devicetree.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Kevin Cernekee <cernekee-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: ralf-6z/3iImG2C8G8FEW9MqTrA@public.gmane.org
Cc: f.fainelli-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org,
	mbizon-MmRyKUhfbQ9GWvitb5QawA@public.gmane.org,
	jogo-p3rKhJxN3npAfugRpC6u6w@public.gmane.org,
	jfraser-dY08KVG/lbpWk0Htik3J/w@public.gmane.org,
	linux-mips-6z/3iImG2C8G8FEW9MqTrA@public.gmane.org,
	devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: [PATCH/RFC 10/17] MIPS: BMIPS: Add special cache handling in c-r4k.c
Date: Mon, 20 Oct 2014 21:28:00 -0700	[thread overview]
Message-ID: <1413865687-15255-11-git-send-email-cernekee@gmail.com> (raw)
In-Reply-To: <1413865687-15255-1-git-send-email-cernekee-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>

BMIPS435x and BMIPS438x have a single shared L1 D$ and load/store unit,
so it isn't necessary to raise IPIs to keep both CPUs coherent.

BMIPS5000 has VIPT L1 caches that handle aliases in hardware, and its I$
fills from D$.  But a special sequence with 2 SYNCs and 32 NOPs is needed
to ensure coherency.

Signed-off-by: Kevin Cernekee <cernekee-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
 arch/mips/mm/c-r4k.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index fbcd867..dd261df 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -917,6 +917,18 @@ static inline void alias_74k_erratum(struct cpuinfo_mips *c)
 	}
 }
 
+static void b5k_instruction_hazard(void)
+{
+	__sync();
+	__sync();
+	__asm__ __volatile__(
+	"       nop; nop; nop; nop; nop; nop; nop; nop\n"
+	"       nop; nop; nop; nop; nop; nop; nop; nop\n"
+	"       nop; nop; nop; nop; nop; nop; nop; nop\n"
+	"       nop; nop; nop; nop; nop; nop; nop; nop\n"
+	: : : "memory");
+}
+
 static char *way_string[] = { NULL, "direct mapped", "2-way",
 	"3-way", "4-way", "5-way", "6-way", "7-way", "8-way"
 };
@@ -1683,6 +1695,37 @@ void r4k_cache_init(void)
 
 	coherency_setup();
 	board_cache_error_setup = r4k_cache_error_setup;
+
+	/*
+	 * Per-CPU overrides
+	 */
+	switch (current_cpu_type()) {
+	case CPU_BMIPS4350:
+	case CPU_BMIPS4380:
+		/* No IPI is needed because all CPUs share the same D$ */
+		flush_data_cache_page = r4k_blast_dcache_page;
+		break;
+	case CPU_BMIPS5000:
+		/* We lose our superpowers if L2 is disabled */
+		if (c->scache.flags & MIPS_CACHE_NOT_PRESENT)
+			break;
+
+		/* I$ fills from D$ just by emptying the write buffers */
+		flush_cache_page = (void *)b5k_instruction_hazard;
+		flush_cache_range = (void *)b5k_instruction_hazard;
+		flush_cache_sigtramp = (void *)b5k_instruction_hazard;
+		local_flush_data_cache_page = (void *)b5k_instruction_hazard;
+		flush_data_cache_page = (void *)b5k_instruction_hazard;
+		flush_icache_range = (void *)b5k_instruction_hazard;
+		local_flush_icache_range = (void *)b5k_instruction_hazard;
+
+		/* Cache aliases are handled in hardware; allow HIGHMEM */
+		current_cpu_data.dcache.flags &= ~MIPS_CACHE_ALIASES;
+
+		/* Optimization: an L2 flush implicitly flushes the L1 */
+		current_cpu_data.options |= MIPS_CPU_INCLUSIVE_CACHES;
+		break;
+	}
 }
 
 static int r4k_cache_pm_notifier(struct notifier_block *self, unsigned long cmd,
-- 
2.1.1

--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

  parent reply	other threads:[~2014-10-21  4:28 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-10-21  4:27 [PATCH/RFC 00/17] MIPS: BMIPS updates and BCM3384 platform support Kevin Cernekee
     [not found] ` <1413865687-15255-1-git-send-email-cernekee-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2014-10-21  4:27   ` [PATCH/RFC 01/17] MIPS: BMIPS: Fix ".previous without corresponding .section" warnings Kevin Cernekee
2014-10-21  4:27   ` [PATCH/RFC 02/17] MIPS: BMIPS: Align secondary boot sequence with latest firmware releases Kevin Cernekee
2014-10-21  4:27   ` [PATCH/RFC 03/17] MIPS: BMIPS: Introduce helper function to change the reset vector Kevin Cernekee
2014-10-21  4:27   ` [PATCH/RFC 04/17] MIPS: BMIPS: Allow BMIPS3300 to utilize SMP ebase relocation code Kevin Cernekee
2014-10-21  4:27   ` [PATCH/RFC 05/17] MIPS: BMIPS: Mask off timer IRQs when hot-unplugging a CPU Kevin Cernekee
2014-10-21  4:27   ` [PATCH/RFC 06/17] MIPS: BMIPS: Explicitly configure reset vectors prior to secondary boot Kevin Cernekee
2014-10-21  4:27   ` [PATCH/RFC 07/17] MIPS: Allow MIPS_CPU_SCACHE to be used with different line sizes Kevin Cernekee
2014-10-21  4:27   ` [PATCH/RFC 08/17] MIPS: BMIPS: Select the appropriate L1_CACHE_SHIFT for 438x and 5000 CPUs Kevin Cernekee
2014-10-21  4:27   ` [PATCH/RFC 09/17] MIPS: BMIPS: Let each platform customize the CPU1 IRQ mask Kevin Cernekee
2014-10-21  4:28   ` Kevin Cernekee [this message]
2014-10-21  4:28   ` [PATCH/RFC 11/17] MIPS: BMIPS: Add PRId for BMIPS5200 (Whirlwind) Kevin Cernekee
2014-10-21  4:28   ` [PATCH/RFC 12/17] MIPS: Create a helper function for DT setup Kevin Cernekee
2014-10-21  4:28   ` [PATCH/RFC 13/17] Documentation: DT: Add entries for BCM3384 and its peripherals Kevin Cernekee
2014-10-21  4:28   ` [PATCH/RFC 14/17] Documentation: DT: Add "mti" vendor prefix Kevin Cernekee
2014-10-21  4:28   ` [PATCH/RFC 15/17] MIPS: bcm3384: Initial commit of bcm3384 platform support Kevin Cernekee
2014-10-21  4:28   ` [PATCH/RFC 16/17] MAINTAINERS: Add entry for BCM33xx cable chips Kevin Cernekee
2014-10-21  4:28   ` [PATCH/RFC 17/17] MAINTAINERS: Add entry for bcm63xx/bcm33xx UDC gadget driver Kevin Cernekee
2014-10-21 19:31   ` [PATCH/RFC 00/17] MIPS: BMIPS updates and BCM3384 platform support Florian Fainelli

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=1413865687-15255-11-git-send-email-cernekee@gmail.com \
    --to=cernekee-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
    --cc=devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=f.fainelli-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
    --cc=jfraser-dY08KVG/lbpWk0Htik3J/w@public.gmane.org \
    --cc=jogo-p3rKhJxN3npAfugRpC6u6w@public.gmane.org \
    --cc=linux-mips-6z/3iImG2C8G8FEW9MqTrA@public.gmane.org \
    --cc=mbizon-MmRyKUhfbQ9GWvitb5QawA@public.gmane.org \
    --cc=ralf-6z/3iImG2C8G8FEW9MqTrA@public.gmane.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).