On Sun, Apr 21, 2024 at 10:13 PM Baolu Lu <baolu.lu@xxxxxxxxxxxxxxx> wrote:
>
> On 4/19/24 12:32 AM, Tomasz Jeznach wrote:
> > Introduce device context allocation and device directory tree
> > management including capabilities discovery sequence, as described
> > in Chapter 2.1 of the RISC-V IOMMU Architecture Specification.
> >
> > Device directory mode will be auto detected using DDTP WARL property,
> > using highest mode supported by the driver and hardware. If none
> > supported can be configured, driver will fall back to global pass-through.
> >
> > First level DDTP page can be located in I/O (detected using DDTP WARL)
> > and system memory.
> >
> > Only identity protection domain is supported by this implementation.
> >
> > Co-developed-by: Nick Kossifidis <mick@xxxxxxxxxxxx>
> > Signed-off-by: Nick Kossifidis <mick@xxxxxxxxxxxx>
> > Signed-off-by: Tomasz Jeznach <tjeznach@xxxxxxxxxxxx>
> > ---
> > drivers/iommu/riscv/iommu.c | 369 +++++++++++++++++++++++++++++++++++-
> > drivers/iommu/riscv/iommu.h | 5 +
> > 2 files changed, 365 insertions(+), 9 deletions(-)
>
> [ ... ]
>
> > +
> > +/*
> > + * Discover supported DDT modes starting from requested value,
> > + * configure DDTP register with accepted mode and root DDT address.
> > + * Accepted iommu->ddt_mode is updated on success.
> > + */
> > +static int riscv_iommu_set_ddtp_mode(struct riscv_iommu_device *iommu,
> > + unsigned int ddtp_mode)
> > +{
> > + struct device *dev = iommu->dev;
> > + u64 ddtp, rq_ddtp;
> > + unsigned int mode, rq_mode = ddtp_mode;
> > + int rc;
> > +
> > + rc = readq_relaxed_poll_timeout(iommu->reg + RISCV_IOMMU_REG_DDTP,
> > + ddtp, !(ddtp & RISCV_IOMMU_DDTP_BUSY),
> > + 10, RISCV_IOMMU_DDTP_TIMEOUT);
> > + if (rc < 0)
> > + return -EBUSY;
> > +
> > + /* Disallow state transition from xLVL to xLVL. */
> > + switch (FIELD_GET(RISCV_IOMMU_DDTP_MODE, ddtp)) {
> > + case RISCV_IOMMU_DDTP_MODE_BARE:
> > + case RISCV_IOMMU_DDTP_MODE_OFF:
> > + break;
> > + default:
> > + if (rq_mode != RISCV_IOMMU_DDTP_MODE_BARE &&
> > + rq_mode != RISCV_IOMMU_DDTP_MODE_OFF)
> > + return -EINVAL;
>
> Is this check duplicate? It appears that it's always true in the default
> branch.
>
No. The condition in the switch represents current mode, while check
in default branch checks desired mode device will be configured to.
I've reworked the code in v3 to be more readable.
> > + break;
> > + }
> > +
> > + do {
> > + rq_ddtp = FIELD_PREP(RISCV_IOMMU_DDTP_MODE, rq_mode);
> > + if (rq_mode > RISCV_IOMMU_DDTP_MODE_BARE)
> > + rq_ddtp |= phys_to_ppn(iommu->ddt_phys);
> > +
> > + riscv_iommu_writeq(iommu, RISCV_IOMMU_REG_DDTP, rq_ddtp);
> > +
> > + rc = readq_relaxed_poll_timeout(iommu->reg + RISCV_IOMMU_REG_DDTP,
> > + ddtp, !(ddtp & RISCV_IOMMU_DDTP_BUSY),
> > + 10, RISCV_IOMMU_DDTP_TIMEOUT);
> > + if (rc < 0) {
> > + dev_warn(dev, "timeout when setting ddtp (ddt mode: %u, read: %llx)\n",
> > + rq_mode, ddtp);
> > + return -EBUSY;
> > + }
> > +
> > + /* Verify IOMMU hardware accepts new DDTP config. */
> > + mode = FIELD_GET(RISCV_IOMMU_DDTP_MODE, ddtp);
> > +
> > + if (rq_mode == mode)
> > + break;
> > +
> > + /* Hardware mandatory DDTP mode has not been accepted. */
> > + if (rq_mode < RISCV_IOMMU_DDTP_MODE_1LVL && rq_ddtp != ddtp) {
> > + dev_warn(dev, "DDTP update failed hw: %llx vs %llx\n", ddtp, rq_ddtp);
> > + return -EINVAL;
> > + }
> > +
> > + /*
> > + * Mode field is WARL, an IOMMU may support a subset of
> > + * directory table levels in which case if we tried to set
> > + * an unsupported number of levels we'll readback either
> > + * a valid xLVL or off/bare. If we got off/bare, try again
> > + * with a smaller xLVL.
> > + */
> > + if (mode < RISCV_IOMMU_DDTP_MODE_1LVL &&
> > + rq_mode > RISCV_IOMMU_DDTP_MODE_1LVL) {
> > + dev_dbg(dev, "DDTP hw mode %u vs %u\n", mode, rq_mode);
> > + rq_mode--;
> > + continue;
> > + }
> > +
> > + /*
> > + * We tried all supported modes and IOMMU hardware failed to
> > + * accept new settings, something went very wrong since off/bare
> > + * and at least one xLVL must be supported.
> > + */
> > + dev_warn(dev, "DDTP hw mode %u, failed to set %u\n", mode, ddtp_mode);
> > + return -EINVAL;
> > + } while (1);
> > +
> > + iommu->ddt_mode = mode;
> > + if (mode != ddtp_mode)
> > + dev_warn(dev, "DDTP failover to %u mode, requested %u\n",
> > + mode, ddtp_mode);
> > +
> > + return 0;
> > +}
> > +
>
> [ ... ]
>
> > +
> > +static int riscv_iommu_attach_domain(struct riscv_iommu_device *iommu,
> > + struct device *dev,
> > + struct iommu_domain *iommu_domain)
> > +{
> > + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
> > + struct riscv_iommu_dc *dc;
> > + u64 fsc, ta, tc;
> > + int i;
> > +
> > + if (!iommu_domain) {
> > + ta = 0;
> > + tc = 0;
> > + fsc = 0;
> > + } else if (iommu_domain->type == IOMMU_DOMAIN_IDENTITY) {
> > + ta = 0;
> > + tc = RISCV_IOMMU_DC_TC_V;
> > + fsc = FIELD_PREP(RISCV_IOMMU_DC_FSC_MODE, RISCV_IOMMU_DC_FSC_MODE_BARE);
> > + } else {
> > + /* This should never happen. */
> > + return -ENODEV;
> > + }
>
> Move the domain->type check code to the domain-specific ops.
>
> > +
> > + /* Update existing or allocate new entries in device directory */
> > + for (i = 0; i < fwspec->num_ids; i++) {
> > + dc = riscv_iommu_get_dc(iommu, fwspec->ids[i], !iommu_domain);
> > + if (!dc && !iommu_domain)
> > + continue;
> > + if (!dc)
> > + return -ENODEV;
> > +
> > + /* Swap device context, update TC valid bit as the last operation */
> > + xchg64(&dc->fsc, fsc);
> > + xchg64(&dc->ta, ta);
> > + xchg64(&dc->tc, tc);
> > +
> > + /* Device context invalidation will be required. Ignoring for now. */
> > + }
> > +
> > return 0;
> > }
> >
> > +static int riscv_iommu_attach_identity_domain(struct iommu_domain *iommu_domain,
> > + struct device *dev)
> > +{
> > + struct riscv_iommu_device *iommu = dev_to_iommu(dev);
> > +
> > + /* Global pass-through already enabled, do nothing. */
> > + if (iommu->ddt_mode == RISCV_IOMMU_DDTP_MODE_BARE)
> > + return 0;
> > +
> > + return riscv_iommu_attach_domain(iommu, dev, iommu_domain);
> > +}
> > +
> > static struct iommu_domain riscv_iommu_identity_domain = {
> > .type = IOMMU_DOMAIN_IDENTITY,
> > .ops = &(const struct iommu_domain_ops) {
> > @@ -82,6 +420,13 @@ static void riscv_iommu_probe_finalize(struct device *dev)
> > iommu_setup_dma_ops(dev, 0, U64_MAX);
> > }
> >
> > +static void riscv_iommu_release_device(struct device *dev)
> > +{
> > + struct riscv_iommu_device *iommu = dev_to_iommu(dev);
> > +
> > + riscv_iommu_attach_domain(iommu, dev, NULL);
>
> Attaching a NULL domain to a device has already been removed. You can
> use the iommu_ops->release_domain here.
>
> > +}
> > +
> > static const struct iommu_ops riscv_iommu_ops = {
> > .owner = THIS_MODULE,
> > .of_xlate = riscv_iommu_of_xlate,
> > @@ -90,6 +435,7 @@ static const struct iommu_ops riscv_iommu_ops = {
> > .device_group = riscv_iommu_device_group,
> > .probe_device = riscv_iommu_probe_device,
> > .probe_finalize = riscv_iommu_probe_finalize,
>
> The probe_finalize op will be removed soon.
>
> https://lore.kernel.org/linux-iommu/bebea331c1d688b34d9862eefd5ede47503961b8.1713523152.git.robin.murphy@xxxxxxx/
Thanks, I'm aware of the change, once this change is pulled for
iommu/next I'll just remove probe_finalize.
>
> > + .release_device = riscv_iommu_release_device,
> > };
> >
> > static int riscv_iommu_init_check(struct riscv_iommu_device *iommu)
> > @@ -124,6 +470,7 @@ void riscv_iommu_remove(struct riscv_iommu_device *iommu)
> > {
> > iommu_device_unregister(&iommu->iommu);
> > iommu_device_sysfs_remove(&iommu->iommu);
> > + riscv_iommu_set_ddtp_mode(iommu, RISCV_IOMMU_DDTP_MODE_OFF);
> > }
> >
> > int riscv_iommu_init(struct riscv_iommu_device *iommu)
> > @@ -133,12 +480,14 @@ int riscv_iommu_init(struct riscv_iommu_device *iommu)
> > rc = riscv_iommu_init_check(iommu);
> > if (rc)
> > return dev_err_probe(iommu->dev, rc, "unexpected device state\n");
> > - /*
> > - * Placeholder for a complete IOMMU device initialization.
> > - * For now, only bare minimum: enable global identity mapping mode and register sysfs.
> > - */
> > - riscv_iommu_writeq(iommu, RISCV_IOMMU_REG_DDTP,
> > - FIELD_PREP(RISCV_IOMMU_DDTP_MODE, RISCV_IOMMU_DDTP_MODE_BARE));
> > +
> > + rc = riscv_iommu_ddt_alloc(iommu);
> > + if (WARN(rc, "cannot allocate device directory\n"))
> > + goto err_init;
> > +
> > + rc = riscv_iommu_set_ddtp_mode(iommu, RISCV_IOMMU_DDTP_MODE_MAX);
> > + if (WARN(rc, "cannot enable iommu device\n"))
> > + goto err_init;
> >
> > rc = iommu_device_sysfs_add(&iommu->iommu, NULL, NULL, "riscv-iommu@%s",
> > dev_name(iommu->dev));
> > @@ -154,5 +503,7 @@ int riscv_iommu_init(struct riscv_iommu_device *iommu)
> > err_iommu:
> > iommu_device_sysfs_remove(&iommu->iommu);
> > err_sysfs:
> > + riscv_iommu_set_ddtp_mode(iommu, RISCV_IOMMU_DDTP_MODE_OFF);
> > +err_init:
> > return rc;
> > }
> > diff --git a/drivers/iommu/riscv/iommu.h b/drivers/iommu/riscv/iommu.h
> > index 700e33dc2446..f1696926582c 100644
> > --- a/drivers/iommu/riscv/iommu.h
> > +++ b/drivers/iommu/riscv/iommu.h
> > @@ -34,6 +34,11 @@ struct riscv_iommu_device {
> > /* available interrupt numbers, MSI or WSI */
> > unsigned int irqs[RISCV_IOMMU_INTR_COUNT];
> > unsigned int irqs_count;
> > +
> > + /* device directory */
> > + unsigned int ddt_mode;
> > + dma_addr_t ddt_phys;
> > + u64 *ddt_root;
> > };
> >
> > int riscv_iommu_init(struct riscv_iommu_device *iommu);
>
> Best regards,
> baolu
Thank you, Best.
- Tomasz
