All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
To: mpe@ellerman.id.au
Cc: ravi.bangoria@linux.ibm.com, jniethe5@gmail.com,
	bala24@linux.ibm.com, paulus@samba.org, sandipan@linux.ibm.com,
	naveen.n.rao@linux.vnet.ibm.com, linuxppc-dev@lists.ozlabs.org
Subject: [PATCH v5 3/5] powerpc/sstep: Support VSX vector paired storage access instructions
Date: Sun, 11 Oct 2020 10:39:06 +0530	[thread overview]
Message-ID: <20201011050908.72173-4-ravi.bangoria@linux.ibm.com> (raw)
In-Reply-To: <20201011050908.72173-1-ravi.bangoria@linux.ibm.com>

From: Balamuruhan S <bala24@linux.ibm.com>

VSX Vector Paired instructions loads/stores an octword (32 bytes)
from/to storage into two sequential VSRs. Add emulation support
for these new instructions:
  * Load VSX Vector Paired (lxvp)
  * Load VSX Vector Paired Indexed (lxvpx)
  * Prefixed Load VSX Vector Paired (plxvp)
  * Store VSX Vector Paired (stxvp)
  * Store VSX Vector Paired Indexed (stxvpx)
  * Prefixed Store VSX Vector Paired (pstxvp)

Suggested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Balamuruhan S <bala24@linux.ibm.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
[kernel test robot reported a build failure]
Reported-by: kernel test robot <lkp@intel.com>
---
 arch/powerpc/lib/sstep.c | 150 +++++++++++++++++++++++++++++++++------
 1 file changed, 129 insertions(+), 21 deletions(-)

diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index faf0bbf3efb7..96ca813a65e7 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -32,6 +32,10 @@ extern char system_call_vectored_emulate[];
 #define XER_OV32	0x00080000U
 #define XER_CA32	0x00040000U
 
+#ifdef CONFIG_VSX
+#define VSX_REGISTER_XTP(rd)   ((((rd) & 1) << 5) | ((rd) & 0xfe))
+#endif
+
 #ifdef CONFIG_PPC_FPU
 /*
  * Functions in ldstfp.S
@@ -279,6 +283,19 @@ static nokprobe_inline void do_byte_reverse(void *ptr, int nb)
 		up[1] = tmp;
 		break;
 	}
+	case 32: {
+		unsigned long *up = (unsigned long *)ptr;
+		unsigned long tmp;
+
+		tmp = byterev_8(up[0]);
+		up[0] = byterev_8(up[3]);
+		up[3] = tmp;
+		tmp = byterev_8(up[2]);
+		up[2] = byterev_8(up[1]);
+		up[1] = tmp;
+		break;
+	}
+
 #endif
 	default:
 		WARN_ON_ONCE(1);
@@ -709,6 +726,8 @@ void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
 	reg->d[0] = reg->d[1] = 0;
 
 	switch (op->element_size) {
+	case 32:
+		/* [p]lxvp[x] */
 	case 16:
 		/* whole vector; lxv[x] or lxvl[l] */
 		if (size == 0)
@@ -717,7 +736,7 @@ void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
 		if (IS_LE && (op->vsx_flags & VSX_LDLEFT))
 			rev = !rev;
 		if (rev)
-			do_byte_reverse(reg, 16);
+			do_byte_reverse(reg, size);
 		break;
 	case 8:
 		/* scalar loads, lxvd2x, lxvdsx */
@@ -793,6 +812,20 @@ void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
 	size = GETSIZE(op->type);
 
 	switch (op->element_size) {
+	case 32:
+		/* [p]stxvp[x] */
+		if (size == 0)
+			break;
+		if (rev) {
+			/* reverse 32 bytes */
+			buf.d[0] = byterev_8(reg->d[3]);
+			buf.d[1] = byterev_8(reg->d[2]);
+			buf.d[2] = byterev_8(reg->d[1]);
+			buf.d[3] = byterev_8(reg->d[0]);
+			reg = &buf;
+		}
+		memcpy(mem, reg, size);
+		break;
 	case 16:
 		/* stxv, stxvx, stxvl, stxvll */
 		if (size == 0)
@@ -861,28 +894,43 @@ static nokprobe_inline int do_vsx_load(struct instruction_op *op,
 				       bool cross_endian)
 {
 	int reg = op->reg;
-	u8 mem[16];
-	union vsx_reg buf;
+	int i, j, nr_vsx_regs;
+	u8 mem[32];
+	union vsx_reg buf[2];
 	int size = GETSIZE(op->type);
 
 	if (!address_ok(regs, ea, size) || copy_mem_in(mem, ea, size, regs))
 		return -EFAULT;
 
-	emulate_vsx_load(op, &buf, mem, cross_endian);
+	nr_vsx_regs = size / sizeof(__vector128);
+	emulate_vsx_load(op, buf, mem, cross_endian);
 	preempt_disable();
 	if (reg < 32) {
 		/* FP regs + extensions */
 		if (regs->msr & MSR_FP) {
-			load_vsrn(reg, &buf);
+			for (i = 0; i < nr_vsx_regs; i++) {
+				j = IS_LE ? nr_vsx_regs - i - 1 : i;
+				load_vsrn(reg + i, &buf[j].v);
+			}
 		} else {
-			current->thread.fp_state.fpr[reg][0] = buf.d[0];
-			current->thread.fp_state.fpr[reg][1] = buf.d[1];
+			for (i = 0; i < nr_vsx_regs; i++) {
+				j = IS_LE ? nr_vsx_regs - i - 1 : i;
+				current->thread.fp_state.fpr[reg + i][0] = buf[j].d[0];
+				current->thread.fp_state.fpr[reg + i][1] = buf[j].d[1];
+			}
 		}
 	} else {
-		if (regs->msr & MSR_VEC)
-			load_vsrn(reg, &buf);
-		else
-			current->thread.vr_state.vr[reg - 32] = buf.v;
+		if (regs->msr & MSR_VEC) {
+			for (i = 0; i < nr_vsx_regs; i++) {
+				j = IS_LE ? nr_vsx_regs - i - 1 : i;
+				load_vsrn(reg + i, &buf[j].v);
+			}
+		} else {
+			for (i = 0; i < nr_vsx_regs; i++) {
+				j = IS_LE ? nr_vsx_regs - i - 1 : i;
+				current->thread.vr_state.vr[reg - 32 + i] = buf[j].v;
+			}
+		}
 	}
 	preempt_enable();
 	return 0;
@@ -893,30 +941,45 @@ static nokprobe_inline int do_vsx_store(struct instruction_op *op,
 					bool cross_endian)
 {
 	int reg = op->reg;
-	u8 mem[16];
-	union vsx_reg buf;
+	int i, j, nr_vsx_regs;
+	u8 mem[32];
+	union vsx_reg buf[2];
 	int size = GETSIZE(op->type);
 
 	if (!address_ok(regs, ea, size))
 		return -EFAULT;
 
+	nr_vsx_regs = size / sizeof(__vector128);
 	preempt_disable();
 	if (reg < 32) {
 		/* FP regs + extensions */
 		if (regs->msr & MSR_FP) {
-			store_vsrn(reg, &buf);
+			for (i = 0; i < nr_vsx_regs; i++) {
+				j = IS_LE ? nr_vsx_regs - i - 1 : i;
+				store_vsrn(reg + i, &buf[j].v);
+			}
 		} else {
-			buf.d[0] = current->thread.fp_state.fpr[reg][0];
-			buf.d[1] = current->thread.fp_state.fpr[reg][1];
+			for (i = 0; i < nr_vsx_regs; i++) {
+				j = IS_LE ? nr_vsx_regs - i - 1 : i;
+				buf[j].d[0] = current->thread.fp_state.fpr[reg + i][0];
+				buf[j].d[1] = current->thread.fp_state.fpr[reg + i][1];
+			}
 		}
 	} else {
-		if (regs->msr & MSR_VEC)
-			store_vsrn(reg, &buf);
-		else
-			buf.v = current->thread.vr_state.vr[reg - 32];
+		if (regs->msr & MSR_VEC) {
+			for (i = 0; i < nr_vsx_regs; i++) {
+				j = IS_LE ? nr_vsx_regs - i - 1 : i;
+				store_vsrn(reg + i, &buf[j].v);
+			}
+		} else {
+			for (i = 0; i < nr_vsx_regs; i++) {
+				j = IS_LE ? nr_vsx_regs - i - 1 : i;
+				buf[j].v = current->thread.vr_state.vr[reg - 32 + i];
+			}
+		}
 	}
 	preempt_enable();
-	emulate_vsx_store(op, &buf, mem, cross_endian);
+	emulate_vsx_store(op, buf, mem, cross_endian);
 	return  copy_mem_out(mem, ea, size, regs);
 }
 #endif /* CONFIG_VSX */
@@ -2403,6 +2466,14 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 			op->vsx_flags = VSX_SPLAT;
 			break;
 
+		case 333:       /* lxvpx */
+			if (!cpu_has_feature(CPU_FTR_ARCH_31))
+				return -1;
+			op->reg = VSX_REGISTER_XTP(rd);
+			op->type = MKOP(LOAD_VSX, 0, 32);
+			op->element_size = 32;
+			break;
+
 		case 364:	/* lxvwsx */
 			op->reg = rd | ((word & 1) << 5);
 			op->type = MKOP(LOAD_VSX, 0, 4);
@@ -2431,6 +2502,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 				VSX_CHECK_VEC;
 			break;
 		}
+		case 461:       /* stxvpx */
+			if (!cpu_has_feature(CPU_FTR_ARCH_31))
+				return -1;
+			op->reg = VSX_REGISTER_XTP(rd);
+			op->type = MKOP(STORE_VSX, 0, 32);
+			op->element_size = 32;
+			break;
 		case 524:	/* lxsspx */
 			op->reg = rd | ((word & 1) << 5);
 			op->type = MKOP(LOAD_VSX, 0, 4);
@@ -2672,6 +2750,22 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 #endif
 
 #ifdef CONFIG_VSX
+	case 6:
+		if (!cpu_has_feature(CPU_FTR_ARCH_31))
+			return -1;
+		op->ea = dqform_ea(word, regs);
+		op->reg = VSX_REGISTER_XTP(rd);
+		op->element_size = 32;
+		switch (word & 0xf) {
+		case 0:         /* lxvp */
+			op->type = MKOP(LOAD_VSX, 0, 32);
+			break;
+		case 1:         /* stxvp */
+			op->type = MKOP(STORE_VSX, 0, 32);
+			break;
+		}
+		break;
+
 	case 61:	/* stfdp, lxv, stxsd, stxssp, stxv */
 		switch (word & 7) {
 		case 0:		/* stfdp with LSB of DS field = 0 */
@@ -2805,12 +2899,26 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 			case 57:	/* pld */
 				op->type = MKOP(LOAD, PREFIXED, 8);
 				break;
+#ifdef CONFIG_VSX
+			case 58:        /* plxvp */
+				op->reg = VSX_REGISTER_XTP(rd);
+				op->type = MKOP(LOAD_VSX, PREFIXED, 32);
+				op->element_size = 32;
+				break;
+#endif /* CONFIG_VSX */
 			case 60:        /* pstq */
 				op->type = MKOP(STORE, PREFIXED, 16);
 				break;
 			case 61:	/* pstd */
 				op->type = MKOP(STORE, PREFIXED, 8);
 				break;
+#ifdef CONFIG_VSX
+			case 62:        /* pstxvp */
+				op->reg = VSX_REGISTER_XTP(rd);
+				op->type = MKOP(STORE_VSX, PREFIXED, 32);
+				op->element_size = 32;
+				break;
+#endif /* CONFIG_VSX */
 			}
 			break;
 		case 1: /* Type 01 Eight-Byte Register-to-Register */
-- 
2.26.2


  parent reply	other threads:[~2020-10-11  5:16 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-11  5:09 [PATCH v5 0/5] powerpc/sstep: VSX 32-byte vector paired load/store instructions Ravi Bangoria
2020-10-11  5:09 ` [PATCH v5 1/5] powerpc/sstep: Emulate prefixed instructions only when CPU_FTR_ARCH_31 is set Ravi Bangoria
2020-10-11 15:06   ` Sandipan Das
2020-10-12  1:51   ` Daniel Axtens
2020-10-12 11:07     ` Ravi Bangoria
2020-10-12 12:55       ` Daniel Axtens
2020-10-12 13:44   ` Daniel Axtens
2020-10-14  7:34     ` Ravi Bangoria
2020-10-11  5:09 ` [PATCH v5 2/5] powerpc/sstep: Cover new VSX instructions under CONFIG_VSX Ravi Bangoria
2020-10-11  5:09 ` Ravi Bangoria [this message]
2020-10-11  5:09 ` [PATCH v5 4/5] powerpc/ppc-opcode: Add encoding macros for VSX vector paired instructions Ravi Bangoria
2020-10-11  5:09 ` [PATCH v5 5/5] powerpc/sstep: Add testcases for VSX vector paired load/store instructions Ravi Bangoria
2020-12-15 10:49 ` [PATCH v5 0/5] powerpc/sstep: VSX 32-byte " Michael Ellerman

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=20201011050908.72173-4-ravi.bangoria@linux.ibm.com \
    --to=ravi.bangoria@linux.ibm.com \
    --cc=bala24@linux.ibm.com \
    --cc=jniethe5@gmail.com \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=naveen.n.rao@linux.vnet.ibm.com \
    --cc=paulus@samba.org \
    --cc=sandipan@linux.ibm.com \
    /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.