Linux-ARM-Kernel Archive on lore.kernel.org
 help / color / Atom feed
From: James Morse <james.morse@arm.com>
To: linux-acpi@vger.kernel.org
Cc: Rafael Wysocki <rjw@rjwysocki.net>,
	Tony Luck <tony.luck@intel.com>, Xie XiuQi <xiexiuqi@huawei.com>,
	Marc Zyngier <marc.zyngier@arm.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will.deacon@arm.com>,
	Christoffer Dall <christoffer.dall@arm.com>,
	Dongjiu Geng <gengdongjiu@huawei.com>,
	linux-mm@kvack.org, Borislav Petkov <bp@alien8.de>,
	james.morse@arm.com, Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
	kvmarm@lists.cs.columbia.edu,
	linux-arm-kernel@lists.infradead.org, Len Brown <lenb@kernel.org>
Subject: [PATCH v8 06/26] ACPI / APEI: Don't store CPER records physical address in struct ghes
Date: Tue, 29 Jan 2019 18:48:42 +0000
Message-ID: <20190129184902.102850-7-james.morse@arm.com> (raw)
In-Reply-To: <20190129184902.102850-1-james.morse@arm.com>

When CPER records are found the address of the records is stashed
in the struct ghes. Once the records have been processed, this
address is overwritten with zero so that it won't be processed
again without being re-populated by firmware.

This goes wrong if a struct ghes can be processed concurrently,
as can happen at probe time when an NMI occurs. If the NMI arrives
on another CPU, the probing CPU may call ghes_clear_estatus() on the
records before the handler had finished with them.
Even on the same CPU, once the interrupted handler is resumed, it
will call ghes_clear_estatus() on the NMIs records, this memory may
have already been re-used by firmware.

Avoid this stashing by letting the caller hold the address. A
later patch will do away with the use of ghes->flags in the
read/clear code too.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
---
Changes since v7:
 * Added buf_paddr to ghes_panic, as it wants to print the estatus

Changes since v6:
 * Moved earlier in the series
 * Added buf_adder = 0 on all the error paths, and test for it in
   ghes_estatus_clear() for extra sanity.
---
 drivers/acpi/apei/ghes.c | 46 +++++++++++++++++++++++-----------------
 include/acpi/ghes.h      |  1 -
 2 files changed, 27 insertions(+), 20 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 33144ab0661a..a34f79153b1a 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -305,29 +305,30 @@ static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len,
 	}
 }
 
-static int ghes_read_estatus(struct ghes *ghes)
+static int ghes_read_estatus(struct ghes *ghes, u64 *buf_paddr)
 {
 	struct acpi_hest_generic *g = ghes->generic;
-	u64 buf_paddr;
 	u32 len;
 	int rc;
 
-	rc = apei_read(&buf_paddr, &g->error_status_address);
+	rc = apei_read(buf_paddr, &g->error_status_address);
 	if (rc) {
+		*buf_paddr = 0;
 		pr_warn_ratelimited(FW_WARN GHES_PFX
 "Failed to read error status block address for hardware error source: %d.\n",
 				   g->header.source_id);
 		return -EIO;
 	}
-	if (!buf_paddr)
+	if (!*buf_paddr)
 		return -ENOENT;
 
-	ghes_copy_tofrom_phys(ghes->estatus, buf_paddr,
+	ghes_copy_tofrom_phys(ghes->estatus, *buf_paddr,
 			      sizeof(*ghes->estatus), 1);
-	if (!ghes->estatus->block_status)
+	if (!ghes->estatus->block_status) {
+		*buf_paddr = 0;
 		return -ENOENT;
+	}
 
-	ghes->buffer_paddr = buf_paddr;
 	ghes->flags |= GHES_TO_CLEAR;
 
 	rc = -EIO;
@@ -339,7 +340,7 @@ static int ghes_read_estatus(struct ghes *ghes)
 	if (cper_estatus_check_header(ghes->estatus))
 		goto err_read_block;
 	ghes_copy_tofrom_phys(ghes->estatus + 1,
-			      buf_paddr + sizeof(*ghes->estatus),
+			      *buf_paddr + sizeof(*ghes->estatus),
 			      len - sizeof(*ghes->estatus), 1);
 	if (cper_estatus_check(ghes->estatus))
 		goto err_read_block;
@@ -349,15 +350,20 @@ static int ghes_read_estatus(struct ghes *ghes)
 	if (rc)
 		pr_warn_ratelimited(FW_WARN GHES_PFX
 				    "Failed to read error status block!\n");
+
 	return rc;
 }
 
-static void ghes_clear_estatus(struct ghes *ghes)
+static void ghes_clear_estatus(struct ghes *ghes, u64 buf_paddr)
 {
 	ghes->estatus->block_status = 0;
 	if (!(ghes->flags & GHES_TO_CLEAR))
 		return;
-	ghes_copy_tofrom_phys(ghes->estatus, ghes->buffer_paddr,
+
+	if (!buf_paddr)
+		return;
+
+	ghes_copy_tofrom_phys(ghes->estatus, buf_paddr,
 			      sizeof(ghes->estatus->block_status), 0);
 	ghes->flags &= ~GHES_TO_CLEAR;
 }
@@ -666,11 +672,11 @@ static int ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
 	return apei_write(val, &gv2->read_ack_register);
 }
 
-static void __ghes_panic(struct ghes *ghes)
+static void __ghes_panic(struct ghes *ghes, u64 buf_paddr)
 {
 	__ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
 
-	ghes_clear_estatus(ghes);
+	ghes_clear_estatus(ghes, buf_paddr);
 
 	/* reboot to log the error! */
 	if (!panic_timeout)
@@ -680,14 +686,15 @@ static void __ghes_panic(struct ghes *ghes)
 
 static int ghes_proc(struct ghes *ghes)
 {
+	u64 buf_paddr;
 	int rc;
 
-	rc = ghes_read_estatus(ghes);
+	rc = ghes_read_estatus(ghes, &buf_paddr);
 	if (rc)
 		goto out;
 
 	if (ghes_severity(ghes->estatus->error_severity) >= GHES_SEV_PANIC) {
-		__ghes_panic(ghes);
+		__ghes_panic(ghes, buf_paddr);
 	}
 
 	if (!ghes_estatus_cached(ghes->estatus)) {
@@ -697,7 +704,7 @@ static int ghes_proc(struct ghes *ghes)
 	ghes_do_proc(ghes, ghes->estatus);
 
 out:
-	ghes_clear_estatus(ghes);
+	ghes_clear_estatus(ghes, buf_paddr);
 
 	if (rc == -ENOENT)
 		return rc;
@@ -912,6 +919,7 @@ static void __process_error(struct ghes *ghes)
 
 static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 {
+	u64 buf_paddr;
 	struct ghes *ghes;
 	int sev, ret = NMI_DONE;
 
@@ -919,8 +927,8 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 		return ret;
 
 	list_for_each_entry_rcu(ghes, &ghes_nmi, list) {
-		if (ghes_read_estatus(ghes)) {
-			ghes_clear_estatus(ghes);
+		if (ghes_read_estatus(ghes, &buf_paddr)) {
+			ghes_clear_estatus(ghes, buf_paddr);
 			continue;
 		} else {
 			ret = NMI_HANDLED;
@@ -929,14 +937,14 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 		sev = ghes_severity(ghes->estatus->error_severity);
 		if (sev >= GHES_SEV_PANIC) {
 			ghes_print_queued_estatus();
-			__ghes_panic(ghes);
+			__ghes_panic(ghes, buf_paddr);
 		}
 
 		if (!(ghes->flags & GHES_TO_CLEAR))
 			continue;
 
 		__process_error(ghes);
-		ghes_clear_estatus(ghes);
+		ghes_clear_estatus(ghes, buf_paddr);
 	}
 
 #ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index cd9ee507d860..f82f4a7ddd90 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -22,7 +22,6 @@ struct ghes {
 		struct acpi_hest_generic_v2 *generic_v2;
 	};
 	struct acpi_hest_generic_status *estatus;
-	u64 buffer_paddr;
 	unsigned long flags;
 	union {
 		struct list_head list;
-- 
2.20.1


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

  parent reply index

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-29 18:48 [PATCH v8 00/26] APEI in_nmi() rework and SDEI wire-up James Morse
2019-01-29 18:48 ` [PATCH v8 01/26] ACPI / APEI: Don't wait to serialise with oops messages when panic()ing James Morse
2019-01-29 18:48 ` [PATCH v8 02/26] ACPI / APEI: Remove silent flag from ghes_read_estatus() James Morse
2019-01-29 18:48 ` [PATCH v8 03/26] ACPI / APEI: Switch estatus pool to use vmalloc memory James Morse
2019-01-29 18:48 ` [PATCH v8 04/26] ACPI / APEI: Make hest.c manage the estatus memory pool James Morse
2019-02-01 13:20   ` Borislav Petkov
2019-01-29 18:48 ` [PATCH v8 05/26] ACPI / APEI: Make estatus pool allocation a static size James Morse
2019-01-29 18:48 ` James Morse [this message]
2019-01-29 18:48 ` [PATCH v8 07/26] ACPI / APEI: Remove spurious GHES_TO_CLEAR check James Morse
2019-01-29 18:48 ` [PATCH v8 08/26] ACPI / APEI: Don't update struct ghes' flags in read/clear estatus James Morse
2019-01-29 18:48 ` [PATCH v8 09/26] ACPI / APEI: Generalise the estatus queue's notify code James Morse
2019-02-01 13:46   ` Borislav Petkov
2019-01-29 18:48 ` [PATCH v8 10/26] ACPI / APEI: Don't allow ghes_ack_error() to mask earlier errors James Morse
2019-01-29 18:48 ` [PATCH v8 11/26] ACPI / APEI: Move NOTIFY_SEA between the estatus-queue and NOTIFY_NMI James Morse
2019-01-29 18:48 ` [PATCH v8 12/26] ACPI / APEI: Switch NOTIFY_SEA to use the estatus queue James Morse
2019-01-29 18:48 ` [PATCH v8 13/26] KVM: arm/arm64: Add kvm_ras.h to collect kvm specific RAS plumbing James Morse
2019-01-29 18:48 ` [PATCH v8 14/26] arm64: KVM/mm: Move SEA handling behind a single 'claim' interface James Morse
2019-01-29 18:48 ` [PATCH v8 15/26] ACPI / APEI: Move locking to the notification helper James Morse
2019-01-29 18:48 ` [PATCH v8 16/26] ACPI / APEI: Let the notification helper specify the fixmap slot James Morse
2019-01-29 18:48 ` [PATCH v8 17/26] ACPI / APEI: Pass ghes and estatus separately to avoid a later copy James Morse
2019-01-29 18:48 ` [PATCH v8 18/26] ACPI / APEI: Make GHES estatus header validation more user friendly James Morse
2019-02-01 14:30   ` Borislav Petkov
2019-01-29 18:48 ` [PATCH v8 19/26] ACPI / APEI: Split ghes_read_estatus() to allow a peek at the CPER length James Morse
2019-01-29 18:48 ` [PATCH v8 20/26] ACPI / APEI: Only use queued estatus entry during in_nmi_queue_one_entry() James Morse
2019-01-29 18:48 ` [PATCH v8 21/26] ACPI / APEI: Use separate fixmap pages for arm64 NMI-like notifications James Morse
2019-01-29 18:48 ` [PATCH v8 22/26] mm/memory-failure: Add memory_failure_queue_kick() James Morse
2019-01-29 18:48 ` [PATCH v8 23/26] ACPI / APEI: Kick the memory_failure() queue for synchronous errors James Morse
2019-01-29 18:49 ` [PATCH v8 24/26] arm64: acpi: Make apei_claim_sea() synchronise with APEI's irq work James Morse
2019-01-30  8:56   ` Julien Thierry
2019-01-29 18:49 ` [PATCH v8 25/26] firmware: arm_sdei: Add ACPI GHES registration helper James Morse
2019-01-29 18:49 ` [PATCH v8 26/26] ACPI / APEI: Add support for the SDEI GHES Notification type James Morse
2019-02-08 11:40 ` [PATCH v8 00/26] APEI in_nmi() rework and SDEI wire-up Rafael J. Wysocki
2019-02-08 14:13   ` James Morse
2019-02-11 11:05     ` Rafael J. Wysocki
2019-02-11 18:35       ` James Morse
2019-02-12 22:14         ` Rafael J. Wysocki

Reply instructions:

You may reply publically 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=20190129184902.102850-7-james.morse@arm.com \
    --to=james.morse@arm.com \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=christoffer.dall@arm.com \
    --cc=gengdongjiu@huawei.com \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=lenb@kernel.org \
    --cc=linux-acpi@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-mm@kvack.org \
    --cc=marc.zyngier@arm.com \
    --cc=n-horiguchi@ah.jp.nec.com \
    --cc=rjw@rjwysocki.net \
    --cc=tony.luck@intel.com \
    --cc=will.deacon@arm.com \
    --cc=xiexiuqi@huawei.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

Linux-ARM-Kernel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-arm-kernel/0 linux-arm-kernel/git/0.git
	git clone --mirror https://lore.kernel.org/linux-arm-kernel/1 linux-arm-kernel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-arm-kernel linux-arm-kernel/ https://lore.kernel.org/linux-arm-kernel \
		linux-arm-kernel@lists.infradead.org
	public-inbox-index linux-arm-kernel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.infradead.lists.linux-arm-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git