diff mbox series

[v6,06/29] iommu/arm-smmu-v3: Add an ops indirection to the STE code

Message ID 6-v6-228e7adf25eb+4155-smmuv3_newapi_p2_jgg@nvidia.com (mailing list archive)
State New, archived
Headers show
Series Update SMMUv3 to the modern iommu API (part 2/3) | expand

Commit Message

Jason Gunthorpe March 27, 2024, 6:07 p.m. UTC
Prepare to put the CD code into the same mechanism. Add an ops indirection
around all the STE specific code and make the worker functions independent
of the entry content being processed.

get_used and sync ops are provided to hook the correct code.

Signed-off-by: Michael Shavit <mshavit@google.com>
Reviewed-by: Michael Shavit <mshavit@google.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 170 ++++++++++++--------
 1 file changed, 102 insertions(+), 68 deletions(-)

Comments

Will Deacon April 9, 2024, 12:40 p.m. UTC | #1
On Wed, Mar 27, 2024 at 03:07:52PM -0300, Jason Gunthorpe wrote:
> Prepare to put the CD code into the same mechanism. Add an ops indirection
> around all the STE specific code and make the worker functions independent
> of the entry content being processed.
> 
> get_used and sync ops are provided to hook the correct code.
> 
> Signed-off-by: Michael Shavit <mshavit@google.com>
> Reviewed-by: Michael Shavit <mshavit@google.com>
> Tested-by: Nicolin Chen <nicolinc@nvidia.com>
> Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> ---
>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 170 ++++++++++++--------
>  1 file changed, 102 insertions(+), 68 deletions(-)

Any chance we can pull the STE testing stuff forward from Michael once
we have the entry writing ops indirection, please? It would be nice to
land that before adding the CD support, I think.

> @@ -1102,17 +1111,14 @@ static bool entry_set(struct arm_smmu_device *smmu, ioasid_t sid,
>   * V=0 process. This relies on the IGNORED behavior described in the
>   * specification.
>   */
> -static void arm_smmu_write_ste(struct arm_smmu_master *master, u32 sid,
> -			       struct arm_smmu_ste *entry,
> -			       const struct arm_smmu_ste *target)
> +static void arm_smmu_write_entry(struct arm_smmu_entry_writer *writer,
> +				 __le64 *entry, const __le64 *target)
>  {
> -	unsigned int num_entry_qwords = ARRAY_SIZE(target->data);
> -	struct arm_smmu_device *smmu = master->smmu;
> -	struct arm_smmu_ste unused_update;
> +	__le64 unused_update[NUM_ENTRY_QWORDS];
>  	u8 used_qword_diff;
>  
>  	used_qword_diff =
> -		arm_smmu_entry_qword_diff(entry, target, &unused_update);
> +		arm_smmu_entry_qword_diff(writer, entry, target, unused_update);
>  	if (hweight8(used_qword_diff) == 1) {
>  		/*
>  		 * Only one qword needs its used bits to be changed. This is a

nit: This comment (lost in the diff context) refers to STEs a couple of
times. Please update to e.g. "STE/CD".

Will
Jason Gunthorpe April 9, 2024, 11:55 p.m. UTC | #2
On Tue, Apr 09, 2024 at 01:40:08PM +0100, Will Deacon wrote:
> On Wed, Mar 27, 2024 at 03:07:52PM -0300, Jason Gunthorpe wrote:
> > Prepare to put the CD code into the same mechanism. Add an ops indirection
> > around all the STE specific code and make the worker functions independent
> > of the entry content being processed.
> > 
> > get_used and sync ops are provided to hook the correct code.
> > 
> > Signed-off-by: Michael Shavit <mshavit@google.com>
> > Reviewed-by: Michael Shavit <mshavit@google.com>
> > Tested-by: Nicolin Chen <nicolinc@nvidia.com>
> > Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
> > Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> > ---
> >  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 170 ++++++++++++--------
> >  1 file changed, 102 insertions(+), 68 deletions(-)
> 
> Any chance we can pull the STE testing stuff forward from Michael once
> we have the entry writing ops indirection, please? It would be nice to
> land that before adding the CD support, I think.

Yes, I can. There is a bit more work because the CD testing is still
not finished, but I can probably do that.

How about this, I split part 2 into half and the first half ends at
"iommu/arm-smmu-v3: Build the whole CD in arm_smmu_make_s1_cd()" (it
finishes changing the CD programming to look like the STE). I'll pull
forward the selftest patch into that series. That is another 9 patches
from what you have taken so far.

The second half is all about "building a generic pasid layer".

Those 8 patches have all been looked at now, so if we pick them up
soonish we can more easially focus on the latter patches.

Agree?

> >  	used_qword_diff =
> > -		arm_smmu_entry_qword_diff(entry, target, &unused_update);
> > +		arm_smmu_entry_qword_diff(writer, entry, target, unused_update);
> >  	if (hweight8(used_qword_diff) == 1) {
> >  		/*
> >  		 * Only one qword needs its used bits to be changed. This is a
> 
> nit: This comment (lost in the diff context) refers to STEs a couple of
> times. Please update to e.g. "STE/CD".

Ok, I'll check them

Thanks,
Jason
Will Deacon April 10, 2024, 2:44 p.m. UTC | #3
On Tue, Apr 09, 2024 at 08:55:12PM -0300, Jason Gunthorpe wrote:
> On Tue, Apr 09, 2024 at 01:40:08PM +0100, Will Deacon wrote:
> > On Wed, Mar 27, 2024 at 03:07:52PM -0300, Jason Gunthorpe wrote:
> > > Prepare to put the CD code into the same mechanism. Add an ops indirection
> > > around all the STE specific code and make the worker functions independent
> > > of the entry content being processed.
> > > 
> > > get_used and sync ops are provided to hook the correct code.
> > > 
> > > Signed-off-by: Michael Shavit <mshavit@google.com>
> > > Reviewed-by: Michael Shavit <mshavit@google.com>
> > > Tested-by: Nicolin Chen <nicolinc@nvidia.com>
> > > Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
> > > Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> > > ---
> > >  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 170 ++++++++++++--------
> > >  1 file changed, 102 insertions(+), 68 deletions(-)
> > 
> > Any chance we can pull the STE testing stuff forward from Michael once
> > we have the entry writing ops indirection, please? It would be nice to
> > land that before adding the CD support, I think.
> 
> Yes, I can. There is a bit more work because the CD testing is still
> not finished, but I can probably do that.
> 
> How about this, I split part 2 into half and the first half ends at
> "iommu/arm-smmu-v3: Build the whole CD in arm_smmu_make_s1_cd()" (it
> finishes changing the CD programming to look like the STE). I'll pull
> forward the selftest patch into that series. That is another 9 patches
> from what you have taken so far.
> 
> The second half is all about "building a generic pasid layer".
> 
> Those 8 patches have all been looked at now, so if we pick them up
> soonish we can more easially focus on the latter patches.
> 
> Agree?

Yes, please, that would be really good.

Thanks,

Will
diff mbox series

Patch

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 6f62a38052b504..19fa511cec2c05 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -47,8 +47,20 @@  enum arm_smmu_msi_index {
 	ARM_SMMU_MAX_MSIS,
 };
 
-static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu,
-				      ioasid_t sid);
+struct arm_smmu_entry_writer_ops;
+struct arm_smmu_entry_writer {
+	const struct arm_smmu_entry_writer_ops *ops;
+	struct arm_smmu_master *master;
+};
+
+struct arm_smmu_entry_writer_ops {
+	__le64 v_bit;
+	void (*get_used)(const __le64 *entry, __le64 *used);
+	void (*sync)(struct arm_smmu_entry_writer *writer);
+};
+
+#define NUM_ENTRY_QWORDS 8
+static_assert(sizeof(struct arm_smmu_ste) == NUM_ENTRY_QWORDS * sizeof(u64));
 
 static phys_addr_t arm_smmu_msi_cfg[ARM_SMMU_MAX_MSIS][3] = {
 	[EVTQ_MSI_INDEX] = {
@@ -977,43 +989,42 @@  void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid)
  * would be nice if this was complete according to the spec, but minimally it
  * has to capture the bits this driver uses.
  */
-static void arm_smmu_get_ste_used(const struct arm_smmu_ste *ent,
-				  struct arm_smmu_ste *used_bits)
+static void arm_smmu_get_ste_used(const __le64 *ent, __le64 *used_bits)
 {
-	unsigned int cfg = FIELD_GET(STRTAB_STE_0_CFG, le64_to_cpu(ent->data[0]));
+	unsigned int cfg = FIELD_GET(STRTAB_STE_0_CFG, le64_to_cpu(ent[0]));
 
-	used_bits->data[0] = cpu_to_le64(STRTAB_STE_0_V);
-	if (!(ent->data[0] & cpu_to_le64(STRTAB_STE_0_V)))
+	used_bits[0] = cpu_to_le64(STRTAB_STE_0_V);
+	if (!(ent[0] & cpu_to_le64(STRTAB_STE_0_V)))
 		return;
 
-	used_bits->data[0] |= cpu_to_le64(STRTAB_STE_0_CFG);
+	used_bits[0] |= cpu_to_le64(STRTAB_STE_0_CFG);
 
 	/* S1 translates */
 	if (cfg & BIT(0)) {
-		used_bits->data[0] |= cpu_to_le64(STRTAB_STE_0_S1FMT |
-						  STRTAB_STE_0_S1CTXPTR_MASK |
-						  STRTAB_STE_0_S1CDMAX);
-		used_bits->data[1] |=
+		used_bits[0] |= cpu_to_le64(STRTAB_STE_0_S1FMT |
+					    STRTAB_STE_0_S1CTXPTR_MASK |
+					    STRTAB_STE_0_S1CDMAX);
+		used_bits[1] |=
 			cpu_to_le64(STRTAB_STE_1_S1DSS | STRTAB_STE_1_S1CIR |
 				    STRTAB_STE_1_S1COR | STRTAB_STE_1_S1CSH |
 				    STRTAB_STE_1_S1STALLD | STRTAB_STE_1_STRW |
 				    STRTAB_STE_1_EATS);
-		used_bits->data[2] |= cpu_to_le64(STRTAB_STE_2_S2VMID);
+		used_bits[2] |= cpu_to_le64(STRTAB_STE_2_S2VMID);
 	}
 
 	/* S2 translates */
 	if (cfg & BIT(1)) {
-		used_bits->data[1] |=
+		used_bits[1] |=
 			cpu_to_le64(STRTAB_STE_1_EATS | STRTAB_STE_1_SHCFG);
-		used_bits->data[2] |=
+		used_bits[2] |=
 			cpu_to_le64(STRTAB_STE_2_S2VMID | STRTAB_STE_2_VTCR |
 				    STRTAB_STE_2_S2AA64 | STRTAB_STE_2_S2ENDI |
 				    STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2R);
-		used_bits->data[3] |= cpu_to_le64(STRTAB_STE_3_S2TTB_MASK);
+		used_bits[3] |= cpu_to_le64(STRTAB_STE_3_S2TTB_MASK);
 	}
 
 	if (cfg == STRTAB_STE_0_CFG_BYPASS)
-		used_bits->data[1] |= cpu_to_le64(STRTAB_STE_1_SHCFG);
+		used_bits[1] |= cpu_to_le64(STRTAB_STE_1_SHCFG);
 }
 
 /*
@@ -1022,57 +1033,55 @@  static void arm_smmu_get_ste_used(const struct arm_smmu_ste *ent,
  * unused_update is an intermediate value of entry that has unused bits set to
  * their new values.
  */
-static u8 arm_smmu_entry_qword_diff(const struct arm_smmu_ste *entry,
-				    const struct arm_smmu_ste *target,
-				    struct arm_smmu_ste *unused_update)
+static u8 arm_smmu_entry_qword_diff(struct arm_smmu_entry_writer *writer,
+				    const __le64 *entry, const __le64 *target,
+				    __le64 *unused_update)
 {
-	struct arm_smmu_ste target_used = {};
-	struct arm_smmu_ste cur_used = {};
+	__le64 target_used[NUM_ENTRY_QWORDS] = {};
+	__le64 cur_used[NUM_ENTRY_QWORDS] = {};
 	u8 used_qword_diff = 0;
 	unsigned int i;
 
-	arm_smmu_get_ste_used(entry, &cur_used);
-	arm_smmu_get_ste_used(target, &target_used);
+	writer->ops->get_used(entry, cur_used);
+	writer->ops->get_used(target, target_used);
 
-	for (i = 0; i != ARRAY_SIZE(target_used.data); i++) {
+	for (i = 0; i != NUM_ENTRY_QWORDS; i++) {
 		/*
 		 * Check that masks are up to date, the make functions are not
 		 * allowed to set a bit to 1 if the used function doesn't say it
 		 * is used.
 		 */
-		WARN_ON_ONCE(target->data[i] & ~target_used.data[i]);
+		WARN_ON_ONCE(target[i] & ~target_used[i]);
 
 		/* Bits can change because they are not currently being used */
-		unused_update->data[i] = (entry->data[i] & cur_used.data[i]) |
-					 (target->data[i] & ~cur_used.data[i]);
+		unused_update[i] = (entry[i] & cur_used[i]) |
+				   (target[i] & ~cur_used[i]);
 		/*
 		 * Each bit indicates that a used bit in a qword needs to be
 		 * changed after unused_update is applied.
 		 */
-		if ((unused_update->data[i] & target_used.data[i]) !=
-		    target->data[i])
+		if ((unused_update[i] & target_used[i]) != target[i])
 			used_qword_diff |= 1 << i;
 	}
 	return used_qword_diff;
 }
 
-static bool entry_set(struct arm_smmu_device *smmu, ioasid_t sid,
-		      struct arm_smmu_ste *entry,
-		      const struct arm_smmu_ste *target, unsigned int start,
+static bool entry_set(struct arm_smmu_entry_writer *writer, __le64 *entry,
+		      const __le64 *target, unsigned int start,
 		      unsigned int len)
 {
 	bool changed = false;
 	unsigned int i;
 
 	for (i = start; len != 0; len--, i++) {
-		if (entry->data[i] != target->data[i]) {
-			WRITE_ONCE(entry->data[i], target->data[i]);
+		if (entry[i] != target[i]) {
+			WRITE_ONCE(entry[i], target[i]);
 			changed = true;
 		}
 	}
 
 	if (changed)
-		arm_smmu_sync_ste_for_sid(smmu, sid);
+		writer->ops->sync(writer);
 	return changed;
 }
 
@@ -1102,17 +1111,14 @@  static bool entry_set(struct arm_smmu_device *smmu, ioasid_t sid,
  * V=0 process. This relies on the IGNORED behavior described in the
  * specification.
  */
-static void arm_smmu_write_ste(struct arm_smmu_master *master, u32 sid,
-			       struct arm_smmu_ste *entry,
-			       const struct arm_smmu_ste *target)
+static void arm_smmu_write_entry(struct arm_smmu_entry_writer *writer,
+				 __le64 *entry, const __le64 *target)
 {
-	unsigned int num_entry_qwords = ARRAY_SIZE(target->data);
-	struct arm_smmu_device *smmu = master->smmu;
-	struct arm_smmu_ste unused_update;
+	__le64 unused_update[NUM_ENTRY_QWORDS];
 	u8 used_qword_diff;
 
 	used_qword_diff =
-		arm_smmu_entry_qword_diff(entry, target, &unused_update);
+		arm_smmu_entry_qword_diff(writer, entry, target, unused_update);
 	if (hweight8(used_qword_diff) == 1) {
 		/*
 		 * Only one qword needs its used bits to be changed. This is a
@@ -1128,22 +1134,21 @@  static void arm_smmu_write_ste(struct arm_smmu_master *master, u32 sid,
 		 * writing it in the next step anyways. This can save a sync
 		 * when the only change is in that qword.
 		 */
-		unused_update.data[critical_qword_index] =
-			entry->data[critical_qword_index];
-		entry_set(smmu, sid, entry, &unused_update, 0, num_entry_qwords);
-		entry_set(smmu, sid, entry, target, critical_qword_index, 1);
-		entry_set(smmu, sid, entry, target, 0, num_entry_qwords);
+		unused_update[critical_qword_index] =
+			entry[critical_qword_index];
+		entry_set(writer, entry, unused_update, 0, NUM_ENTRY_QWORDS);
+		entry_set(writer, entry, target, critical_qword_index, 1);
+		entry_set(writer, entry, target, 0, NUM_ENTRY_QWORDS);
 	} else if (used_qword_diff) {
 		/*
 		 * At least two qwords need their inuse bits to be changed. This
 		 * requires a breaking update, zero the V bit, write all qwords
 		 * but 0, then set qword 0
 		 */
-		unused_update.data[0] = entry->data[0] &
-					cpu_to_le64(~STRTAB_STE_0_V);
-		entry_set(smmu, sid, entry, &unused_update, 0, 1);
-		entry_set(smmu, sid, entry, target, 1, num_entry_qwords - 1);
-		entry_set(smmu, sid, entry, target, 0, 1);
+		unused_update[0] = entry[0] & (~writer->ops->v_bit);
+		entry_set(writer, entry, unused_update, 0, 1);
+		entry_set(writer, entry, target, 1, NUM_ENTRY_QWORDS - 1);
+		entry_set(writer, entry, target, 0, 1);
 	} else {
 		/*
 		 * No inuse bit changed. Sanity check that all unused bits are 0
@@ -1151,18 +1156,7 @@  static void arm_smmu_write_ste(struct arm_smmu_master *master, u32 sid,
 		 * compute_qword_diff().
 		 */
 		WARN_ON_ONCE(
-			entry_set(smmu, sid, entry, target, 0, num_entry_qwords));
-	}
-
-	/* It's likely that we'll want to use the new STE soon */
-	if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH)) {
-		struct arm_smmu_cmdq_ent
-			prefetch_cmd = { .opcode = CMDQ_OP_PREFETCH_CFG,
-					 .prefetch = {
-						 .sid = sid,
-					 } };
-
-		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
+			entry_set(writer, entry, target, 0, NUM_ENTRY_QWORDS));
 	}
 }
 
@@ -1435,17 +1429,57 @@  arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc)
 	WRITE_ONCE(*dst, cpu_to_le64(val));
 }
 
-static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
+struct arm_smmu_ste_writer {
+	struct arm_smmu_entry_writer writer;
+	u32 sid;
+};
+
+static void arm_smmu_ste_writer_sync_entry(struct arm_smmu_entry_writer *writer)
 {
+	struct arm_smmu_ste_writer *ste_writer =
+		container_of(writer, struct arm_smmu_ste_writer, writer);
 	struct arm_smmu_cmdq_ent cmd = {
 		.opcode	= CMDQ_OP_CFGI_STE,
 		.cfgi	= {
-			.sid	= sid,
+			.sid	= ste_writer->sid,
 			.leaf	= true,
 		},
 	};
 
-	arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd);
+	arm_smmu_cmdq_issue_cmd_with_sync(writer->master->smmu, &cmd);
+}
+
+static const struct arm_smmu_entry_writer_ops arm_smmu_ste_writer_ops = {
+	.sync = arm_smmu_ste_writer_sync_entry,
+	.get_used = arm_smmu_get_ste_used,
+	.v_bit = cpu_to_le64(STRTAB_STE_0_V),
+};
+
+static void arm_smmu_write_ste(struct arm_smmu_master *master, u32 sid,
+			       struct arm_smmu_ste *ste,
+			       const struct arm_smmu_ste *target)
+{
+	struct arm_smmu_device *smmu = master->smmu;
+	struct arm_smmu_ste_writer ste_writer = {
+		.writer = {
+			.ops = &arm_smmu_ste_writer_ops,
+			.master = master,
+		},
+		.sid = sid,
+	};
+
+	arm_smmu_write_entry(&ste_writer.writer, ste->data, target->data);
+
+	/* It's likely that we'll want to use the new STE soon */
+	if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH)) {
+		struct arm_smmu_cmdq_ent
+			prefetch_cmd = { .opcode = CMDQ_OP_PREFETCH_CFG,
+					 .prefetch = {
+						 .sid = sid,
+					 } };
+
+		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
+	}
 }
 
 static void arm_smmu_make_abort_ste(struct arm_smmu_ste *target)