Linux-ARM-Kernel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Sven Peter <sven@kernel.org>
To: Janne Grunau <j@jannau.net>, Neal Gompa <neal@gompa.dev>,
	 Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@kernel.dk>,
	 Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
	 Arnd Bergmann <arnd@arndb.de>
Cc: asahi@lists.linux.dev, linux-arm-kernel@lists.infradead.org,
	 linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org,
	 Sven Peter <sven@kernel.org>
Subject: [PATCH 4/6] nvme: Add a quirk for page aligned admin queue buffers
Date: Thu, 06 Aug 2026 17:27:36 +0200	[thread overview]
Message-ID: <20260806-b4-nvme-fwabi-v1-4-bde19ce8db04@kernel.org> (raw)
In-Reply-To: <20260806-b4-nvme-fwabi-v1-0-bde19ce8db04@kernel.org>

Apple controllers seem to require any queue buffers on the admin queue
to be aligned to the NVMe controller page size. Weirdly, this constraint
does not apply to the i/o queue where any alignment is fine. This has
always been required on pre-M1 controllers and is required starting with
macOS 15 firmware or post-M4 controllers again. On M1/M2/M3 we only got
away with this because there was a chicken bit to disable this
requirement. Let's add a quirk that enforces this alignment.

Signed-off-by: Sven Peter <sven@kernel.org>
---
 drivers/nvme/host/core.c | 5 ++++-
 drivers/nvme/host/nvme.h | 7 +++++++
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 453c1f0b2dd0..b76f4e4d8850 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2071,7 +2071,10 @@ static void nvme_set_ctrl_limits(struct nvme_ctrl *ctrl,
 	lim->max_integrity_segments = ctrl->max_integrity_segments;
 	lim->virt_boundary_mask = ctrl->ops->get_virt_boundary(ctrl, is_admin);
 	lim->max_segment_size = UINT_MAX;
-	lim->dma_alignment = 3;
+	if (is_admin && (ctrl->quirks & NVME_QUIRK_ADMIN_PAGE_ALIGN))
+		lim->dma_alignment = NVME_CTRL_PAGE_SIZE - 1;
+	else
+		lim->dma_alignment = 3;
 }
 
 static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 824651cc898d..957ded0c6f53 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -178,6 +178,11 @@ enum nvme_quirks {
 	 * Align dma pool segment size to 512 bytes
 	 */
 	NVME_QUIRK_DMAPOOL_ALIGN_512		= (1 << 22),
+
+	/*
+	 * Admin queue DMA buffers must be page aligned
+	 */
+	NVME_QUIRK_ADMIN_PAGE_ALIGN		= (1 << 23),
 };
 
 static inline char *nvme_quirk_name(enum nvme_quirks q)
@@ -229,6 +234,8 @@ static inline char *nvme_quirk_name(enum nvme_quirks q)
 		return "broken_msi";
 	case NVME_QUIRK_DMAPOOL_ALIGN_512:
 		return "dmapool_align_512";
+	case NVME_QUIRK_ADMIN_PAGE_ALIGN:
+		return "admin_page_align";
 	}
 
 	return "unknown";

-- 
2.55.0




  parent reply	other threads:[~2026-08-06 15:28 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-06 15:27 [PATCH 0/6] Apple NVMe fixes for macOS 15+ firmware / M4 support Sven Peter
2026-08-06 15:27 ` [PATCH 1/6] nvme-apple: Destroy the admin queue on removal Sven Peter
2026-08-06 15:27 ` [PATCH 2/6] nvme-apple: Don't set a DMA direction for commands without a data transfer Sven Peter
2026-08-06 15:27 ` [PATCH 3/6] nvme-apple: Never set the opcode in the NVMMU TCB Sven Peter
2026-08-06 15:27 ` Sven Peter [this message]
2026-08-06 15:27 ` [PATCH 5/6] nvme-apple: Require page aligned buffers on the admin queue Sven Peter
2026-08-06 15:27 ` [PATCH 6/6] nvme-apple: Drop the PRP null check chicken bit Sven Peter
2026-08-06 16:50 ` [PATCH 0/6] Apple NVMe fixes for macOS 15+ firmware / M4 support Nick Chan
2026-08-06 17:37 ` Janne Grunau
2026-08-07 15:36 ` Joshua Peisach

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=20260806-b4-nvme-fwabi-v1-4-bde19ce8db04@kernel.org \
    --to=sven@kernel.org \
    --cc=arnd@arndb.de \
    --cc=asahi@lists.linux.dev \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=j@jannau.net \
    --cc=kbusch@kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=neal@gompa.dev \
    --cc=sagi@grimberg.me \
    /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