All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
To: linux-crypto@vger.kernel.org
Cc: herbert@gondor.apana.org.au,
	linux-arm-kernel@lists.infradead.org,
	Ard Biesheuvel <ard.biesheuvel@linaro.org>,
	Dave Martin <Dave.Martin@arm.com>,
	Russell King - ARM Linux <linux@armlinux.org.uk>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Mark Rutland <mark.rutland@arm.com>,
	linux-rt-users@vger.kernel.org,
	Peter Zijlstra <peterz@infradead.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will.deacon@arm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Thomas Gleixner <tglx@linutronix.de>
Subject: [PATCH v3 10/20] arm64: assembler: add utility macros to push/pop stack frames
Date: Wed,  6 Dec 2017 19:43:36 +0000	[thread overview]
Message-ID: <20171206194346.24393-11-ard.biesheuvel@linaro.org> (raw)
In-Reply-To: <20171206194346.24393-1-ard.biesheuvel@linaro.org>

We are going to add code to all the NEON crypto routines that will
turn them into non-leaf functions, so we need to manage the stack
frames. To make this less tedious and error prone, add some macros
that take the number of callee saved registers to preserve and the
extra size to allocate in the stack frame (for locals) and emit
the ldp/stp sequences.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/include/asm/assembler.h | 60 ++++++++++++++++++++
 1 file changed, 60 insertions(+)

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index aef72d886677..5f61487e9f93 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -499,6 +499,66 @@ alternative_else_nop_endif
 #endif
 	.endm
 
+	/*
+	 * frame_push - Push @regcount callee saved registers to the stack,
+	 *              starting at x19, as well as x29/x30, and set x29 to
+	 *              the new value of sp. Add @extra bytes of stack space
+	 *              for locals.
+	 */
+	.macro		frame_push, regcount:req, extra
+	__frame		st, \regcount, \extra
+	.endm
+
+	/*
+	 * frame_pop  - Pop @regcount callee saved registers from the stack,
+	 *              starting at x19, as well as x29/x30. Also pop @extra
+	 *              bytes of stack space for locals.
+	 */
+	.macro		frame_pop, regcount:req, extra
+	__frame		ld, \regcount, \extra
+	.endm
+
+	.macro		__frame, op, regcount:req, extra=0
+	.ifc		\op, st
+	stp		x29, x30, [sp, #-((\regcount + 3) / 2) * 16 - \extra]!
+	mov		x29, sp
+	.endif
+	.if		\regcount < 0 || \regcount > 10
+	.error		"regcount should be in the range [0 ... 10]"
+	.endif
+	.if		(\extra % 16) != 0
+	.error		"extra should be a multiple of 16 bytes"
+	.endif
+	.if		\regcount > 1
+	\op\()p		x19, x20, [sp, #16]
+	.if		\regcount > 3
+	\op\()p		x21, x22, [sp, #32]
+	.if		\regcount > 5
+	\op\()p		x23, x24, [sp, #48]
+	.if		\regcount > 7
+	\op\()p		x25, x26, [sp, #64]
+	.if		\regcount > 9
+	\op\()p		x27, x28, [sp, #80]
+	.elseif		\regcount == 9
+	\op\()r		x27, [sp, #80]
+	.endif
+	.elseif		\regcount == 7
+	\op\()r		x25, [sp, #64]
+	.endif
+	.elseif		\regcount == 5
+	\op\()r		x23, [sp, #48]
+	.endif
+	.elseif		\regcount == 3
+	\op\()r		x21, [sp, #32]
+	.endif
+	.elseif		\regcount == 1
+	\op\()r		x19, [sp, #16]
+	.endif
+	.ifc		\op, ld
+	ldp		x29, x30, [sp], #((\regcount + 3) / 2) * 16 + \extra
+	.endif
+	.endm
+
 /*
  * Errata workaround post TTBR0_EL1 update.
  */
-- 
2.11.0


WARNING: multiple messages have this Message-ID (diff)
From: ard.biesheuvel@linaro.org (Ard Biesheuvel)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v3 10/20] arm64: assembler: add utility macros to push/pop stack frames
Date: Wed,  6 Dec 2017 19:43:36 +0000	[thread overview]
Message-ID: <20171206194346.24393-11-ard.biesheuvel@linaro.org> (raw)
In-Reply-To: <20171206194346.24393-1-ard.biesheuvel@linaro.org>

We are going to add code to all the NEON crypto routines that will
turn them into non-leaf functions, so we need to manage the stack
frames. To make this less tedious and error prone, add some macros
that take the number of callee saved registers to preserve and the
extra size to allocate in the stack frame (for locals) and emit
the ldp/stp sequences.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/include/asm/assembler.h | 60 ++++++++++++++++++++
 1 file changed, 60 insertions(+)

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index aef72d886677..5f61487e9f93 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -499,6 +499,66 @@ alternative_else_nop_endif
 #endif
 	.endm
 
+	/*
+	 * frame_push - Push @regcount callee saved registers to the stack,
+	 *              starting at x19, as well as x29/x30, and set x29 to
+	 *              the new value of sp. Add @extra bytes of stack space
+	 *              for locals.
+	 */
+	.macro		frame_push, regcount:req, extra
+	__frame		st, \regcount, \extra
+	.endm
+
+	/*
+	 * frame_pop  - Pop @regcount callee saved registers from the stack,
+	 *              starting at x19, as well as x29/x30. Also pop @extra
+	 *              bytes of stack space for locals.
+	 */
+	.macro		frame_pop, regcount:req, extra
+	__frame		ld, \regcount, \extra
+	.endm
+
+	.macro		__frame, op, regcount:req, extra=0
+	.ifc		\op, st
+	stp		x29, x30, [sp, #-((\regcount + 3) / 2) * 16 - \extra]!
+	mov		x29, sp
+	.endif
+	.if		\regcount < 0 || \regcount > 10
+	.error		"regcount should be in the range [0 ... 10]"
+	.endif
+	.if		(\extra % 16) != 0
+	.error		"extra should be a multiple of 16 bytes"
+	.endif
+	.if		\regcount > 1
+	\op\()p		x19, x20, [sp, #16]
+	.if		\regcount > 3
+	\op\()p		x21, x22, [sp, #32]
+	.if		\regcount > 5
+	\op\()p		x23, x24, [sp, #48]
+	.if		\regcount > 7
+	\op\()p		x25, x26, [sp, #64]
+	.if		\regcount > 9
+	\op\()p		x27, x28, [sp, #80]
+	.elseif		\regcount == 9
+	\op\()r		x27, [sp, #80]
+	.endif
+	.elseif		\regcount == 7
+	\op\()r		x25, [sp, #64]
+	.endif
+	.elseif		\regcount == 5
+	\op\()r		x23, [sp, #48]
+	.endif
+	.elseif		\regcount == 3
+	\op\()r		x21, [sp, #32]
+	.endif
+	.elseif		\regcount == 1
+	\op\()r		x19, [sp, #16]
+	.endif
+	.ifc		\op, ld
+	ldp		x29, x30, [sp], #((\regcount + 3) / 2) * 16 + \extra
+	.endif
+	.endm
+
 /*
  * Errata workaround post TTBR0_EL1 update.
  */
-- 
2.11.0

  parent reply	other threads:[~2017-12-06 19:43 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-12-06 19:43 [PATCH v3 00/20] crypto: arm64 - play nice with CONFIG_PREEMPT Ard Biesheuvel
2017-12-06 19:43 ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 01/20] crypto: testmgr - add a new test case for CRC-T10DIF Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 02/20] crypto: arm64/aes-ce-ccm - move kernel mode neon en/disable into loop Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 03/20] crypto: arm64/aes-blk " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 04/20] crypto: arm64/aes-bs " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 05/20] crypto: arm64/chacha20 " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 06/20] crypto: arm64/aes-blk - remove configurable interleave Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 07/20] crypto: arm64/aes-blk - add 4 way interleave to CBC encrypt path Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 08/20] crypto: arm64/aes-blk - add 4 way interleave to CBC-MAC " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 09/20] crypto: arm64/sha256-neon - play nice with CONFIG_PREEMPT kernels Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` Ard Biesheuvel [this message]
2017-12-06 19:43   ` [PATCH v3 10/20] arm64: assembler: add utility macros to push/pop stack frames Ard Biesheuvel
2017-12-07 14:11   ` Dave Martin
2017-12-07 14:11     ` Dave Martin
2017-12-07 14:21     ` Ard Biesheuvel
2017-12-07 14:21       ` Ard Biesheuvel
2017-12-07 14:53       ` Dave Martin
2017-12-07 14:53         ` Dave Martin
2017-12-07 14:58         ` Ard Biesheuvel
2017-12-07 14:58           ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 11/20] arm64: assembler: add macros to conditionally yield the NEON under PREEMPT Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-07 14:39   ` Dave Martin
2017-12-07 14:39     ` Dave Martin
2017-12-07 14:50     ` Ard Biesheuvel
2017-12-07 14:50       ` Ard Biesheuvel
2017-12-07 15:47       ` Ard Biesheuvel
2017-12-07 15:47         ` Ard Biesheuvel
2017-12-07 15:51         ` Ard Biesheuvel
2017-12-07 15:51           ` Ard Biesheuvel
2017-12-07 16:15         ` Dave Martin
2017-12-07 16:15           ` Dave Martin
2017-12-07 16:11       ` Dave Martin
2017-12-07 16:11         ` Dave Martin
2017-12-06 19:43 ` [PATCH v3 12/20] crypto: arm64/sha1-ce - yield NEON after every block of input Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 13/20] crypto: arm64/sha2-ce " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 14/20] crypto: arm64/aes-ccm " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 15/20] crypto: arm64/aes-blk " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 16/20] crypto: arm64/aes-bs " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 17/20] crypto: arm64/aes-ghash " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 18/20] crypto: arm64/crc32-ce " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 19/20] crypto: arm64/crct10dif-ce " Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel
2017-12-06 19:43 ` [PATCH v3 20/20] DO NOT MERGE Ard Biesheuvel
2017-12-06 19:43   ` Ard Biesheuvel

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=20171206194346.24393-11-ard.biesheuvel@linaro.org \
    --to=ard.biesheuvel@linaro.org \
    --cc=Dave.Martin@arm.com \
    --cc=bigeasy@linutronix.de \
    --cc=catalin.marinas@arm.com \
    --cc=herbert@gondor.apana.org.au \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=mark.rutland@arm.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=will.deacon@arm.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.