All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Gibson <david@gibson.dropbear.id.au>
To: "Paul A. Clarke" <pc@us.ibm.com>
Cc: richard.henderson@linaro.org, qemu-ppc@nongnu.org, qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [PATCH v4] ppc: Add support for 'mffsl' instruction
Date: Sat, 17 Aug 2019 18:18:11 +1000	[thread overview]
Message-ID: <20190817081811.GE2259@umbus.fritz.box> (raw)
In-Reply-To: <1565982203-11048-1-git-send-email-pc@us.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 8388 bytes --]

On Fri, Aug 16, 2019 at 02:03:23PM -0500, Paul A. Clarke wrote:
65;5603;1c> From: "Paul A. Clarke" <pc@us.ibm.com>
> 
> ISA 3.0B added a set of Floating-Point Status and Control Register (FPSCR)
> instructions: mffsce, mffscdrn, mffscdrni, mffscrn, mffscrni, mffsl.
> This patch adds support for 'mffsl'.
> 
> 'mffsl' is identical to 'mffs', except it only returns mode, status, and enable
> bits from the FPSCR.
> 
> On CPUs without support for 'mffsl' (below ISA 3.0), the 'mffsl' instruction
> will execute identically to 'mffs'.
> 
> Note: I renamed FPSCR_RN to FPSCR_RN0 so I could create an FPSCR_RN mask which
> is both bits of the FPSCR rounding mode, as defined in the ISA.
> 
> I also fixed a typo in the definition of FPSCR_FR.
> 
> Signed-off-by: Paul A. Clarke <pc@us.ibm.com>

Applied to ppc-for-4.2, thanks.

> 
> v4:
> - nit: added some braces to resolve a checkpatch complaint.
> 
> v3:
> - Changed tcg_gen_and_i64 to tcg_gen_andi_i64, eliminating the need for a
>   temporary, per review from Richard Henderson.
> 
> v2:
> - I found that I copied too much of the 'mffs' implementation.
>   The 'Rc' condition code bits are not needed for 'mffsl'.  Removed.
> - I now free the (renamed) 'tmask' temporary.
> - I now bail early for older ISA to the original 'mffs' implementation.
> 
> ---
>  disas/ppc.c                        |  5 +++++
>  target/ppc/cpu.h                   | 15 ++++++++++-----
>  target/ppc/fpu_helper.c            |  4 ++--
>  target/ppc/translate/fp-impl.inc.c | 22 ++++++++++++++++++++++
>  target/ppc/translate/fp-ops.inc.c  |  4 +++-
>  5 files changed, 42 insertions(+), 8 deletions(-)
> 
> diff --git a/disas/ppc.c b/disas/ppc.c
> index a545437..63e97cf 100644
> --- a/disas/ppc.c
> +++ b/disas/ppc.c
> @@ -1765,6 +1765,9 @@ extract_tbr (unsigned long insn,
>  /* An X_MASK with the RA and RB fields fixed.  */
>  #define XRARB_MASK (X_MASK | RA_MASK | RB_MASK)
>  
> +/* An X form instruction with the RA field fixed.  */
> +#define XRA(op, xop, ra) (X((op), (xop)) | (((ra) << 16) & XRA_MASK))
> +
>  /* An XRARB_MASK, but with the L bit clear.  */
>  #define XRLARB_MASK (XRARB_MASK & ~((unsigned long) 1 << 16))
>  
> @@ -4998,6 +5001,8 @@ const struct powerpc_opcode powerpc_opcodes[] = {
>  { "ddivq",   XRC(63,546,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
>  { "ddivq.",  XRC(63,546,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
>  
> +{ "mffsl",   XRA(63,583,12), XRARB_MASK,	POWER9,	{ FRT } },
> +
>  { "mffs",    XRC(63,583,0), XRARB_MASK,	COM,		{ FRT } },
>  { "mffs.",   XRC(63,583,1), XRARB_MASK,	COM,		{ FRT } },
>  
> diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
> index c9beba2..74e8da4 100644
> --- a/target/ppc/cpu.h
> +++ b/target/ppc/cpu.h
> @@ -591,7 +591,7 @@ enum {
>  #define FPSCR_XE     3  /* Floating-point inexact exception enable           */
>  #define FPSCR_NI     2  /* Floating-point non-IEEE mode                      */
>  #define FPSCR_RN1    1
> -#define FPSCR_RN     0  /* Floating-point rounding control                   */
> +#define FPSCR_RN0    0  /* Floating-point rounding control                   */
>  #define fpscr_fex    (((env->fpscr) >> FPSCR_FEX)    & 0x1)
>  #define fpscr_vx     (((env->fpscr) >> FPSCR_VX)     & 0x1)
>  #define fpscr_ox     (((env->fpscr) >> FPSCR_OX)     & 0x1)
> @@ -614,7 +614,7 @@ enum {
>  #define fpscr_ze     (((env->fpscr) >> FPSCR_ZE)     & 0x1)
>  #define fpscr_xe     (((env->fpscr) >> FPSCR_XE)     & 0x1)
>  #define fpscr_ni     (((env->fpscr) >> FPSCR_NI)     & 0x1)
> -#define fpscr_rn     (((env->fpscr) >> FPSCR_RN)     & 0x3)
> +#define fpscr_rn     (((env->fpscr) >> FPSCR_RN0)    & 0x3)
>  /* Invalid operation exception summary */
>  #define fpscr_ix ((env->fpscr) & ((1 << FPSCR_VXSNAN) | (1 << FPSCR_VXISI)  | \
>                                    (1 << FPSCR_VXIDI)  | (1 << FPSCR_VXZDZ)  | \
> @@ -640,7 +640,7 @@ enum {
>  #define FP_VXZDZ        (1ull << FPSCR_VXZDZ)
>  #define FP_VXIMZ        (1ull << FPSCR_VXIMZ)
>  #define FP_VXVC         (1ull << FPSCR_VXVC)
> -#define FP_FR           (1ull << FSPCR_FR)
> +#define FP_FR           (1ull << FPSCR_FR)
>  #define FP_FI           (1ull << FPSCR_FI)
>  #define FP_C            (1ull << FPSCR_C)
>  #define FP_FL           (1ull << FPSCR_FL)
> @@ -648,7 +648,7 @@ enum {
>  #define FP_FE           (1ull << FPSCR_FE)
>  #define FP_FU           (1ull << FPSCR_FU)
>  #define FP_FPCC         (FP_FL | FP_FG | FP_FE | FP_FU)
> -#define FP_FPRF         (FP_C  | FP_FL | FP_FG | FP_FE | FP_FU)
> +#define FP_FPRF         (FP_C | FP_FPCC)
>  #define FP_VXSOFT       (1ull << FPSCR_VXSOFT)
>  #define FP_VXSQRT       (1ull << FPSCR_VXSQRT)
>  #define FP_VXCVI        (1ull << FPSCR_VXCVI)
> @@ -659,7 +659,12 @@ enum {
>  #define FP_XE           (1ull << FPSCR_XE)
>  #define FP_NI           (1ull << FPSCR_NI)
>  #define FP_RN1          (1ull << FPSCR_RN1)
> -#define FP_RN           (1ull << FPSCR_RN)
> +#define FP_RN0          (1ull << FPSCR_RN0)
> +#define FP_RN           (FP_RN1 | FP_RN0)
> +
> +#define FP_MODE         FP_RN
> +#define FP_ENABLES      (FP_VE | FP_OE | FP_UE | FP_ZE | FP_XE)
> +#define FP_STATUS       (FP_FR | FP_FI | FP_FPRF)
>  
>  /* the exception bits which can be cleared by mcrfs - includes FX */
>  #define FP_EX_CLEAR_BITS (FP_FX     | FP_OX     | FP_UX     | FP_ZX     | \
> diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
> index f437c88..5611cf0 100644
> --- a/target/ppc/fpu_helper.c
> +++ b/target/ppc/fpu_helper.c
> @@ -403,7 +403,7 @@ void helper_fpscr_clrbit(CPUPPCState *env, uint32_t bit)
>      if (prev == 1) {
>          switch (bit) {
>          case FPSCR_RN1:
> -        case FPSCR_RN:
> +        case FPSCR_RN0:
>              fpscr_set_rounding_mode(env);
>              break;
>          case FPSCR_VXSNAN:
> @@ -557,7 +557,7 @@ void helper_fpscr_setbit(CPUPPCState *env, uint32_t bit)
>              }
>              break;
>          case FPSCR_RN1:
> -        case FPSCR_RN:
> +        case FPSCR_RN0:
>              fpscr_set_rounding_mode(env);
>              break;
>          default:
> diff --git a/target/ppc/translate/fp-impl.inc.c b/target/ppc/translate/fp-impl.inc.c
> index 9dcff94..7cd9d8d 100644
> --- a/target/ppc/translate/fp-impl.inc.c
> +++ b/target/ppc/translate/fp-impl.inc.c
> @@ -617,6 +617,28 @@ static void gen_mffs(DisasContext *ctx)
>      tcg_temp_free_i64(t0);
>  }
>  
> +/* mffsl */
> +static void gen_mffsl(DisasContext *ctx)
> +{
> +    TCGv_i64 t0;
> +
> +    if (unlikely(!(ctx->insns_flags2 & PPC2_ISA300))) {
> +        return gen_mffs(ctx);
> +    }
> +
> +    if (unlikely(!ctx->fpu_enabled)) {
> +        gen_exception(ctx, POWERPC_EXCP_FPU);
> +        return;
> +    }
> +    t0 = tcg_temp_new_i64();
> +    gen_reset_fpstatus();
> +    tcg_gen_extu_tl_i64(t0, cpu_fpscr);
> +    /* Mask everything except mode, status, and enables.  */
> +    tcg_gen_andi_i64(t0, t0, FP_MODE | FP_STATUS | FP_ENABLES);
> +    set_fpr(rD(ctx->opcode), t0);
> +    tcg_temp_free_i64(t0);
> +}
> +
>  /* mtfsb0 */
>  static void gen_mtfsb0(DisasContext *ctx)
>  {
> diff --git a/target/ppc/translate/fp-ops.inc.c b/target/ppc/translate/fp-ops.inc.c
> index 621f6bf..88ebc25 100644
> --- a/target/ppc/translate/fp-ops.inc.c
> +++ b/target/ppc/translate/fp-ops.inc.c
> @@ -104,7 +104,9 @@ GEN_HANDLER_E(fcpsgn, 0x3F, 0x08, 0x00, 0x00000000, PPC_NONE, PPC2_ISA205),
>  GEN_HANDLER_E(fmrgew, 0x3F, 0x06, 0x1E, 0x00000001, PPC_NONE, PPC2_VSX207),
>  GEN_HANDLER_E(fmrgow, 0x3F, 0x06, 0x1A, 0x00000001, PPC_NONE, PPC2_VSX207),
>  GEN_HANDLER(mcrfs, 0x3F, 0x00, 0x02, 0x0063F801, PPC_FLOAT),
> -GEN_HANDLER(mffs, 0x3F, 0x07, 0x12, 0x001FF800, PPC_FLOAT),
> +GEN_HANDLER_E_2(mffs, 0x3F, 0x07, 0x12, 0x00, 0x00000000, PPC_FLOAT, PPC_NONE),
> +GEN_HANDLER_E_2(mffsl, 0x3F, 0x07, 0x12, 0x18, 0x00000000, PPC_FLOAT,
> +    PPC2_ISA300),
>  GEN_HANDLER(mtfsb0, 0x3F, 0x06, 0x02, 0x001FF800, PPC_FLOAT),
>  GEN_HANDLER(mtfsb1, 0x3F, 0x06, 0x01, 0x001FF800, PPC_FLOAT),
>  GEN_HANDLER(mtfsf, 0x3F, 0x07, 0x16, 0x00000000, PPC_FLOAT),

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

      parent reply	other threads:[~2019-08-17 11:01 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-16 19:03 [Qemu-devel] [PATCH v4] ppc: Add support for 'mffsl' instruction Paul A. Clarke
2019-08-16 19:16 ` no-reply
2019-08-17  8:18 ` David Gibson [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190817081811.GE2259@umbus.fritz.box \
    --to=david@gibson.dropbear.id.au \
    --cc=pc@us.ibm.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongnu.org \
    --cc=richard.henderson@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.