From: Mostafa Saleh <smostafa@google.com>
To: linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, kvmarm@lists.linux.dev,
iommu@lists.linux.dev
Cc: catalin.marinas@arm.com, will@kernel.org, maz@kernel.org,
oliver.upton@linux.dev, joey.gouly@arm.com,
suzuki.poulose@arm.com, yuzenghui@huawei.com, joro@8bytes.org,
jgg@ziepe.ca, mark.rutland@arm.com, qperret@google.com,
tabba@google.com, vdonnefort@google.com,
sebastianene@google.com, keirf@google.com,
Mostafa Saleh <smostafa@google.com>
Subject: [PATCH v8 05/25] iommu/arm-smmu-v3: Move hitless machinery to common code
Date: Tue, 22 Sep 2026 13:12:38 +0000 [thread overview]
Message-ID: <20260922131259.2975334-6-smostafa@google.com> (raw)
In-Reply-To: <20260922131259.2975334-1-smostafa@google.com>
Move the hitless STE functions to the common file so it can be
reused by the hypervisor.
No functional change.
Signed-off-by: Mostafa Saleh <smostafa@google.com>
---
.../arm/arm-smmu-v3/arm-smmu-v3-common-lib.c | 240 +++++++++++++++++
.../arm/arm-smmu-v3/arm-smmu-v3-common-lib.h | 6 +
.../iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c | 1 +
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 242 ------------------
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 7 +-
5 files changed, 249 insertions(+), 247 deletions(-)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common-lib.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common-lib.c
index a341974e7aaf..39b3cde9f5d2 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common-lib.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common-lib.c
@@ -4,6 +4,8 @@
* Arm SMMUv3 driver functions shared with hypervisor.
*/
+#include <kunit/visibility.h>
+
#include "arm-smmu-v3.h"
#include "arm-smmu-v3-common-lib.h"
@@ -174,3 +176,241 @@ u32 arm_smmu_idr5_probe(ARM_SMMU_OBJ *smmu)
return reg;
}
+
+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[0]));
+
+ used_bits[0] = cpu_to_le64(STRTAB_STE_0_V);
+ if (!(ent[0] & cpu_to_le64(STRTAB_STE_0_V)))
+ return;
+
+ used_bits[0] |= cpu_to_le64(STRTAB_STE_0_CFG);
+
+ /* S1 translates */
+ if (cfg & BIT(0)) {
+ 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 | STRTAB_STE_1_MEV);
+ used_bits[2] |= cpu_to_le64(STRTAB_STE_2_S2VMID);
+
+ /*
+ * See 13.5 Summary of attribute/permission configuration fields
+ * for the SHCFG behavior.
+ */
+ if (FIELD_GET(STRTAB_STE_1_S1DSS, le64_to_cpu(ent[1])) ==
+ STRTAB_STE_1_S1DSS_BYPASS)
+ used_bits[1] |= cpu_to_le64(STRTAB_STE_1_SHCFG);
+ }
+
+ /* S2 translates */
+ if (cfg & BIT(1)) {
+ used_bits[1] |=
+ cpu_to_le64(STRTAB_STE_1_S2FWB | STRTAB_STE_1_EATS |
+ STRTAB_STE_1_SHCFG | STRTAB_STE_1_MEV);
+ 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_S2S |
+ STRTAB_STE_2_S2R);
+ used_bits[3] |= cpu_to_le64(STRTAB_STE_3_S2TTB_MASK);
+ }
+
+ if (cfg == STRTAB_STE_0_CFG_BYPASS)
+ used_bits[1] |= cpu_to_le64(STRTAB_STE_1_SHCFG);
+}
+EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_used);
+
+void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target,
+ __le64 *safe_bits)
+{
+ const u64 eats_s1chk =
+ FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_S1CHK);
+ const u64 eats_trans =
+ FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_TRANS);
+
+ /*
+ * When an STE changes EATS_TRANS, the sequencing code in the attach
+ * logic already will have the PCI cap for ATS disabled. Thus at this
+ * moment we can expect that the device will not generate ATS queries
+ * and so we don't care about the sequencing of EATS. The purpose of
+ * EATS_TRANS is to protect the system from hostile untrusted devices
+ * that issue ATS when the PCI config space is disabled. However, if
+ * EATS_TRANS is being changed, then we must have already trusted the
+ * device as the EATS_TRANS security block is being disabled.
+ *
+ * Note: now the EATS_TRANS update is moved to the first entry_set().
+ * Changing S2S and EATS might transiently result in S2S=1 and EATS=1
+ * which is a bad STE (see "5.2 Stream Table Entry"). In such a case,
+ * we can't do a hitless update. Also, it should not be added to the
+ * safe bits with STRTAB_STE_1_EATS_S1CHK, because EATS=0b11 would be
+ * effectively an errant 0b00 configuration.
+ */
+ if (!((cur[1] | target[1]) & cpu_to_le64(eats_s1chk)) &&
+ !((cur[2] | target[2]) & cpu_to_le64(STRTAB_STE_2_S2S)))
+ safe_bits[1] |= cpu_to_le64(eats_trans);
+
+ /*
+ * MEV does not meaningfully impact the operation of the HW, it only
+ * changes how many fault events are generated, thus we can relax it
+ * when computing the ordering. The spec notes the device can act like
+ * MEV=1 anyhow:
+ *
+ * Note: Software must expect, and be able to deal with, coalesced
+ * fault records even when MEV == 0.
+ */
+ safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_MEV);
+}
+EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_update_safe);
+
+/*
+ * Figure out if we can do a hitless update of entry to become target. Returns a
+ * bit mask where 1 indicates that qword needs to be set disruptively.
+ * unused_update is an intermediate value of entry that has unused bits set to
+ * their new values.
+ */
+static u8 arm_smmu_entry_qword_diff(struct arm_smmu_entry_writer *writer,
+ const __le64 *entry, const __le64 *target,
+ __le64 *unused_update)
+{
+ __le64 target_used[NUM_ENTRY_QWORDS] = {};
+ __le64 cur_used[NUM_ENTRY_QWORDS] = {};
+ __le64 safe[NUM_ENTRY_QWORDS] = {};
+ u8 used_qword_diff = 0;
+ unsigned int i;
+
+ writer->ops->get_used(entry, cur_used);
+ writer->ops->get_used(target, target_used);
+ if (writer->ops->get_update_safe)
+ writer->ops->get_update_safe(entry, target, safe);
+
+ for (i = 0; i != NUM_ENTRY_QWORDS; i++) {
+ /*
+ * Safe is only used for bits that are used by both entries,
+ * otherwise it is sequenced according to the unused entry.
+ */
+ safe[i] &= target_used[i] & cur_used[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[i] & ~target_used[i]);
+
+ /* Bits can change because they are not currently being used */
+ cur_used[i] &= ~safe[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[i] & target_used[i]) != target[i])
+ used_qword_diff |= 1 << i;
+ }
+ return used_qword_diff;
+}
+
+static void 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[i] != target[i]) {
+ WRITE_ONCE(entry[i], target[i]);
+ changed = true;
+ }
+ }
+
+ if (changed)
+ writer->ops->sync(writer);
+}
+
+/*
+ * Update the STE/CD to the target configuration. The transition from the
+ * current entry to the target entry takes place over multiple steps that
+ * attempts to make the transition hitless if possible. This function takes care
+ * not to create a situation where the HW can perceive a corrupted entry. HW is
+ * only required to have a 64 bit atomicity with stores from the CPU, while
+ * entries are many 64 bit values big.
+ *
+ * The difference between the current value and the target value is analyzed to
+ * determine which of three updates are required - disruptive, hitless or no
+ * change.
+ *
+ * In the most general disruptive case we can make any update in three steps:
+ * - Disrupting the entry (V=0)
+ * - Fill now unused qwords, execpt qword 0 which contains V
+ * - Make qword 0 have the final value and valid (V=1) with a single 64
+ * bit store
+ *
+ * However this disrupts the HW while it is happening. There are several
+ * interesting cases where a STE/CD can be updated without disturbing the HW
+ * because only a small number of bits are changing (S1DSS, CONFIG, etc) or
+ * because the used bits don't intersect. We can detect this by calculating how
+ * many 64 bit values need update after adjusting the unused bits and skip the
+ * V=0 process. This relies on the IGNORED behavior described in the
+ * specification.
+ */
+void arm_smmu_write_entry(struct arm_smmu_entry_writer *writer, __le64 *entry,
+ const __le64 *target)
+{
+ __le64 unused_update[NUM_ENTRY_QWORDS];
+ u8 used_qword_diff;
+
+ /*
+ * Many of the entry structures have pointers to other structures that
+ * need to have their updates be visible before any writes of the entry
+ * happen.
+ */
+ dma_wmb();
+
+ used_qword_diff =
+ 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
+ * hitless update, update all bits the current STE/CD is
+ * ignoring to their new values, then update a single "critical
+ * qword" to change the STE/CD and finally 0 out any bits that
+ * are now unused in the target configuration.
+ */
+ unsigned int critical_qword_index = ffs(used_qword_diff) - 1;
+
+ /*
+ * Skip writing unused bits in the critical qword since we'll be
+ * writing it in the next step anyways. This can save a sync
+ * when the only change is in that qword.
+ */
+ 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[0] = 0;
+ 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, though safe bits may have changed.
+ */
+ entry_set(writer, entry, target, 0, NUM_ENTRY_QWORDS);
+ }
+}
+EXPORT_SYMBOL_IF_KUNIT(arm_smmu_write_entry);
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common-lib.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common-lib.h
index e736b6a8c78c..9a7064c8e879 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common-lib.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-common-lib.h
@@ -28,4 +28,10 @@ u32 arm_smmu_idr0_probe(ARM_SMMU_OBJ *smmu);
void arm_smmu_idr3_probe(ARM_SMMU_OBJ *smmu);
u32 arm_smmu_idr5_probe(ARM_SMMU_OBJ *smmu);
+void arm_smmu_get_ste_used(const __le64 *ent, __le64 *used_bits);
+void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target,
+ __le64 *safe_bits);
+void arm_smmu_write_entry(struct arm_smmu_entry_writer *writer, __le64 *cur,
+ const __le64 *target);
+
#endif /* __ARM_SMMU_V3_COMMON_LIB_H */
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c
index add671363c82..ea9c85d2c7f0 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c
@@ -6,6 +6,7 @@
#include <linux/io-pgtable.h>
#include "arm-smmu-v3.h"
+#include "arm-smmu-v3-common-lib.h"
struct arm_smmu_test_writer {
struct arm_smmu_entry_writer writer;
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 c4c652431ee0..2043c6dc1bdf 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -59,10 +59,8 @@ enum arm_smmu_msi_index {
ARM_SMMU_MAX_MSIS,
};
-#define NUM_ENTRY_QWORDS 8
static_assert(sizeof(struct arm_smmu_ste) == NUM_ENTRY_QWORDS * sizeof(u64));
static_assert(sizeof(struct arm_smmu_cd) == NUM_ENTRY_QWORDS * sizeof(u64));
-
static phys_addr_t arm_smmu_msi_cfg[ARM_SMMU_MAX_MSIS][3] = {
[EVTQ_MSI_INDEX] = {
ARM_SMMU_EVTQ_IRQ_CFG0,
@@ -1205,246 +1203,6 @@ EXPORT_SYMBOL_IF_KUNIT(arm_smmu_invs_purge);
* would be nice if this was complete according to the spec, but minimally it
* has to capture the bits this driver uses.
*/
-VISIBLE_IF_KUNIT
-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[0]));
-
- used_bits[0] = cpu_to_le64(STRTAB_STE_0_V);
- if (!(ent[0] & cpu_to_le64(STRTAB_STE_0_V)))
- return;
-
- used_bits[0] |= cpu_to_le64(STRTAB_STE_0_CFG);
-
- /* S1 translates */
- if (cfg & BIT(0)) {
- 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 | STRTAB_STE_1_MEV);
- used_bits[2] |= cpu_to_le64(STRTAB_STE_2_S2VMID);
-
- /*
- * See 13.5 Summary of attribute/permission configuration fields
- * for the SHCFG behavior.
- */
- if (FIELD_GET(STRTAB_STE_1_S1DSS, le64_to_cpu(ent[1])) ==
- STRTAB_STE_1_S1DSS_BYPASS)
- used_bits[1] |= cpu_to_le64(STRTAB_STE_1_SHCFG);
- }
-
- /* S2 translates */
- if (cfg & BIT(1)) {
- used_bits[1] |=
- cpu_to_le64(STRTAB_STE_1_S2FWB | STRTAB_STE_1_EATS |
- STRTAB_STE_1_SHCFG | STRTAB_STE_1_MEV);
- 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_S2S |
- STRTAB_STE_2_S2R);
- used_bits[3] |= cpu_to_le64(STRTAB_STE_3_S2TTB_MASK);
- }
-
- if (cfg == STRTAB_STE_0_CFG_BYPASS)
- used_bits[1] |= cpu_to_le64(STRTAB_STE_1_SHCFG);
-}
-EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_used);
-
-VISIBLE_IF_KUNIT
-void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target,
- __le64 *safe_bits)
-{
- const u64 eats_s1chk =
- FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_S1CHK);
- const u64 eats_trans =
- FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_TRANS);
-
- /*
- * When an STE changes EATS_TRANS, the sequencing code in the attach
- * logic already will have the PCI cap for ATS disabled. Thus at this
- * moment we can expect that the device will not generate ATS queries
- * and so we don't care about the sequencing of EATS. The purpose of
- * EATS_TRANS is to protect the system from hostile untrusted devices
- * that issue ATS when the PCI config space is disabled. However, if
- * EATS_TRANS is being changed, then we must have already trusted the
- * device as the EATS_TRANS security block is being disabled.
- *
- * Note: now the EATS_TRANS update is moved to the first entry_set().
- * Changing S2S and EATS might transiently result in S2S=1 and EATS=1
- * which is a bad STE (see "5.2 Stream Table Entry"). In such a case,
- * we can't do a hitless update. Also, it should not be added to the
- * safe bits with STRTAB_STE_1_EATS_S1CHK, because EATS=0b11 would be
- * effectively an errant 0b00 configuration.
- */
- if (!((cur[1] | target[1]) & cpu_to_le64(eats_s1chk)) &&
- !((cur[2] | target[2]) & cpu_to_le64(STRTAB_STE_2_S2S)))
- safe_bits[1] |= cpu_to_le64(eats_trans);
-
- /*
- * MEV does not meaningfully impact the operation of the HW, it only
- * changes how many fault events are generated, thus we can relax it
- * when computing the ordering. The spec notes the device can act like
- * MEV=1 anyhow:
- *
- * Note: Software must expect, and be able to deal with, coalesced
- * fault records even when MEV == 0.
- */
- safe_bits[1] |= cpu_to_le64(STRTAB_STE_1_MEV);
-}
-EXPORT_SYMBOL_IF_KUNIT(arm_smmu_get_ste_update_safe);
-
-/*
- * Figure out if we can do a hitless update of entry to become target. Returns a
- * bit mask where 1 indicates that qword needs to be set disruptively.
- * unused_update is an intermediate value of entry that has unused bits set to
- * their new values.
- */
-static u8 arm_smmu_entry_qword_diff(struct arm_smmu_entry_writer *writer,
- const __le64 *entry, const __le64 *target,
- __le64 *unused_update)
-{
- __le64 target_used[NUM_ENTRY_QWORDS] = {};
- __le64 cur_used[NUM_ENTRY_QWORDS] = {};
- __le64 safe[NUM_ENTRY_QWORDS] = {};
- u8 used_qword_diff = 0;
- unsigned int i;
-
- writer->ops->get_used(entry, cur_used);
- writer->ops->get_used(target, target_used);
- if (writer->ops->get_update_safe)
- writer->ops->get_update_safe(entry, target, safe);
-
- for (i = 0; i != NUM_ENTRY_QWORDS; i++) {
- /*
- * Safe is only used for bits that are used by both entries,
- * otherwise it is sequenced according to the unused entry.
- */
- safe[i] &= target_used[i] & cur_used[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[i] & ~target_used[i]);
-
- /* Bits can change because they are not currently being used */
- cur_used[i] &= ~safe[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[i] & target_used[i]) != target[i])
- used_qword_diff |= 1 << i;
- }
- return used_qword_diff;
-}
-
-static void 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[i] != target[i]) {
- WRITE_ONCE(entry[i], target[i]);
- changed = true;
- }
- }
-
- if (changed)
- writer->ops->sync(writer);
-}
-
-/*
- * Update the STE/CD to the target configuration. The transition from the
- * current entry to the target entry takes place over multiple steps that
- * attempts to make the transition hitless if possible. This function takes care
- * not to create a situation where the HW can perceive a corrupted entry. HW is
- * only required to have a 64 bit atomicity with stores from the CPU, while
- * entries are many 64 bit values big.
- *
- * The difference between the current value and the target value is analyzed to
- * determine which of three updates are required - disruptive, hitless or no
- * change.
- *
- * In the most general disruptive case we can make any update in three steps:
- * - Disrupting the entry (V=0)
- * - Fill now unused qwords, execpt qword 0 which contains V
- * - Make qword 0 have the final value and valid (V=1) with a single 64
- * bit store
- *
- * However this disrupts the HW while it is happening. There are several
- * interesting cases where a STE/CD can be updated without disturbing the HW
- * because only a small number of bits are changing (S1DSS, CONFIG, etc) or
- * because the used bits don't intersect. We can detect this by calculating how
- * many 64 bit values need update after adjusting the unused bits and skip the
- * V=0 process. This relies on the IGNORED behavior described in the
- * specification.
- */
-VISIBLE_IF_KUNIT
-void arm_smmu_write_entry(struct arm_smmu_entry_writer *writer, __le64 *entry,
- const __le64 *target)
-{
- __le64 unused_update[NUM_ENTRY_QWORDS];
- u8 used_qword_diff;
-
- /*
- * Many of the entry structures have pointers to other structures that
- * need to have their updates be visible before any writes of the entry
- * happen.
- */
- dma_wmb();
-
- used_qword_diff =
- 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
- * hitless update, update all bits the current STE/CD is
- * ignoring to their new values, then update a single "critical
- * qword" to change the STE/CD and finally 0 out any bits that
- * are now unused in the target configuration.
- */
- unsigned int critical_qword_index = ffs(used_qword_diff) - 1;
-
- /*
- * Skip writing unused bits in the critical qword since we'll be
- * writing it in the next step anyways. This can save a sync
- * when the only change is in that qword.
- */
- 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[0] = 0;
- 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, though safe bits may have changed.
- */
- entry_set(writer, entry, target, 0, NUM_ENTRY_QWORDS);
- }
-}
-EXPORT_SYMBOL_IF_KUNIT(arm_smmu_write_entry);
static void arm_smmu_sync_cd(struct arm_smmu_master *master,
int ssid, bool leaf)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index d5963a01452f..28efa733e796 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -1088,11 +1088,6 @@ void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target,
bool ats_enabled);
#if IS_ENABLED(CONFIG_KUNIT)
-void arm_smmu_get_ste_used(const __le64 *ent, __le64 *used_bits);
-void arm_smmu_get_ste_update_safe(const __le64 *cur, const __le64 *target,
- __le64 *safe_bits);
-void arm_smmu_write_entry(struct arm_smmu_entry_writer *writer, __le64 *cur,
- const __le64 *target);
void arm_smmu_get_cd_used(const __le64 *ent, __le64 *used_bits);
void arm_smmu_make_bypass_ste(struct arm_smmu_device *smmu,
struct arm_smmu_ste *target);
@@ -1321,6 +1316,8 @@ static inline u64 arm_smmu_tlb_inv_range_enc(u8 num, u8 scale)
FIELD_PREP(CMDQ_TLBI_0_SCALE, scale & 0x1f);
}
+#define NUM_ENTRY_QWORDS 8
+
#ifdef CONFIG_ARM_SMMU_V3_SVA
bool arm_smmu_sva_supported(struct arm_smmu_device *smmu);
void arm_smmu_sva_notifier_synchronize(void);
--
2.55.0.1082.g2b9226bbc0-goog
next prev parent reply other threads:[~2026-09-22 13:13 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-22 13:12 [PATCH v8 00/25] KVM: arm64: SMMUv3 driver for pKVM (trap and emulate) Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 01/25] KVM: arm64: Donate MMIO to the hypervisor Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 02/25] iommu/arm-smmu-v3: Move Queue and STE functions to header Mostafa Saleh
2026-09-22 18:23 ` Nicolin Chen
2026-09-22 13:12 ` [PATCH v8 03/25] iommu/arm-smmu-v3: Introduce RangeInval encoding helpers Mostafa Saleh
2026-09-22 18:45 ` Nicolin Chen
2026-09-22 13:12 ` [PATCH v8 04/25] iommu/arm-smmu-v3: Move IDR parsing to common functions Mostafa Saleh
2026-09-22 19:45 ` Nicolin Chen
2026-09-22 21:48 ` Jason Gunthorpe
2026-09-22 13:12 ` Mostafa Saleh [this message]
2026-09-22 19:59 ` [PATCH v8 05/25] iommu/arm-smmu-v3: Move hitless machinery to common code Nicolin Chen
2026-09-22 13:12 ` [PATCH v8 06/25] KVM: arm64: iommu: Introduce IOMMU driver infrastructure Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 07/25] KVM: arm64: iommu: Shadow host stage-2 page table Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 08/25] KVM: arm64: iommu: Add memory pool Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 09/25] KVM: arm64: iommu: Support DABT for IOMMU Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 10/25] iommu/arm-smmu-v3-kvm: Add SMMUv3 driver Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 11/25] iommu/arm-smmu-v3-kvm: Add the kernel driver Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 12/25] iommu/arm-smmu-v3-kvm: Probe SMMU HW Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 13/25] iommu/arm-smmu-v3-kvm: Add MMIO emulation Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 14/25] iommu/arm-smmu-v3-kvm: Shadow the command queue Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 15/25] iommu/arm-smmu-v3-kvm: Add CMDQ functions Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 16/25] iommu/arm-smmu-v3-kvm: Emulate CMDQ for host Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 17/25] iommu/arm-smmu-v3-kvm: Shadow stream table Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 18/25] iommu/arm-smmu-v3-kvm: Shadow STEs Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 19/25] iommu/arm-smmu-v3-kvm: Share other queues Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 20/25] iommu/arm-smmu-v3-kvm: Emulate GBPA Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 21/25] iommu/io-pgtable-arm: Support io-pgtable-arm in the hypervisor Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 22/25] iommu/arm-smmu-v3-kvm: Shadow the CPU stage-2 page table Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 23/25] iommu/arm-smmu-v3-kvm: Invalidate the SMMU TLBs Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 24/25] iommu/arm-smmu-v3-kvm: Enable nesting Mostafa Saleh
2026-09-22 13:12 ` [PATCH v8 25/25] KVM: arm64: Add documentation for pKVM DMA isolation Mostafa Saleh
2026-09-22 18:07 ` [PATCH v8 00/25] KVM: arm64: SMMUv3 driver for pKVM (trap and emulate) Nicolin Chen
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=20260922131259.2975334-6-smostafa@google.com \
--to=smostafa@google.com \
--cc=catalin.marinas@arm.com \
--cc=iommu@lists.linux.dev \
--cc=jgg@ziepe.ca \
--cc=joey.gouly@arm.com \
--cc=joro@8bytes.org \
--cc=keirf@google.com \
--cc=kvmarm@lists.linux.dev \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=maz@kernel.org \
--cc=oliver.upton@linux.dev \
--cc=qperret@google.com \
--cc=sebastianene@google.com \
--cc=suzuki.poulose@arm.com \
--cc=tabba@google.com \
--cc=vdonnefort@google.com \
--cc=will@kernel.org \
--cc=yuzenghui@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
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
all inboxes | Powered by JetHome®