@@ -30,6 +30,7 @@ config PARISC
select TTY # Needed for pdc_cons.c
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_HASH
select HAVE_ARCH_SECCOMP_FILTER
select ARCH_NO_COHERENT_DMA_MMAP
new file mode 100644
@@ -0,0 +1,182 @@
+#ifndef _ASM_HASH_H
+#define _ASM_HASH_H
+
+/*
+ * HP-PA only implements integer multiply in the FPU. However, for
+ * integer multiplies by constant, it has a number of shift-and-add
+ * (but no shift-and-subtract, sigh!) instructions that a compiler
+ * can synthesize a code sequence with.
+ *
+ * Unfortunately, GCC isn't very efficient at using them. For example
+ * it uses three instructions for "x *= 21" when only two are needed.
+ * But we can find a sequence manually.
+ */
+
+#define HAVE_ARCH__HASH_32 1
+
+/*
+ * This is a multiply by GOLDEN_RATIO_32 = 0x61C88647 optimized for the
+ * PA7100 pairing rules. This is an in-order 2-way superscalar processor.
+ * Only one instruction in a pair may be a shift (by more than 3 bits),
+ * but other than that, simple ALU ops (including shift-and-add by up
+ * to 3 bits) may be paired arbitrarily.
+ *
+ * PA8xxx processors are out of order and don't need such careful
+ * scheduling.
+ *
+ * This 6-step sequence was found by Yevgen Voronenko's implementation
+ * of the Hcub algorithm at http://spiral.ece.cmu.edu/mcm/gen.html.
+ */
+static inline u32 __attribute_const__ __hash_32(u32 x)
+{
+ u32 a, b, c;
+
+ /*
+ * Phase 1: Compute a = (x << 19) + x,
+ * b = (x << 9) + a, c = (x << 23) + b.
+ */
+ a = x << 19; /* Two shifts can't be paired */
+ b = x << 9; a += x;
+ c = x << 23; b += a;
+ c += b;
+ /* Phase 2: Return (b<<11) + (c<<6) + (a<<3) - c */
+ b <<= 11;
+ a += c << 3; b -= c;
+ return (a << 3) + b;
+}
+
+#if BITS_PER_LONG == 64
+
+#define HAVE_ARCH_HASH_64 1
+
+#if HAVE_ARCH_HASH_64 == 1
+/*
+ * Multiply by GOLDEN_RATIO_64. Finding a good shift-and-add chain for
+ * this is tricky, because available software for the purpose chokes on
+ * constants this large. (It's mostly used for compiling FIR filter
+ * coefficients into FPGAs.)
+ *
+ * However, Jason Thong pointed out a work-around. The Hcub software
+ * (http://spiral.ece.cmu.edu/mcm/gen.html) is designed for *multiple*
+ * constant multiplication, and is good at finding shift-and-add chains
+ * which share common terms.
+ *
+ * Looking at 0x0x61C8864680B583EB in binary:
+ * 0110000111001000100001100100011010000000101101011000001111101011
+ * \______________/ \__________/ \_______/ \________/
+ * \____________________________/ \____________________/
+ * you can see the non-zero bits are divided into several well-separated
+ * blocks. Hcub can find algorithms for those terms separately, which
+ * can then be shifted and added together.
+ *
+ * Various combinations all work, but using just two large blocks,
+ * 0xC3910C8D << 31 in the high bits, and 0xB583EB in the low bits,
+ * produces as good an algorithm as any, and with one more small shift
+ * than alternatives.
+ *
+ * The high bits are a larger number and more work to compute, as well
+ * as needing one extra cycle to shift left 31 bits before the final
+ * addition, so they are the critical path for scheduling. The low bits
+ * can fit into the scheduling slots left over.
+ *
+ * This is scheduled for the PA-8xxx series, which can issue up to
+ * 2 ALU operations (of any type, adds or shifts) per cycle.
+ *
+ * In several places, the construction asm("" : (=r) (dest) : "0" (src));
+ * is used. This basically performs "dest = src", but prevents gcc from
+ * inferring anything about the value assigned to "dest". This blocks it
+ * from some mistaken optimizations like rearranging "y += z; x -= y;"
+ * into "x -= z; x -= y;", or "x <<= 23; y += x; z += x << 1;" into
+ * "y += x << 23; z += x << 24;".
+ *
+ * Because the actual assembly generated is empty, this construct is
+ * usefully portable across all GCC platforms, and so can be test-compiled
+ * on non-PA systems.
+ *
+ * In two places, additional unused input dependencies are added. This
+ * forces GCC's scheduling so it does not rearrange instructions too much.
+ */
+static __always_inline u32 __attribute_const__
+hash_64(u64 a, unsigned int bits)
+{
+ u64 b, c, d;
+
+ asm("" : "=r" (b) : "0" (a * 5)); // b = a * 5
+ c = a << 13;
+
+ b = (b << 2) + a; // b = a * 21
+ asm("" : "=r" (d) : "0" (a << 17)); // d = a << 17
+
+ a = b + (a << 1); // a = a * 23
+ c += d;
+
+ d = a << 10;
+ asm("" : "=r" (a) : "0" (a << 19)); // a <<= 19
+
+ d = a - d;
+ asm("" : "=r" (a) : "0" (a << 4), // a <<= 4;
+ "X" (d)); // Force dependency, damn it!
+
+ a += b;
+ c += b;
+
+ d -= c;
+ c += a << 1;
+
+ asm("" : "=r" (b) : "0" (b << 7+31), // b <<= 7+31;
+ "X" (c), "X" (d)); // Force dependency, damn it!
+ a += c << 3;
+
+ b += d;
+ a <<= 31;
+
+ a += b;
+ return a >> (64 - bits);
+}
+
+#else /* HAVE_ARCH_HASH_64 != 1 */
+/*
+ * If we don't care about matching the generic function, here's an
+ * alternative hash function; Thomas Wang's 64-to-32 bit hash function.
+ * https://web.archive.org/web/2011/http://www.concentric.net/~Ttwang/tech/inthash.htm
+ * http://burtleburtle.net/bob/hash/integer.html
+ *
+ * This algorithm concentrates the entropy in the low bits of the output,
+ * so they are returned.
+ *
+ * Compared to the multiply, this uses 2 registers (rather than 4), and
+ * 12 instructions (rather than 20), but each instruction in sequentially
+ * dependent, so it's 10 cycles (rather than 8).
+ *
+ * (In both cases, I'm not counting the final extract of the desired bits.)
+ */
+static __always_inline u32 __attribute_const__
+hash_64(u64 x, unsigned int bits)
+{
+ u64 y;
+
+ if (!__builtin_constant_p(bits))
+ asm("mtsarcm %1" : "=q" (bits) : "r" (bits));
+
+ x = ~x + (x << 18);
+ x ^= x >> 31;
+ y = x * 5; /* GCC uses 3 instructions for "x *= 21" */
+ x += y << 2;
+ x ^= x >> 11;
+ x += x << 6;
+ x ^= x >> 22;
+
+ if (__builtin_constant_p(bits)) {
+ x = x >> (64 - bits) << (64 - bits);
+ } else {
+ asm("depdi,z -1,%%sar,64,%0" : "=r" (y) : "q" (bits));
+ x &= ~y;
+ }
+
+ return x;
+}
+
+#endif /* HAVE_ARCH_HASH_64 */
+#endif /* BITS_PER_LONG == 64 */
+
+#endif /* _ASM_HASH_H */
PA-RISC is interesting; integer multiplies are implemented in the FPU, so are painful in the kernel. But it tries to be friendly to shift-and-add sequences. __hash_32 is implemented using the same shift-and-add sequence as Microblaze, just scheduled for the PA7100. (It's 2-way superscalar but in-order, like the Pentium.) hash_64 was tricky, but a suggestion from Jason Thong allowed a good solution by breaking up the multiplier. After an embarrassing amount of fiddling about, I found a 19-instruction sequence for the multiply that can be executed in 10 cycles using only 4 temporaries. (The PA8xxx can issue 4 instructions per cycle, but 2 must be ALU ops and 2 must be loads/stores. And the final add can't be paired.) An alternative implementation is included, but not enabled by default: Thomas Wang's 64-to-32-bit hash. This is more compact than the multiply, but has a slightly longer dependency chain. Signed-off-by: George Spelvin <linux@sciencehorizons.net> Cc: Helge Deller <deller@gmx.de> Cc: linux-parisc@vger.kernel.org --- Okay, I'm happy with this one. Helge, could you test it whenever you get a chance? I've left the alternate hash_64 path in for now, but the one not chosen should be deleted before sending to Linus. arch/parisc/Kconfig | 1 + arch/parisc/include/asm/hash.h | 182 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 183 insertions(+) create mode 100644 arch/parisc/include/asm/hash.h