openreq_init(struct open_request *req,
-					struct tcp_sock *tp,
+					struct tcp_options_received *rx_opt,
 					struct sk_buff *skb)
 {
 	req->rcv_wnd = 0;		/* So that tcp_send_synack() knows! */
 	req->rcv_isn = TCP_SKB_CB(skb)->seq;
-	req->mss = tp->mss_clamp;
-	req->ts_recent = tp->saw_tstamp ? tp->rcv_tsval : 0;
-	req->tstamp_ok = tp->tstamp_ok;
-	req->sack_ok = tp->sack_ok;
-	req->snd_wscale = tp->snd_wscale;
-	req->wscale_ok = tp->wscale_ok;
+	req->mss = rx_opt->mss_clamp;
+	req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
+	req->tstamp_ok = rx_opt->tstamp_ok;
+	req->sack_ok = rx_opt->sack_ok;
+	req->snd_wscale = rx_opt->snd_wscale;
+	req->wscale_ok = rx_opt->wscale_ok;
 	req->acked = 0;
 	req->ecn_ok = 0;
 	req->rmt_port = skb->h.th->source;
@@ -1885,11 +1886,11 @@ static inline int tcp_fin_time(const struct tcp_sock *tp)
 	return fin_timeout;
 }
 
-static inline int tcp_paws_check(const struct tcp_sock *tp, int rst)
+static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, int rst)
 {
-	if ((s32)(tp->rcv_tsval - tp->ts_recent) >= 0)
+	if ((s32)(rx_opt->rcv_tsval - rx_opt->ts_recent) >= 0)
 		return 0;
-	if (xtime.tv_sec >= tp->ts_recent_stamp + TCP_PAWS_24DAYS)
+	if (xtime.tv_sec >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)
 		return 0;
 
 	/* RST segments are not recommended to carry timestamp,
@@ -1904,7 +1905,7 @@ static inline int tcp_paws_check(const struct tcp_sock *tp, int rst)
 
 	   However, we can relax time bounds for RST segments to MSL.
 	 */
-	if (rst && xtime.tv_sec >= tp->ts_recent_stamp + TCP_PAWS_MSL)
+	if (rst && xtime.tv_sec >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
 		return 0;
 	return 1;
 }