From: Mostafa Saleh <smostafa@google.com>
To: Jason Gunthorpe <jgg@nvidia.com>
Cc: iommu@lists.linux.dev, Joerg Roedel <joro@8bytes.org>,
linux-arm-kernel@lists.infradead.org,
Robin Murphy <robin.murphy@arm.com>,
Will Deacon <will@kernel.org>, Eric Auger <eric.auger@redhat.com>,
Jean-Philippe Brucker <jean-philippe@linaro.org>,
Moritz Fischer <mdf@kernel.org>,
Michael Shavit <mshavit@google.com>,
Nicolin Chen <nicolinc@nvidia.com>,
patches@lists.linux.dev,
Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com>
Subject: Re: [PATCH v5 05/27] iommu/arm-smmu-v3: Make CD programming use arm_smmu_write_entry()
Date: Sat, 23 Mar 2024 13:02:15 +0000 [thread overview]
Message-ID: <Zf7S109OKJlRVXiR@google.com> (raw)
In-Reply-To: <5-v5-9a37e0c884ce+31e3-smmuv3_newapi_p2_jgg@nvidia.com>
Hi Jason,
On Mon, Mar 04, 2024 at 07:43:53PM -0400, Jason Gunthorpe wrote:
> CD table entries and STE's have the same essential programming sequence,
> just with different types and sizes.
>
> Have arm_smmu_write_ctx_desc() generate a target CD and call
> arm_smmu_write_entry() to do the programming. Due to the way the
> target CD is generated by modifying the existing CD this alone is not
> enough for the CD callers to be freed of the ordering requirements.
>
> The following patches will make the rest of the CD flow mirror the STE
> flow with precise CD contents generated in all cases.
>
> Currently the logic can't ensure that the CD always conforms to the used
> requirements until all the CD generation is moved to the new method. Add a
> temporary no_used_check to disable the assertions.
>
I am still going through the patches, but is it possible to
reorder/squash to avoid that, so it is easier to review?
> Signed-off-by: Michael Shavit <mshavit@google.com>
> Tested-by: Nicolin Chen <nicolinc@nvidia.com>
> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> ---
> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 101 ++++++++++++++------
> 1 file changed, 74 insertions(+), 27 deletions(-)
>
> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> index b7f947e36f596f..237fd6d92c880b 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -57,11 +57,14 @@ struct arm_smmu_entry_writer {
> struct arm_smmu_entry_writer_ops {
> unsigned int num_entry_qwords;
> __le64 v_bit;
> + bool no_used_check;
> void (*get_used)(const __le64 *entry, __le64 *used);
> void (*sync)(struct arm_smmu_entry_writer *writer);
> };
>
> -#define NUM_ENTRY_QWORDS (sizeof(struct arm_smmu_ste) / sizeof(u64))
> +#define NUM_ENTRY_QWORDS \
> + (max(sizeof(struct arm_smmu_ste), sizeof(struct arm_smmu_cd)) / \
> + sizeof(u64))
>
> static phys_addr_t arm_smmu_msi_cfg[ARM_SMMU_MAX_MSIS][3] = {
> [EVTQ_MSI_INDEX] = {
> @@ -1056,7 +1059,8 @@ static u8 arm_smmu_entry_qword_diff(struct arm_smmu_entry_writer *writer,
> * allowed to set a bit to 1 if the used function doesn't say it
> * is used.
> */
> - WARN_ON_ONCE(target[i] & ~target_used[i]);
> + if (!writer->ops->no_used_check)
> + WARN_ON_ONCE(target[i] & ~target_used[i]);
>
> /* Bits can change because they are not currently being used */
> unused_update[i] = (entry[i] & cur_used[i]) |
> @@ -1065,7 +1069,8 @@ static u8 arm_smmu_entry_qword_diff(struct arm_smmu_entry_writer *writer,
> * Each bit indicates that a used bit in a qword needs to be
> * changed after unused_update is applied.
> */
> - if ((unused_update[i] & target_used[i]) != target[i])
> + if ((unused_update[i] & target_used[i]) !=
> + (target[i] & target_used[i]))
> used_qword_diff |= 1 << i;
> }
> return used_qword_diff;
> @@ -1161,8 +1166,11 @@ static void arm_smmu_write_entry(struct arm_smmu_entry_writer *writer,
> * in the entry. The target was already sanity checked by
> * compute_qword_diff().
> */
> - WARN_ON_ONCE(
> - entry_set(writer, entry, target, 0, num_entry_qwords));
> + if (writer->ops->no_used_check)
> + entry_set(writer, entry, target, 0, num_entry_qwords);
> + else
> + WARN_ON_ONCE(entry_set(writer, entry, target, 0,
> + num_entry_qwords));
> }
> }
>
> @@ -1242,6 +1250,59 @@ static struct arm_smmu_cd *arm_smmu_get_cd_ptr(struct arm_smmu_master *master,
> return &l1_desc->l2ptr[idx];
> }
>
> +struct arm_smmu_cd_writer {
> + struct arm_smmu_entry_writer writer;
> + unsigned int ssid;
> +};
> +
> +static void arm_smmu_get_cd_used(const __le64 *ent, __le64 *used_bits)
> +{
> + used_bits[0] = cpu_to_le64(CTXDESC_CD_0_V);
> + if (!(ent[0] & cpu_to_le64(CTXDESC_CD_0_V)))
> + return;
> + memset(used_bits, 0xFF, sizeof(struct arm_smmu_cd));
This is a slightly different approach than what the driver does for STEs,
where it explicitly sets the used bits. Is there a reason for that?
> +
> + /* EPD0 means T0SZ/TG0/IR0/OR0/SH0/TTB0 are IGNORED */
> + if (ent[0] & cpu_to_le64(CTXDESC_CD_0_TCR_EPD0)) {
> + used_bits[0] &= ~cpu_to_le64(
> + CTXDESC_CD_0_TCR_T0SZ | CTXDESC_CD_0_TCR_TG0 |
> + CTXDESC_CD_0_TCR_IRGN0 | CTXDESC_CD_0_TCR_ORGN0 |
> + CTXDESC_CD_0_TCR_SH0);
> + used_bits[1] &= ~cpu_to_le64(CTXDESC_CD_1_TTB0_MASK);
> + }
> +}
We should add a comment about EPD1 maybe?
> +
> +static void arm_smmu_cd_writer_sync_entry(struct arm_smmu_entry_writer *writer)
> +{
> + struct arm_smmu_cd_writer *cd_writer =
> + container_of(writer, struct arm_smmu_cd_writer, writer);
> +
> + arm_smmu_sync_cd(writer->master, cd_writer->ssid, true);
> +}
> +
> +static const struct arm_smmu_entry_writer_ops arm_smmu_cd_writer_ops = {
> + .sync = arm_smmu_cd_writer_sync_entry,
> + .get_used = arm_smmu_get_cd_used,
> + .v_bit = cpu_to_le64(CTXDESC_CD_0_V),
> + .no_used_check = true,
> + .num_entry_qwords = sizeof(struct arm_smmu_cd) / sizeof(u64),
> +};
> +
> +static void arm_smmu_write_cd_entry(struct arm_smmu_master *master, int ssid,
> + struct arm_smmu_cd *cdptr,
> + const struct arm_smmu_cd *target)
> +{
> + struct arm_smmu_cd_writer cd_writer = {
> + .writer = {
> + .ops = &arm_smmu_cd_writer_ops,
> + .master = master,
> + },
> + .ssid = ssid,
> + };
> +
> + arm_smmu_write_entry(&cd_writer.writer, cdptr->data, target->data);
> +}
> +
> int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
> struct arm_smmu_ctx_desc *cd)
> {
> @@ -1258,17 +1319,20 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
> */
> u64 val;
> bool cd_live;
> - struct arm_smmu_cd *cdptr;
> + struct arm_smmu_cd target;
> + struct arm_smmu_cd *cdptr = ⌖
> + struct arm_smmu_cd *cd_table_entry;
> struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table;
> struct arm_smmu_device *smmu = master->smmu;
>
> if (WARN_ON(ssid >= (1 << cd_table->s1cdmax)))
> return -E2BIG;
>
> - cdptr = arm_smmu_get_cd_ptr(master, ssid);
> - if (!cdptr)
> + cd_table_entry = arm_smmu_get_cd_ptr(master, ssid);
> + if (!cd_table_entry)
> return -ENOMEM;
>
> + target = *cd_table_entry;
> val = le64_to_cpu(cdptr->data[0]);
> cd_live = !!(val & CTXDESC_CD_0_V);
>
> @@ -1290,13 +1354,6 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
> cdptr->data[2] = 0;
> cdptr->data[3] = cpu_to_le64(cd->mair);
>
> - /*
> - * STE may be live, and the SMMU might read dwords of this CD in any
> - * order. Ensure that it observes valid values before reading
> - * V=1.
> - */
> - arm_smmu_sync_cd(master, ssid, true);
> -
> val = cd->tcr |
> #ifdef __BIG_ENDIAN
> CTXDESC_CD_0_ENDI |
> @@ -1310,18 +1367,8 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
> if (cd_table->stall_enabled)
> val |= CTXDESC_CD_0_S;
> }
> -
> - /*
> - * The SMMU accesses 64-bit values atomically. See IHI0070Ca 3.21.3
> - * "Configuration structures and configuration invalidation completion"
> - *
> - * The size of single-copy atomic reads made by the SMMU is
> - * IMPLEMENTATION DEFINED but must be at least 64 bits. Any single
> - * field within an aligned 64-bit span of a structure can be altered
> - * without first making the structure invalid.
> - */
> - WRITE_ONCE(cdptr->data[0], cpu_to_le64(val));
> - arm_smmu_sync_cd(master, ssid, true);
> + cdptr->data[0] = cpu_to_le64(val);
> + arm_smmu_write_cd_entry(master, ssid, cd_table_entry, &target);
> return 0;
> }
>
> --
> 2.43.2
Thanks,
Mostafa
next prev parent reply other threads:[~2024-03-23 13:02 UTC|newest]
Thread overview: 116+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-04 23:43 [PATCH v5 00/27] Update SMMUv3 to the modern iommu API (part 2/3) Jason Gunthorpe
2024-03-04 23:43 ` [PATCH v5 01/27] iommu/arm-smmu-v3: Do not allow a SVA domain to be set on the wrong PASID Jason Gunthorpe
2024-03-15 3:38 ` Nicolin Chen
2024-03-18 18:16 ` Jason Gunthorpe
2024-03-22 17:48 ` Mostafa Saleh
2024-03-26 18:30 ` Jason Gunthorpe
2024-03-26 19:06 ` Mostafa Saleh
2024-03-26 22:10 ` Jason Gunthorpe
2024-03-04 23:43 ` [PATCH v5 02/27] iommu/arm-smmu-v3: Do not ATC invalidate the entire domain Jason Gunthorpe
2024-03-13 9:18 ` Michael Shavit
2024-03-15 2:24 ` Nicolin Chen
2024-03-16 18:09 ` Moritz Fischer
2024-03-22 17:51 ` Mostafa Saleh
2024-03-04 23:43 ` [PATCH v5 03/27] iommu/arm-smmu-v3: Add a type for the CD entry Jason Gunthorpe
2024-03-13 9:44 ` Michael Shavit
2024-03-16 18:10 ` Moritz Fischer
2024-03-18 18:02 ` Jason Gunthorpe
2024-03-15 3:12 ` Nicolin Chen
2024-03-22 17:52 ` Mostafa Saleh
2024-03-04 23:43 ` [PATCH v5 04/27] iommu/arm-smmu-v3: Add an ops indirection to the STE code Jason Gunthorpe
2024-03-13 11:30 ` Michael Shavit
2024-03-15 4:22 ` Nicolin Chen
2024-03-15 5:20 ` Nicolin Chen
2024-03-18 18:06 ` Jason Gunthorpe
2024-03-22 18:14 ` Mostafa Saleh
2024-03-25 14:11 ` Jason Gunthorpe
2024-03-25 21:01 ` Mostafa Saleh
2024-03-04 23:43 ` [PATCH v5 05/27] iommu/arm-smmu-v3: Make CD programming use arm_smmu_write_entry() Jason Gunthorpe
2024-03-15 7:52 ` Nicolin Chen
2024-03-20 12:46 ` Jason Gunthorpe
2024-03-16 18:14 ` Moritz Fischer
2024-03-23 13:02 ` Mostafa Saleh [this message]
2024-03-25 14:25 ` Jason Gunthorpe
2024-03-26 18:30 ` Jason Gunthorpe
2024-03-26 19:12 ` Mostafa Saleh
2024-03-26 22:27 ` Jason Gunthorpe
2024-03-27 9:45 ` Mostafa Saleh
2024-03-27 16:42 ` Jason Gunthorpe
2024-03-04 23:43 ` [PATCH v5 06/27] iommu/arm-smmu-v3: Consolidate clearing a CD table entry Jason Gunthorpe
2024-03-13 11:57 ` Michael Shavit
2024-03-15 6:17 ` Nicolin Chen
2024-03-16 18:15 ` Moritz Fischer
2024-03-22 18:36 ` Mostafa Saleh
2024-03-25 14:14 ` Jason Gunthorpe
2024-03-25 21:02 ` Mostafa Saleh
2024-03-04 23:43 ` [PATCH v5 07/27] iommu/arm-smmu-v3: Move the CD generation for S1 domains into a function Jason Gunthorpe
2024-03-13 12:13 ` Michael Shavit
2024-03-18 18:11 ` Jason Gunthorpe
2024-03-23 13:11 ` Mostafa Saleh
2024-03-25 14:30 ` Jason Gunthorpe
2024-03-04 23:43 ` [PATCH v5 08/27] iommu/arm-smmu-v3: Move allocation of the cdtable into arm_smmu_get_cd_ptr() Jason Gunthorpe
2024-03-13 12:15 ` Michael Shavit
2024-03-16 3:31 ` Nicolin Chen
2024-03-22 19:07 ` Mostafa Saleh
2024-03-25 14:21 ` Jason Gunthorpe
2024-03-25 21:03 ` Mostafa Saleh
2024-03-04 23:43 ` [PATCH v5 09/27] iommu/arm-smmu-v3: Allocate the CD table entry in advance Jason Gunthorpe
2024-03-13 12:17 ` Michael Shavit
2024-03-16 4:16 ` Nicolin Chen
2024-03-18 18:14 ` Jason Gunthorpe
2024-03-22 19:15 ` Mostafa Saleh
2024-03-04 23:43 ` [PATCH v5 10/27] iommu/arm-smmu-v3: Move the CD generation for SVA into a function Jason Gunthorpe
2024-03-16 5:19 ` Nicolin Chen
2024-03-20 13:09 ` Jason Gunthorpe
2024-03-04 23:43 ` [PATCH v5 11/27] iommu/arm-smmu-v3: Build the whole CD in arm_smmu_make_s1_cd() Jason Gunthorpe
2024-03-15 10:04 ` Michael Shavit
2024-03-20 12:50 ` Jason Gunthorpe
2024-03-23 13:20 ` Mostafa Saleh
2024-03-04 23:44 ` [PATCH v5 12/27] iommu/arm-smmu-v3: Start building a generic PASID layer Jason Gunthorpe
2024-03-19 16:11 ` Michael Shavit
2024-03-20 18:32 ` Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 13/27] iommu/arm-smmu-v3: Make smmu_domain->devices into an allocated list Jason Gunthorpe
2024-03-19 13:09 ` Michael Shavit
2024-03-04 23:44 ` [PATCH v5 14/27] iommu/arm-smmu-v3: Make changing domains be hitless for ATS Jason Gunthorpe
2024-03-21 12:26 ` Michael Shavit
2024-03-21 13:28 ` Jason Gunthorpe
2024-03-21 14:53 ` Michael Shavit
2024-03-21 14:57 ` Michael Shavit
2024-03-21 17:32 ` Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 15/27] iommu/arm-smmu-v3: Add ssid to struct arm_smmu_master_domain Jason Gunthorpe
2024-03-19 13:31 ` Michael Shavit
2024-03-20 12:53 ` Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 16/27] iommu/arm-smmu-v3: Keep track of valid CD entries in the cd_table Jason Gunthorpe
2024-03-19 13:55 ` Michael Shavit
2024-03-20 18:21 ` Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 17/27] iommu/arm-smmu-v3: Thread SSID through the arm_smmu_attach_*() interface Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 18/27] iommu/arm-smmu-v3: Make SVA allocate a normal arm_smmu_domain Jason Gunthorpe
2024-03-19 14:52 ` Michael Shavit
2024-03-20 23:20 ` Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 19/27] iommu/arm-smmu-v3: Keep track of arm_smmu_master_domain for SVA Jason Gunthorpe
2024-03-21 10:47 ` Michael Shavit
2024-03-21 13:55 ` Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 20/27] iommu: Add ops->domain_alloc_sva() Jason Gunthorpe
2024-03-19 15:09 ` Michael Shavit
2024-03-04 23:44 ` [PATCH v5 21/27] iommu/arm-smmu-v3: Put the SVA mmu notifier in the smmu_domain Jason Gunthorpe
2024-03-19 16:23 ` Michael Shavit
2024-03-20 18:35 ` Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 22/27] iommu/arm-smmu-v3: Consolidate freeing the ASID/VMID Jason Gunthorpe
2024-03-19 16:44 ` Michael Shavit
2024-03-19 18:37 ` Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 23/27] iommu/arm-smmu-v3: Move the arm_smmu_asid_xa to per-smmu like vmid Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 24/27] iommu/arm-smmu-v3: Bring back SVA BTM support Jason Gunthorpe
2024-03-19 17:07 ` Michael Shavit
2024-03-20 13:05 ` Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 25/27] iommu/arm-smmu-v3: Allow IDENTITY/BLOCKED to be set while PASID is used Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 26/27] iommu/arm-smmu-v3: Allow a PASID to be set when RID is IDENTITY/BLOCKED Jason Gunthorpe
2024-03-04 23:44 ` [PATCH v5 27/27] iommu/arm-smmu-v3: Allow setting a S1 domain to a PASID Jason Gunthorpe
2024-03-15 10:40 ` [PATCH v5 00/27] Update SMMUv3 to the modern iommu API (part 2/3) Shameerali Kolothum Thodi
2024-03-23 13:38 ` Mostafa Saleh
2024-03-25 14:35 ` Jason Gunthorpe
2024-03-25 21:06 ` Mostafa Saleh
2024-03-25 22:44 ` Jason Gunthorpe
2024-03-25 10:22 ` Mostafa Saleh
2024-03-25 10:44 ` Shameerali Kolothum Thodi
2024-03-25 11:22 ` Mostafa Saleh
2024-03-25 16:47 ` Jason Gunthorpe
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=Zf7S109OKJlRVXiR@google.com \
--to=smostafa@google.com \
--cc=eric.auger@redhat.com \
--cc=iommu@lists.linux.dev \
--cc=jean-philippe@linaro.org \
--cc=jgg@nvidia.com \
--cc=joro@8bytes.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=mdf@kernel.org \
--cc=mshavit@google.com \
--cc=nicolinc@nvidia.com \
--cc=patches@lists.linux.dev \
--cc=robin.murphy@arm.com \
--cc=shameerali.kolothum.thodi@huawei.com \
--cc=will@kernel.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