summaryrefslogblamecommitdiffstats
path: root/fs/jffs2/compr_rtime.c
blob: 406d9cc84ba8d99b7520b4ee931d9c010f9e5bea (plain) (tree)
1
2
3
4
5
6
7
8
9
10


                                                     
                                       
                                                               




                                                                       















                                                                        

                         




                                                         
                                                                      
 
                                      


                       

                                              


                                                             
 


                                                     
 

                                           
 











                                                                            
 



                                                                                         
 



                                                           
                                                                    
 
                                      

                       


                                              



                                    
 



                                                                                 
 








                                                                                       
                                               


                         
                 
 






















                                                        
/*
 * JFFS2 -- Journalling Flash File System, Version 2.
 *
 * Copyright © 2001-2007 Red Hat, Inc.
 * Copyright © 2004-2010 David Woodhouse <dwmw2@infradead.org>
 *
 * Created by Arjan van de Ven <arjanv@redhat.com>
 *
 * For licensing information, see the file 'LICENCE' in this directory.
 *
 *
 *
 * Very simple lz77-ish encoder.
 *
 * Theory of operation: Both encoder and decoder have a list of "last
 * occurrences" for every possible source-value; after sending the
 * first source-byte, the second byte indicated the "run" length of
 * matches
 *
 * The algorithm is intended to only send "whole bytes", no bit-messing.
 *
 */

#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/jffs2.h>
#include "compr.h"

/* _compress returns the compressed size, -1 if bigger */
static int jffs2_rtime_compress(unsigned char *data_in,
				unsigned char *cpage_out,
				uint32_t *sourcelen, uint32_t *dstlen)
{
	unsigned short positions[256];
	int outpos = 0;
	int pos=0;

	memset(positions,0,sizeof(positions));

	while (pos < (*sourcelen) && outpos <= (*dstlen)-2) {
		int backpos, runlen=0;
		unsigned char value;

		value = data_in[pos];

		cpage_out[outpos++] = data_in[pos++];

		backpos = positions[value];
		positions[value]=pos;

		while ((backpos < pos) && (pos < (*sourcelen)) &&
		       (data_in[pos]==data_in[backpos++]) && (runlen<255)) {
			pos++;
			runlen++;
		}
		cpage_out[outpos++] = runlen;
	}

	if (outpos >= pos) {
		/* We failed */
		return -1;
	}

	/* Tell the caller how much we managed to compress, and how much space it took */
	*sourcelen = pos;
	*dstlen = outpos;
	return 0;
}


static int jffs2_rtime_decompress(unsigned char *data_in,
				  unsigned char *cpage_out,
				  uint32_t srclen, uint32_t destlen)
{
	unsigned short positions[256];
	int outpos = 0;
	int pos=0;

	memset(positions,0,sizeof(positions));

	while (outpos<destlen) {
		unsigned char value;
		int backoffs;
		int repeat;

		value = data_in[pos++];
		cpage_out[outpos++] = value; /* first the verbatim copied byte */
		repeat = data_in[pos++];
		backoffs = positions[value];

		positions[value]=outpos;
		if (repeat) {
			if (backoffs + repeat >= outpos) {
				while(repeat) {
					cpage_out[outpos++] = cpage_out[backoffs++];
					repeat--;
				}
			} else {
				memcpy(&cpage_out[outpos],&cpage_out[backoffs],repeat);
				outpos+=repeat;
			}
		}
	}
	return 0;
}

static struct jffs2_compressor jffs2_rtime_comp = {
    .priority = JFFS2_RTIME_PRIORITY,
    .name = "rtime",
    .compr = JFFS2_COMPR_RTIME,
    .compress = &jffs2_rtime_compress,
    .decompress = &jffs2_rtime_decompress,
#ifdef JFFS2_RTIME_DISABLED
    .disabled = 1,
#else
    .disabled = 0,
#endif
};

int jffs2_rtime_init(void)
{
    return jffs2_register_compressor(&jffs2_rtime_comp);
}

void jffs2_rtime_exit(void)
{
    jffs2_unregister_compressor(&jffs2_rtime_comp);
}
ommitgraph'>| * RDMA/netlink: Fix general protection faultLeon Romanovsky2017-12-074-4/+4 | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The RDMA netlink core code checks validity of messages by ensuring that type and operand are in range. It works well for almost all clients except NLDEV, which has cb_table less than number of operands. Request to access such operand will trigger the following kernel panic. This patch updates all places where cb_table is declared for the consistency, but only NLDEV is actually need it. general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN Modules linked in: CPU: 0 PID: 522 Comm: syz-executor6 Not tainted 4.13.0+ #4 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014 task: ffff8800657799c0 task.stack: ffff8800695d000 RIP: 0010:rdma_nl_rcv_msg+0x13a/0x4c0 RSP: 0018:ffff8800695d7838 EFLAGS: 00010207 RAX: dffffc0000000000 RBX: 1ffff1000d2baf0b RCX: 00000000704ff4d7 RDX: 0000000000000000 RSI: ffffffff81ddb03c RDI: 00000003827fa6bc RBP: ffff8800695d7900 R08: ffffffff82ec0578 R09: 0000000000000000 R10: ffff8800695d7900 R11: 0000000000000001 R12: 000000000000001c R13: ffff880069d31e00 R14: 00000000ffffffff R15: ffff880069d357c0 FS: 00007fee6acb8700(0000) GS:ffff88006ca00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000201a9000 CR3: 0000000059766000 CR4: 00000000000006b0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? rdma_nl_multicast+0x80/0x80 rdma_nl_rcv+0x36b/0x4d0 ? ibnl_put_attr+0xc0/0xc0 netlink_unicast+0x4bd/0x6d0 ? netlink_sendskb+0x50/0x50 ? drop_futex_key_refs.isra.4+0x68/0xb0 netlink_sendmsg+0x9ab/0xbd0 ? nlmsg_notify+0x140/0x140 ? wake_up_q+0xa1/0xf0 ? drop_futex_key_refs.isra.4+0x68/0xb0 sock_sendmsg+0x88/0xd0 sock_write_iter+0x228/0x3c0 ? sock_sendmsg+0xd0/0xd0 ? do_futex+0x3e5/0xb20 ? iov_iter_init+0xaf/0x1d0 __vfs_write+0x46e/0x640 ? sched_clock_cpu+0x1b/0x190 ? __vfs_read+0x620/0x620 ? __fget+0x23a/0x390 ? rw_verify_area+0xca/0x290 vfs_write+0x192/0x490 SyS_write+0xde/0x1c0 ? SyS_read+0x1c0/0x1c0 ? trace_hardirqs_on_thunk+0x1a/0x1c entry_SYSCALL_64_fastpath+0x18/0xad RIP: 0033:0x7fee6a74a219 RSP: 002b:00007fee6acb7d58 EFLAGS: 00000212 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000638000 RCX: 00007fee6a74a219 RDX: 0000000000000078 RSI: 0000000020141000 RDI: 0000000000000006 RBP: 0000000000000046 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000212 R12: ffff8800695d7f98 R13: 0000000020141000 R14: 0000000000000006 R15: 00000000ffffffff Code: d6 48 b8 00 00 00 00 00 fc ff df 66 41 81 e4 ff 03 44 8d 72 ff 4a 8d 3c b5 c0 a6 7f 82 44 89 b5 4c ff ff ff 48 89 f9 48 c1 e9 03 <0f> b6 0c 01 48 89 f8 83 e0 07 83 c0 03 38 c8 7c 08 84 c9 0f 85 RIP: rdma_nl_rcv_msg+0x13a/0x4c0 RSP: ffff8800695d7838 ---[ end trace ba085d123959c8ec ]--- Kernel panic - not syncing: Fatal exception Cc: syzkaller <syzkaller@googlegroups.com> Fixes: b4c598a67ea1 ("RDMA/netlink: Implement nldev device dumpit calback") Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com> | * IB/mlx4: Fix RSS hash fields restrictionsGuy Levi2017-12-071-7/+19 | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Mistakenly the driver didn't allow RSS hash fields combinations which involve both IPv4 and IPv6 protocols. This bug caused to failures for user's use cases for RSS. Consequently, this patch fixes this bug and allows any combination that the HW can support. Additionally, the patch fixes the driver to return an error in case the user provides an unsupported mask for RSS hash fields. Fixes: 3078f5f1bd8b ("IB/mlx4: Add support for RSS QP") Signed-off-by: Guy Levi <guyle@mellanox.com> Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com> | * IB/core: Don't enforce PKey security on SMI MADsDaniel Jurgens2017-12-071-2/+5 | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Per the infiniband spec an SMI MAD can have any PKey. Checking the pkey on SMI MADs is not necessary, and it seems that some older adapters using the mthca driver don't follow the convention of using the default PKey, resulting in false denials, or errors querying the PKey cache. SMI MAD security is still enforced, only agents allowed to manage the subnet are able to receive or send SMI MADs. Reported-by: Chris Blake <chrisrblake93@gmail.com> Cc: <stable@vger.kernel.org> # v4.12 Fixes: 47a2b338fe63 ("IB/core: Enforce security on management datagrams") Signed-off-by: Daniel Jurgens <danielj@mellanox.com> Reviewed-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com> | * IB/core: Bound check alternate path port numberDaniel Jurgens2017-12-071-0/+6 | | | | | | | | | | | | | | | | | | | | | | | | The alternate port number is used as an array index in the IB security implementation, invalid values can result in a kernel panic. Cc: <stable@vger.kernel.org> # v4.12 Fixes: d291f1a65232 ("IB/core: Enforce PKey security on QPs") Signed-off-by: Daniel Jurgens <danielj@mellanox.com> Reviewed-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com> * | Merge branch 'i2c/for-current' of ↵Linus Torvalds2017-12-166-20/+19Star |\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux Pull i2c fixes from Wolfram Sang: "Two bugfixes for the AT24 I2C eeprom driver and some minor corrections for I2C bus drivers" * 'i2c/for-current' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux: i2c: piix4: Fix port number check on release i2c: stm32: Fix copyrights i2c-cht-wc: constify platform_device_id eeprom: at24: change nvmem stride to 1 eeprom: at24: fix I2C device selection for runtime PM | * | i2c: piix4: Fix port number check on releaseJean Delvare2017-12-121-1/+1 | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The port number shift is still hard-coded to 1 while it now depends on the hardware. Thankfully 0 is always 0 no matter how you shift it, so this was a bug without consequences. Signed-off-by: Jean Delvare <jdelvare@suse.de> Fixes: 0fe16195f891 ("i2c: piix4: Fix SMBus port selection for AMD Family 17h chips") Reviewed-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Wolfram Sang <wsa@the-dreams.de> | * | i2c: stm32: Fix copyrightsBenjamin Gaignard2017-12-123-3/+6 | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Uniformize STMicroelectronics copyrights headers and add SPDX identifier. Signed-off-by: Benjamin Gaignard <benjamin.gaignard@st.com> Acked-by: Alexandre TORGUE <alexandre.torgue@st.com> Acked-by: Pierre-Yves MORDRET <pierre-yves.mordret@st.com> Acked-by: M'boumba Cedric Madianga <cedric.madianga@gmail.com> Signed-off-by: Wolfram Sang <wsa@the-dreams.de> | * | Merge tag 'at24-4.15-rc3-fixes-for-wolfram' of ↵Wolfram Sang2017-12-121-15/+11Star | |\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux into i2c/for-current Sakari fixed a regression introduced during the 4.15 merge window and David submitted a fix for an issue that has existed in at24 since introducing nvmem. | | * | eeprom: at24: change nvmem stride to 1David Lechner2017-12-061-1/+1 | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Trying to read the MAC address from an eeprom that has an offset that is not a multiple of 4 causes an error currently. Fix it by changing the nvmem stride to 1. Cc: stable@vger.kernel.org Signed-off-by: David Lechner <david@lechnology.com> [Bartosz: tweaked the commit message] Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl> | | * | eeprom: at24: fix I2C device selection for runtime PMSakari Ailus2017-12-031-14/+10Star | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The at24 driver creates dummy I2C devices to access offsets in the chip that are outside the area supported using a single I2C address. It is not meaningful to use runtime PM to such devices; the system firmware (ACPI) does not know about these devices nor runtime PM was enabled for them. Always use the real device instead of the dummy ones. Fixes: 98e8201039af ("eeprom: at24: enable runtime pm support") Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com> Tested-by: Sven Van Asbroeck on a 24AA16/24LC16B <svendev@arcx.com> [Bartosz: rebased on top of previous fixes for 4.15, tweaked the commit message] [Sven: fixed Bartosz's rebase] Signed-off-by: Sven Van Asbroeck <svendev@arcx.com> Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl> | * | | i2c-cht-wc: constify platform_device_idArvind Yadav2017-12-071-1/+1 | |/ / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | platform_device_id are not supposed to change at runtime. All functions working with platform_device_id provided by <linux/platform_device.h> work with const platform_device_id. So mark the non-const structs as const. Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com> Reviewed-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Wolfram Sang <wsa@the-dreams.de> * | | Merge tag 'nfs-for-4.15-3' of git://git.linux-nfs.org/projects/anna/linux-nfsLinus Torvalds2017-12-168-19/+50 |\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull NFS client fixes from Anna Schumaker: "This has two stable bugfixes, one to fix a BUG_ON() when nfs_commit_inode() is called with no outstanding commit requests and another to fix a race in the SUNRPC receive codepath. Additionally, there are also fixes for an NFS client deadlock and an xprtrdma performance regression. Summary: Stable bugfixes: - NFS: Avoid a BUG_ON() in nfs_commit_inode() by not waiting for a commit in the case that there were no commit requests. - SUNRPC: Fix a race in the receive code path Other fixes: - NFS: Fix a deadlock in nfs client initialization - xprtrdma: Fix a performance regression for small IOs" * tag 'nfs-for-4.15-3' of git://git.linux-nfs.org/projects/anna/linux-nfs: SUNRPC: Fix a race in the receive code path nfs: don't wait on commit in nfs_commit_inode() if there were no commit requests xprtrdma: Spread reply processing over more CPUs nfs: fix a deadlock in nfs client initialization | * | | SUNRPC: Fix a race in the receive code pathTrond Myklebust2017-12-151-9/+19 | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We must ensure that the call to rpc_sleep_on() in xprt_transmit() cannot race with the call to xprt_complete_rqst(). Reported-by: Chuck Lever <chuck.lever@oracle.com> Link: https://bugzilla.linux-nfs.org/show_bug.cgi?id=317 Fixes: ce7c252a8c74 ("SUNRPC: Add a separate spinlock to protect..") Cc: stable@vger.kernel.org # 4.14+ Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> | * | | nfs: don't wait on commit in nfs_commit_inode() if there were no commit requestsScott Mayhew2017-12-151-0/+2 | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If there were no commit requests, then nfs_commit_inode() should not wait on the commit or mark the inode dirty, otherwise the following BUG_ON can be triggered: [ 1917.130762] kernel BUG at fs/inode.c:578! [ 1917.130766] Oops: Exception in kernel mode, sig: 5 [#1] [ 1917.130768] SMP NR_CPUS=2048 NUMA pSeries [ 1917.130772] Modules linked in: iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi blocklayoutdriver rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache sunrpc sg nx_crypto pseries_rng ip_tables xfs libcrc32c sd_mod crc_t10dif crct10dif_generic crct10dif_common ibmvscsi scsi_transport_srp ibmveth scsi_tgt dm_mirror dm_region_hash dm_log dm_mod [ 1917.130805] CPU: 2 PID: 14923 Comm: umount.nfs4 Tainted: G ------------ T 3.10.0-768.el7.ppc64 #1 [ 1917.130810] task: c0000005ecd88040 ti: c00000004cea0000 task.ti: c00000004cea0000 [ 1917.130813] NIP: c000000000354178 LR: c000000000354160 CTR: c00000000012db80 [ 1917.130816] REGS: c00000004cea3720 TRAP: 0700 Tainted: G ------------ T (3.10.0-768.el7.ppc64) [ 1917.130820] MSR: 8000000100029032 <SF,EE,ME,IR,DR,RI> CR: 22002822 XER: 20000000 [ 1917.130828] CFAR: c00000000011f594 SOFTE: 1 GPR00: c000000000354160 c00000004cea39a0 c0000000014c4700 c0000000018cc750 GPR04: 000000000000c750 80c0000000000000 0600000000000000 04eeb76bea749a03 GPR08: 0000000000000034 c0000000018cc758 0000000000000001 d000000005e619e8 GPR12: c00000000012db80 c000000007b31200 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR24: 0000000000000000 c000000000dfc3ec 0000000000000000 c0000005eefc02c0 GPR28: d0000000079dbd50 c0000005b94a02c0 c0000005b94a0250 c0000005b94a01c8 [ 1917.130867] NIP [c000000000354178] .evict+0x1c8/0x350 [ 1917.130871] LR [c000000000354160] .evict+0x1b0/0x350 [ 1917.130873] Call Trace: [ 1917.130876] [c00000004cea39a0] [c000000000354160] .evict+0x1b0/0x350 (unreliable) [ 1917.130880] [c00000004cea3a30] [c0000000003558cc] .evict_inodes+0x13c/0x270 [ 1917.130884] [c00000004cea3af0] [c000000000327d20] .kill_anon_super+0x70/0x1e0 [ 1917.130896] [c00000004cea3b80] [d000000005e43e30] .nfs_kill_super+0x20/0x60 [nfs] [ 1917.130900] [c00000004cea3c00] [c000000000328a20] .deactivate_locked_super+0xa0/0x1b0 [ 1917.130903] [c00000004cea3c80] [c00000000035ba54] .cleanup_mnt+0xd4/0x180 [ 1917.130907] [c00000004cea3d10] [c000000000119034] .task_work_run+0x114/0x150 [ 1917.130912] [c00000004cea3db0] [c00000000001ba6c] .do_notify_resume+0xcc/0x100 [ 1917.130916] [c00000004cea3e30] [c00000000000a7b0] .ret_from_except_lite+0x5c/0x60 [ 1917.130919] Instruction dump: [ 1917.130921] 7fc3f378 486734b5 60000000 387f00a0 38800003 4bdcb365 60000000 e95f00a0 [ 1917.130927] 694a0060 7d4a0074 794ad182 694a0001 <0b0a0000> 892d02a4 2f890000 40de0134 Signed-off-by: Scott Mayhew <smayhew@redhat.com> Cc: stable@vger.kernel.org # 4.5+ Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> | * | | xprtrdma: Spread reply processing over more CPUsChuck Lever2017-12-154-6/+5Star | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit d8f532d20ee4 ("xprtrdma: Invoke rpcrdma_reply_handler directly from RECV completion") introduced a performance regression for NFS I/O small enough to not need memory registration. In multi- threaded benchmarks that generate primarily small I/O requests, IOPS throughput is reduced by nearly a third. This patch restores the previous level of throughput. Because workqueues are typically BOUND (in particular ib_comp_wq, nfsiod_workqueue, and rpciod_workqueue), NFS/RDMA workloads tend to aggregate on the CPU that is handling Receive completions. The usual approach to addressing this problem is to create a QP and CQ for each CPU, and then schedule transactions on the QP for the CPU where you want the transaction to complete. The transaction then does not require an extra context switch during completion to end up on the same CPU where the transaction was started. This approach doesn't work for the Linux NFS/RDMA client because currently the Linux NFS client does not support multiple connections per client-server pair, and the RDMA core API does not make it straightforward for ULPs to determine which CPU is responsible for handling Receive completions for a CQ. So for the moment, record the CPU number in the rpcrdma_req before the transport sends each RPC Call. Then during Receive completion, queue the RPC completion on that same CPU. Additionally, move all RPC completion processing to the deferred handler so that even RPCs with simple small replies complete on the CPU that sent the corresponding RPC Call. Fixes: d8f532d20ee4 ("xprtrdma: Invoke rpcrdma_reply_handler ...") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> | * | | nfs: fix a deadlock in nfs client initializationScott Mayhew2017-12-152-4/+24 | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The following deadlock can occur between a process waiting for a client to initialize in while walking the client list during nfsv4 server trunking detection and another process waiting for the nfs_clid_init_mutex so it can initialize that client: Process 1 Process 2 --------- --------- spin_lock(&nn->nfs_client_lock); list_add_tail(&CLIENTA->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); spin_lock(&nn->nfs_client_lock); list_add_tail(&CLIENTB->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); mutex_lock(&nfs_clid_init_mutex); nfs41_walk_client_list(clp, result, cred); nfs_wait_client_init_complete(CLIENTA); (waiting for nfs_clid_init_mutex) Make sure nfs_match_client() only evaluates clients that have completed initialization in order to prevent that deadlock. This patch also fixes v4.0 trunking behavior by not marking the client NFS_CS_READY until the clientid has been confirmed. Signed-off-by: Scott Mayhew <smayhew@redhat.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> * | | | Revert "mm: replace p??_write with pte_access_permitted in fault + gup paths"Linus Torvalds2017-12-167-22/+15Star | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commits 5c9d2d5c269c, c7da82b894e9, and e7fe7b5cae90. We'll probably need to revisit this, but basically we should not complicate the get_user_pages_fast() case, and checking the actual page table protection key bits will require more care anyway, since the protection keys depend on the exact state of the VM in question. Particularly when doing a "remote" page lookup (ie in somebody elses VM, not your own), you need to be much more careful than this was. Dave Hansen says: "So, the underlying bug here is that we now a get_user_pages_remote() and then go ahead and do the p*_access_permitted() checks against the current PKRU. This was introduced recently with the addition of the new p??_access_permitted() calls. We have checks in the VMA path for the "remote" gups and we avoid consulting PKRU for them. This got missed in the pkeys selftests because I did a ptrace read, but not a *write*. I also didn't explicitly test it against something where a COW needed to be done" It's also not entirely clear that it makes sense to check the protection key bits at this level at all. But one possible eventual solution is to make the get_user_pages_fast() case just abort if it sees protection key bits set, which makes us fall back to the regular get_user_pages() case, which then has a vma and can do the check there if we want to. We'll see. Somewhat related to this all: what we _do_ want to do some day is to check the PAGE_USER bit - it should obviously always be set for user pages, but it would be a good check to have back. Because we have no generic way to test for it, we lost it as part of moving over from the architecture-specific x86 GUP implementation to the generic one in commit e585513b76f7 ("x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation"). Cc: Peter Zijlstra <peterz@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> * | | | Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netLinus Torvalds2017-12-15