Searched hist:199603 (Results 1 - 6 of 6) sorted by relevance

/freebsd-10.1-release/sys/net/
H A Dbpf_jitter.cdiff 199603 Fri Nov 20 16:59:34 MST 2009 jkim - Allocate scratch memory on stack instead of pre-allocating it with
the filter as we do from bpf_filter()[1].
- Revert experimental use of contigmalloc(9)/contigfree(9). It has no
performance benefit over malloc(9)/free(9)[2].

Requested by: rwatson[1]
Pointed out by: rwatson, jhb, alc[2]
H A Dbpf_jitter.hdiff 199603 Fri Nov 20 16:59:34 MST 2009 jkim - Allocate scratch memory on stack instead of pre-allocating it with
the filter as we do from bpf_filter()[1].
- Revert experimental use of contigmalloc(9)/contigfree(9). It has no
performance benefit over malloc(9)/free(9)[2].

Requested by: rwatson[1]
Pointed out by: rwatson, jhb, alc[2]
/freebsd-10.1-release/sys/amd64/amd64/
H A Dbpf_jit_machdep.cdiff 199603 Fri Nov 20 16:59:34 MST 2009 jkim - Allocate scratch memory on stack instead of pre-allocating it with
the filter as we do from bpf_filter()[1].
- Revert experimental use of contigmalloc(9)/contigfree(9). It has no
performance benefit over malloc(9)/free(9)[2].

Requested by: rwatson[1]
Pointed out by: rwatson, jhb, alc[2]
H A Dbpf_jit_machdep.hdiff 199603 Fri Nov 20 16:59:34 MST 2009 jkim - Allocate scratch memory on stack instead of pre-allocating it with
the filter as we do from bpf_filter()[1].
- Revert experimental use of contigmalloc(9)/contigfree(9). It has no
performance benefit over malloc(9)/free(9)[2].

Requested by: rwatson[1]
Pointed out by: rwatson, jhb, alc[2]
/freebsd-10.1-release/sys/i386/i386/
H A Dbpf_jit_machdep.cdiff 199603 Fri Nov 20 16:59:34 MST 2009 jkim - Allocate scratch memory on stack instead of pre-allocating it with
the filter as we do from bpf_filter()[1].
- Revert experimental use of contigmalloc(9)/contigfree(9). It has no
performance benefit over malloc(9)/free(9)[2].

Requested by: rwatson[1]
Pointed out by: rwatson, jhb, alc[2]
H A Dbpf_jit_machdep.hdiff 199603 Fri Nov 20 16:59:34 MST 2009 jkim - Allocate scratch memory on stack instead of pre-allocating it with
the filter as we do from bpf_filter()[1].
- Revert experimental use of contigmalloc(9)/contigfree(9). It has no
performance benefit over malloc(9)/free(9)[2].

Requested by: rwatson[1]
Pointed out by: rwatson, jhb, alc[2]

Completed in 167 milliseconds