Re: Re: [PATCH V2 1/3] riscv: Add Zicbop instruction definitions & cpufeature
From: Andrew Jones
Date: Wed Jan 03 2024 - 01:50:01 EST
On Wed, Jan 03, 2024 at 02:13:00PM +0800, Guo Ren wrote:
> On Tue, Jan 2, 2024 at 6:32 PM Andrew Jones <ajones@xxxxxxxxxxxxxxxx> wrote:
> >
> > On Sun, Dec 31, 2023 at 03:29:51AM -0500, guoren@xxxxxxxxxx wrote:
> > > From: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
> > >
> > > Cache-block prefetch instructions are HINTs to the hardware to
> > > indicate that software intends to perform a particular type of
> > > memory access in the near future. This patch adds prefetch.i,
> > > prefetch.r and prefetch.w instruction definitions by
> > > RISCV_ISA_EXT_ZICBOP cpufeature.
> >
> > It also adds S-type instruction encoding support which isn't mentioned.
> > Actually, it'd probably be best to put the new instruction encoding in
> > its own separate patch.
> Okay, I would separate the instruction encoding patch in the next version.
>
> >
> > >
> > > Signed-off-by: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
> > > Signed-off-by: Guo Ren <guoren@xxxxxxxxxx>
> > > ---
> > > arch/riscv/Kconfig | 15 ++++++++
> > > arch/riscv/include/asm/hwcap.h | 1 +
> > > arch/riscv/include/asm/insn-def.h | 60 +++++++++++++++++++++++++++++++
> > > arch/riscv/kernel/cpufeature.c | 1 +
> > > 4 files changed, 77 insertions(+)
> > >
> > > diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> > > index 24c1799e2ec4..fcbd417d65ea 100644
> > > --- a/arch/riscv/Kconfig
> > > +++ b/arch/riscv/Kconfig
> > > @@ -579,6 +579,21 @@ config RISCV_ISA_ZICBOZ
> > >
> > > If you don't know what to do here, say Y.
> > >
> > > +config RISCV_ISA_ZICBOP
> > > + bool "Zicbop extension support for cache block prefetch"
> > > + depends on MMU
> > > + depends on RISCV_ALTERNATIVE
> > > + default y
> > > + help
> > > + Adds support to dynamically detect the presence of the ZICBOP
> > > + extension (Cache Block Prefetch Operations) and enable its
> > > + usage.
> > > +
> > > + The Zicbop extension can be used to prefetch cache block for
> >
> > blocks
> >
> > > + read/write fetch.
> > > +
> > > + If you don't know what to do here, say Y.
> > > +
> > > config TOOLCHAIN_HAS_ZIHINTPAUSE
> > > bool
> > > default y
> > > diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
> > > index 06d30526ef3b..77d3b6ee25ab 100644
> > > --- a/arch/riscv/include/asm/hwcap.h
> > > +++ b/arch/riscv/include/asm/hwcap.h
> > > @@ -57,6 +57,7 @@
> > > #define RISCV_ISA_EXT_ZIHPM 42
> > > #define RISCV_ISA_EXT_SMSTATEEN 43
> > > #define RISCV_ISA_EXT_ZICOND 44
> > > +#define RISCV_ISA_EXT_ZICBOP 45
> > >
> > > #define RISCV_ISA_EXT_MAX 64
> > >
> > > diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h
> > > index e27179b26086..bbda350a63bf 100644
> > > --- a/arch/riscv/include/asm/insn-def.h
> > > +++ b/arch/riscv/include/asm/insn-def.h
> > > @@ -18,6 +18,13 @@
> > > #define INSN_I_RD_SHIFT 7
> > > #define INSN_I_OPCODE_SHIFT 0
> > >
> > > +#define INSN_S_SIMM7_SHIFT 25
> > > +#define INSN_S_RS2_SHIFT 20
> > > +#define INSN_S_RS1_SHIFT 15
> > > +#define INSN_S_FUNC3_SHIFT 12
> > > +#define INSN_S_SIMM5_SHIFT 7
> > > +#define INSN_S_OPCODE_SHIFT 0
> > > +
> > > #ifdef __ASSEMBLY__
> > >
> > > #ifdef CONFIG_AS_HAS_INSN
> > > @@ -30,6 +37,10 @@
> > > .insn i \opcode, \func3, \rd, \rs1, \simm12
> > > .endm
> > >
> > > + .macro insn_s, opcode, func3, rs2, simm12, rs1
> > > + .insn s \opcode, \func3, \rs2, \simm12(\rs1)
> > > + .endm
> > > +
> > > #else
> > >
> > > #include <asm/gpr-num.h>
> > > @@ -51,10 +62,20 @@
> > > (\simm12 << INSN_I_SIMM12_SHIFT))
> > > .endm
> > >
> > > + .macro insn_s, opcode, func3, rs2, simm12, rs1
> > > + .4byte ((\opcode << INSN_S_OPCODE_SHIFT) | \
> > > + (\func3 << INSN_S_FUNC3_SHIFT) | \
> > > + (.L__gpr_num_\rs2 << INSN_S_RS2_SHIFT) | \
> > > + (.L__gpr_num_\rs1 << INSN_S_RS1_SHIFT) | \
> > > + ((\simm12 & 0x1f) << INSN_S_SIMM5_SHIFT) | \
> > > + (((\simm12 >> 5) & 0x7f) << INSN_S_SIMM7_SHIFT))
> > > + .endm
> > > +
> > > #endif
> > >
> > > #define __INSN_R(...) insn_r __VA_ARGS__
> > > #define __INSN_I(...) insn_i __VA_ARGS__
> > > +#define __INSN_S(...) insn_s __VA_ARGS__
> > >
> > > #else /* ! __ASSEMBLY__ */
> > >
> > > @@ -66,6 +87,9 @@
> > > #define __INSN_I(opcode, func3, rd, rs1, simm12) \
> > > ".insn i " opcode ", " func3 ", " rd ", " rs1 ", " simm12 "\n"
> > >
> > > +#define __INSN_S(opcode, func3, rs2, simm12, rs1) \
> > > + ".insn s " opcode ", " func3 ", " rs2 ", " simm12 "(" rs1 ")\n"
> > > +
> > > #else
> > >
> > > #include <linux/stringify.h>
> > > @@ -92,12 +116,26 @@
> > > " (\\simm12 << " __stringify(INSN_I_SIMM12_SHIFT) "))\n" \
> > > " .endm\n"
> > >
> > > +#define DEFINE_INSN_S \
> > > + __DEFINE_ASM_GPR_NUMS \
> > > +" .macro insn_s, opcode, func3, rs2, simm12, rs1\n" \
> > > +" .4byte ((\\opcode << " __stringify(INSN_S_OPCODE_SHIFT) ") |" \
> > > +" (\\func3 << " __stringify(INSN_S_FUNC3_SHIFT) ") |" \
> > > +" (.L__gpr_num_\\rs2 << " __stringify(INSN_S_RS2_SHIFT) ") |" \
> > > +" (.L__gpr_num_\\rs1 << " __stringify(INSN_S_RS1_SHIFT) ") |" \
> > > +" ((\\simm12 & 0x1f) << " __stringify(INSN_S_SIMM5_SHIFT) ") |" \
> > > +" (((\\simm12 >> 5) & 0x7f) << " __stringify(INSN_S_SIMM7_SHIFT) "))\n" \
> > > +" .endm\n"
> > > +
> > > #define UNDEFINE_INSN_R \
> > > " .purgem insn_r\n"
> > >
> > > #define UNDEFINE_INSN_I \
> > > " .purgem insn_i\n"
> > >
> > > +#define UNDEFINE_INSN_S \
> > > +" .purgem insn_s\n"
> > > +
> > > #define __INSN_R(opcode, func3, func7, rd, rs1, rs2) \
> > > DEFINE_INSN_R \
> > > "insn_r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n" \
> > > @@ -108,6 +146,11 @@
> > > "insn_i " opcode ", " func3 ", " rd ", " rs1 ", " simm12 "\n" \
> > > UNDEFINE_INSN_I
> > >
> > > +#define __INSN_S(opcode, func3, rs2, simm12, rs1) \
> > > + DEFINE_INSN_S \
> > > + "insn_s " opcode ", " func3 ", " rs2 ", " simm12 ", " rs1 "\n" \
> > > + UNDEFINE_INSN_S
> > > +
> > > #endif
> > >
> > > #endif /* ! __ASSEMBLY__ */
> > > @@ -120,6 +163,10 @@
> > > __INSN_I(RV_##opcode, RV_##func3, RV_##rd, \
> > > RV_##rs1, RV_##simm12)
> > >
> > > +#define INSN_S(opcode, func3, rs2, simm12, rs1) \
> > > + __INSN_S(RV_##opcode, RV_##func3, RV_##rs2, \
> > > + RV_##simm12, RV_##rs1)
> > > +
> > > #define RV_OPCODE(v) __ASM_STR(v)
> > > #define RV_FUNC3(v) __ASM_STR(v)
> > > #define RV_FUNC7(v) __ASM_STR(v)
> > > @@ -133,6 +180,7 @@
> > > #define RV___RS2(v) __RV_REG(v)
> > >
> > > #define RV_OPCODE_MISC_MEM RV_OPCODE(15)
> > > +#define RV_OPCODE_OP_IMM RV_OPCODE(19)
> > > #define RV_OPCODE_SYSTEM RV_OPCODE(115)
> > >
> > > #define HFENCE_VVMA(vaddr, asid) \
> > > @@ -196,4 +244,16 @@
> > > INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \
> > > RS1(base), SIMM12(4))
> > >
> > > +#define CBO_PREFETCH_I(base, offset) \
> > > + INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(0), \
> > > + SIMM12(offset), RS1(base))
> > > +
> > > +#define CBO_PREFETCH_R(base, offset) \
> > > + INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(1), \
> > > + SIMM12(offset), RS1(base))
> > > +
> > > +#define CBO_PREFETCH_W(base, offset) \
> > > + INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(3), \
> > > + SIMM12(offset), RS1(base))
> >
> > Shouldn't we ensure the lower 5-bits of offset are zero by masking it?
> The spec says:
> "These instructions operate on the cache block whose effective address
> is the sum of the base address specified in rs1 and the sign-extended
> offset encoded in imm[11:0], where imm[4:0] shall equal 0b00000. The
> effective address is translated into a corresponding physical address
> by the appropriate translation mechanisms."
>
> So, the user of prefetch.w should keep imm[4:0] zero.
Yes, the user _should_ keep imm[4:0] zero. Unless we can validate at
compile time that all users have passed offsets with the lower 5-bits
set to zero, then I think we should mask them here, since I'd rather
not provide the user a footgun.
> Just like the
> patch has done, the whole imm[11:0] is zero.
That's just one possible use, and I think exposing the offset operand to
users makes sense for unrolled sequences of invocations, so I wouldn't
count on offset always being zero.
Thanks,
drew