I went ahead and did the forward bisect, here's the final step:

 $ git bisect good
0691783adb950a3839cc2bae5117c30e48c89539 is the first bad commit
commit 0691783adb950a3839cc2bae5117c30e48c89539
Author: Trond Myklebust <email address hidden>
Date:   Sun Aug 30 18:37:59 2015 -0700

    NFSv4.1: Fix a protocol issue with CLOSE stateids
    
    commit 4a1e2feb9d246775dee0f78ed5b18826bae2b1c5 upstream.
    
    According to RFC5661 Section 18.2.4, CLOSE is supposed to return
    the zero stateid. This means that nfs_clear_open_stateid_locked()
    cannot assume that the result stateid will always match the 'other'
    field of the existing open stateid when trying to determine a race
    with a parallel OPEN.
    
    Instead, we look at the argument, and check for matches.
    
    Signed-off-by: Trond Myklebust <email address hidden>
    Signed-off-by: Greg Kroah-Hartman <email address hidden>

:040000 040000 cacf56a9f720cac415b4a20b597bfed7354d18ac aba15a8e370ad358f94d16ed4e6bb72fb7636daa M	fs

And for the record, here's the log:

 $ git bisect log
git bisect start
# bad: [1c02865136fee1d10d434dc9e3616c8e39905e9b] Linux 4.2.6
git bisect bad 1c02865136fee1d10d434dc9e3616c8e39905e9b
# good: [64291f7db5bd8150a74ad2036f1037e6a0428df2] Linux 4.2
git bisect good 64291f7db5bd8150a74ad2036f1037e6a0428df2
# bad: [496c2053cd784dd653d295e499503f14907022b3] x86/efi: Fix boot crash by mapping EFI memmap entries bottom-up at runtime, instead of top-down
git bisect bad 496c2053cd784dd653d295e499503f14907022b3
# good: [9c67f424970dd732af60ed2378ff2f6bb7463edf] powerpc/pseries: Release DRC when configure_connector fails
git bisect good 9c67f424970dd732af60ed2378ff2f6bb7463edf
# bad: [9a04c65c6bcd5fea9e892d338f3d3da8df46c9a1] sctp: fix race on protocol/netns initialization
git bisect bad 9a04c65c6bcd5fea9e892d338f3d3da8df46c9a1
# bad: [7d36bc720a19bcd7be6161cbe36bb81914e30459] parisc: Filter out spurious interrupts in PA-RISC irq handler
git bisect bad 7d36bc720a19bcd7be6161cbe36bb81914e30459
# good: [18ea445c33dc60bebdc55348a882b1bb172ff05a] NFS: Don't let the ctime override attribute barriers.
git bisect good 18ea445c33dc60bebdc55348a882b1bb172ff05a
# bad: [8fd1f7a1c4bbfb43f3f17d12f5c60925ebd9dd6c] svcrdma: Change maximum server payload back to RPCSVC_MAXPAYLOAD
git bisect bad 8fd1f7a1c4bbfb43f3f17d12f5c60925ebd9dd6c
# good: [95141b15234777ad155895d1cb1e6f41eb2182ed] NFSv4: Force a post-op attribute update when holding a delegation
git bisect good 95141b15234777ad155895d1cb1e6f41eb2182ed
# bad: [0691783adb950a3839cc2bae5117c30e48c89539] NFSv4.1: Fix a protocol issue with CLOSE stateids
git bisect bad 0691783adb950a3839cc2bae5117c30e48c89539
# good: [f232178c124f70fddaeb81dfd82ec25c0fba58cc] NFSv4.1/flexfiles: Fix a protocol error in layoutreturn
git bisect good f232178c124f70fddaeb81dfd82ec25c0fba58cc
# first bad commit: [0691783adb950a3839cc2bae5117c30e48c89539] NFSv4.1: Fix a protocol issue with CLOSE stateids

Let me know if additional information would be helpful.  I'll leave the 10+ test kernels installed for a few more days, but I'd like to clean them out as soon as possible (it's a cluttered boot menu right now...)

Thanks.