linux-riscv.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Palmer Dabbelt <palmer@sifive.com>,
	Paul Walmsley <paul.walmsley@sifive.com>
Cc: Anup Patel <anup@brainfault.org>,
	Damien Le Moal <damien.lemoal@wdc.com>,
	linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: [PATCH 05/12] riscv: implement remote sfence.i using IPIs
Date: Mon, 28 Oct 2019 13:10:36 +0100	[thread overview]
Message-ID: <20191028121043.22934-6-hch@lst.de> (raw)
In-Reply-To: <20191028121043.22934-1-hch@lst.de>

The RISC-V ISA only supports flushing the instruction cache for the
local CPU core.  Currently we always offload the remote TLB flushing to
the SBI, which then issues an IPI under the hoods.  But with M-mode
we do not have an SBI so we have to do it ourselves.   IPI to the
other nodes using the existing kernel helpers instead if we have
native clint support and thus can IPI directly from the kernel.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/include/asm/sbi.h |  3 +++
 arch/riscv/mm/cacheflush.c   | 24 ++++++++++++++++++------
 2 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index b167af3e7470..0cb74eccc73f 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -94,5 +94,8 @@ static inline void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
 {
 	SBI_CALL_4(SBI_REMOTE_SFENCE_VMA_ASID, hart_mask, start, size, asid);
 }
+#else /* CONFIG_RISCV_SBI */
+/* stub to for code is only reachable under IS_ENABLED(CONFIG_RISCV_SBI): */
+void sbi_remote_fence_i(const unsigned long *hart_mask);
 #endif /* CONFIG_RISCV_SBI */
 #endif /* _ASM_RISCV_SBI_H */
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index 3f15938dec89..794c9ab256eb 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -10,9 +10,17 @@
 
 #include <asm/sbi.h>
 
+static void ipi_remote_fence_i(void *info)
+{
+	return local_flush_icache_all();
+}
+
 void flush_icache_all(void)
 {
-	sbi_remote_fence_i(NULL);
+	if (IS_ENABLED(CONFIG_RISCV_SBI))
+		sbi_remote_fence_i(NULL);
+	else
+		on_each_cpu(ipi_remote_fence_i, NULL, 1);
 }
 
 /*
@@ -28,7 +36,7 @@ void flush_icache_all(void)
 void flush_icache_mm(struct mm_struct *mm, bool local)
 {
 	unsigned int cpu;
-	cpumask_t others, hmask, *mask;
+	cpumask_t others, *mask;
 
 	preempt_disable();
 
@@ -46,10 +54,7 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 	 */
 	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
 	local |= cpumask_empty(&others);
-	if (mm != current->active_mm || !local) {
-		riscv_cpuid_to_hartid_mask(&others, &hmask);
-		sbi_remote_fence_i(hmask.bits);
-	} else {
+	if (mm == current->active_mm && local) {
 		/*
 		 * It's assumed that at least one strongly ordered operation is
 		 * performed on this hart between setting a hart's cpumask bit
@@ -59,6 +64,13 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 		 * with flush_icache_deferred().
 		 */
 		smp_mb();
+	} else if (IS_ENABLED(CONFIG_RISCV_SBI)) {
+		cpumask_t hartid_mask;
+
+		riscv_cpuid_to_hartid_mask(&others, &hartid_mask);
+		sbi_remote_fence_i(cpumask_bits(&hartid_mask));
+	} else {
+		on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);
 	}
 
 	preempt_enable();
-- 
2.20.1


_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

  parent reply	other threads:[~2019-10-28 12:11 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-28 12:10 RISC-V nommu support v6 Christoph Hellwig
2019-10-28 12:10 ` [PATCH 01/12] riscv: abstract out CSR names for supervisor vs machine mode Christoph Hellwig
2019-11-05 17:56   ` Paul Walmsley
2019-11-05 17:57   ` Paul Walmsley
2019-11-05 18:02     ` Marc Zyngier
2019-11-12 10:38   ` Thomas Gleixner
2019-11-14  7:30   ` Paul Walmsley
2019-10-28 12:10 ` [PATCH 02/12] riscv: don't allow selecting SBI based drivers for M-mode Christoph Hellwig
2019-11-14  7:31   ` Paul Walmsley
2019-10-28 12:10 ` [PATCH 03/12] riscv: poison SBI calls " Christoph Hellwig
2019-10-31 23:55   ` Paul Walmsley
2019-10-28 12:10 ` [PATCH 04/12] riscv: cleanup the default power off implementation Christoph Hellwig
2019-10-31 20:49   ` Paul Walmsley
2019-10-31 23:56   ` Paul Walmsley
2019-10-28 12:10 ` Christoph Hellwig [this message]
2019-10-31 23:57   ` [PATCH 05/12] riscv: implement remote sfence.i using IPIs Paul Walmsley
2019-10-28 12:10 ` [PATCH 06/12] riscv: add support for MMIO access to the timer registers Christoph Hellwig
2019-11-05 18:01   ` Paul Walmsley
2019-11-12 10:39   ` Thomas Gleixner
2019-11-17 23:06   ` Paul Walmsley
2019-10-28 12:10 ` [PATCH 07/12] riscv: provide native clint access for M-mode Christoph Hellwig
2019-10-28 12:10 ` [PATCH 08/12] riscv: read the hart ID from mhartid on boot Christoph Hellwig
2019-10-28 12:10 ` [PATCH 09/12] riscv: clear the instruction cache and all registers when booting Christoph Hellwig
2019-11-14  7:45   ` Paul Walmsley
2019-10-28 12:10 ` [PATCH 10/12] riscv: add nommu support Christoph Hellwig
2019-11-17 23:13   ` Paul Walmsley
2019-12-16 22:03     ` David Abdurachmanov
2019-12-17  3:18       ` Paul Walmsley
2019-10-28 12:10 ` [PATCH 11/12] riscv: provide a flat image loader Christoph Hellwig
2019-11-17 23:14   ` Paul Walmsley
2019-10-28 12:10 ` [PATCH 12/12] riscv: disable the EFI PECOFF header for M-mode Christoph Hellwig
2019-10-30 20:21 ` RISC-V nommu support v6 Paul Walmsley
2019-10-31 15:52   ` Christoph Hellwig
2019-10-31 20:13     ` Paul Walmsley
2019-11-23  2:19     ` Paul Walmsley
2019-12-11  8:42       ` Greentime Hu
2020-02-12 12:19       ` Greentime Hu
2019-11-11  9:47   ` Christoph Hellwig
2019-11-11 17:02     ` Paul Walmsley
2019-11-13 13:18       ` Christoph Hellwig

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=20191028121043.22934-6-hch@lst.de \
    --to=hch@lst.de \
    --cc=anup@brainfault.org \
    --cc=damien.lemoal@wdc.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=palmer@sifive.com \
    --cc=paul.walmsley@sifive.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 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).