diff options
| -rw-r--r-- | Documentation/devicetree/bindings/iommu/qcom,tbu.yaml | 69 | ||||
| -rw-r--r-- | drivers/iommu/Kconfig | 25 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu-v3/Makefile | 1 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 167 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c | 465 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 551 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 60 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c | 496 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 8 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h | 2 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu.c | 20 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu.h | 3 |
12 files changed, 1526 insertions, 341 deletions
diff --git a/Documentation/devicetree/bindings/iommu/qcom,tbu.yaml b/Documentation/devicetree/bindings/iommu/qcom,tbu.yaml new file mode 100644 index 000000000000..82dfe935573e --- /dev/null +++ b/Documentation/devicetree/bindings/iommu/qcom,tbu.yaml @@ -0,0 +1,69 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/iommu/qcom,tbu.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm TBU (Translation Buffer Unit) + +maintainers: + - Georgi Djakov <quic_c_gdjako@quicinc.com> + +description: + The Qualcomm SMMU500 implementation consists of TCU and TBU. The TBU contains + a Translation Lookaside Buffer (TLB) that caches page tables. TBUs provides + debug features to trace and trigger debug transactions. There are multiple TBU + instances with each client core. + +properties: + compatible: + enum: + - qcom,sc7280-tbu + - qcom,sdm845-tbu + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + interconnects: + maxItems: 1 + + power-domains: + maxItems: 1 + + qcom,stream-id-range: + description: | + Phandle of a SMMU device and Stream ID range (address and size) that + is assigned by the TBU + $ref: /schemas/types.yaml#/definitions/phandle-array + items: + - items: + - description: phandle of a smmu node + - description: stream id base address + - description: stream id size + +required: + - compatible + - reg + - qcom,stream-id-range + +additionalProperties: false + +examples: + - | + #include <dt-bindings/clock/qcom,gcc-sdm845.h> + #include <dt-bindings/interconnect/qcom,icc.h> + #include <dt-bindings/interconnect/qcom,sdm845.h> + + tbu@150e1000 { + compatible = "qcom,sdm845-tbu"; + reg = <0x150e1000 0x1000>; + clocks = <&gcc GCC_AGGRE_NOC_PCIE_TBU_CLK>; + interconnects = <&system_noc MASTER_GNOC_SNOC QCOM_ICC_TAG_ACTIVE_ONLY + &config_noc SLAVE_IMEM_CFG QCOM_ICC_TAG_ACTIVE_ONLY>; + power-domains = <&gcc HLOS1_VOTE_AGGRE_NOC_MMU_PCIE_TBU_GDSC>; + qcom,stream-id-range = <&apps_smmu 0x1c00 0x400>; + }; +... diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 0af39bbbe3a3..66325210c8c9 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -376,13 +376,17 @@ config ARM_SMMU_QCOM config ARM_SMMU_QCOM_DEBUG bool "ARM SMMU QCOM implementation defined debug support" - depends on ARM_SMMU_QCOM + depends on ARM_SMMU_QCOM=y help Support for implementation specific debug features in ARM SMMU - hardware found in QTI platforms. + hardware found in QTI platforms. This include support for + the Translation Buffer Units (TBU) that can be used to obtain + additional information when debugging memory management issues + like context faults. - Say Y here to enable debug for issues such as TLB sync timeouts - which requires implementation defined register dumps. + Say Y here to enable debug for issues such as context faults + or TLB sync timeouts which requires implementation defined + register dumps. config ARM_SMMU_V3 tristate "ARM Ltd. System MMU Version 3 (SMMUv3) Support" @@ -397,9 +401,9 @@ config ARM_SMMU_V3 Say Y here if your system includes an IOMMU device implementing the ARM SMMUv3 architecture. +if ARM_SMMU_V3 config ARM_SMMU_V3_SVA bool "Shared Virtual Addressing support for the ARM SMMUv3" - depends on ARM_SMMU_V3 select IOMMU_SVA select IOMMU_IOPF select MMU_NOTIFIER @@ -410,6 +414,17 @@ config ARM_SMMU_V3_SVA Say Y here if your system supports SVA extensions such as PCIe PASID and PRI. +config ARM_SMMU_V3_KUNIT_TEST + bool "KUnit tests for arm-smmu-v3 driver" if !KUNIT_ALL_TESTS + depends on KUNIT + depends on ARM_SMMU_V3_SVA + default KUNIT_ALL_TESTS + help + Enable this option to unit-test arm-smmu-v3 driver functions. + + If unsure, say N. +endif + config S390_IOMMU def_bool y if S390 && PCI depends on S390 && PCI diff --git a/drivers/iommu/arm/arm-smmu-v3/Makefile b/drivers/iommu/arm/arm-smmu-v3/Makefile index 54feb1ecccad..0b97054b3929 100644 --- a/drivers/iommu/arm/arm-smmu-v3/Makefile +++ b/drivers/iommu/arm/arm-smmu-v3/Makefile @@ -2,4 +2,5 @@ obj-$(CONFIG_ARM_SMMU_V3) += arm_smmu_v3.o arm_smmu_v3-objs-y += arm-smmu-v3.o arm_smmu_v3-objs-$(CONFIG_ARM_SMMU_V3_SVA) += arm-smmu-v3-sva.o +arm_smmu_v3-objs-$(CONFIG_ARM_SMMU_V3_KUNIT_TEST) += arm-smmu-v3-test.o arm_smmu_v3-objs := $(arm_smmu_v3-objs-y) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index 2cd433a9c8a0..34a977a0767d 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -8,6 +8,7 @@ #include <linux/mmu_notifier.h> #include <linux/sched/mm.h> #include <linux/slab.h> +#include <kunit/visibility.h> #include "arm-smmu-v3.h" #include "../../io-pgtable-arm.h" @@ -34,21 +35,25 @@ struct arm_smmu_bond { static DEFINE_MUTEX(sva_lock); -/* - * Write the CD to the CD tables for all masters that this domain is attached - * to. Note that this is only used to update existing CD entries in the target - * CD table, for which it's assumed that arm_smmu_write_ctx_desc can't fail. - */ -static void arm_smmu_update_ctx_desc_devices(struct arm_smmu_domain *smmu_domain, - int ssid, - struct arm_smmu_ctx_desc *cd) +static void +arm_smmu_update_s1_domain_cd_entry(struct arm_smmu_domain *smmu_domain) { struct arm_smmu_master *master; + struct arm_smmu_cd target_cd; unsigned long flags; spin_lock_irqsave(&smmu_domain->devices_lock, flags); list_for_each_entry(master, &smmu_domain->devices, domain_head) { - arm_smmu_write_ctx_desc(master, ssid, cd); + struct arm_smmu_cd *cdptr; + + /* S1 domains only support RID attachment right now */ + cdptr = arm_smmu_get_cd_ptr(master, IOMMU_NO_PASID); + if (WARN_ON(!cdptr)) + continue; + + arm_smmu_make_s1_cd(&target_cd, master, smmu_domain); + arm_smmu_write_cd_entry(master, IOMMU_NO_PASID, cdptr, + &target_cd); } spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); } @@ -96,7 +101,7 @@ arm_smmu_share_asid(struct mm_struct *mm, u16 asid) * be some overlap between use of both ASIDs, until we invalidate the * TLB. */ - arm_smmu_update_ctx_desc_devices(smmu_domain, IOMMU_NO_PASID, cd); + arm_smmu_update_s1_domain_cd_entry(smmu_domain); /* Invalidate TLB entries previously associated with that context */ arm_smmu_tlb_inv_asid(smmu, asid); @@ -105,11 +110,86 @@ arm_smmu_share_asid(struct mm_struct *mm, u16 asid) return NULL; } +static u64 page_size_to_cd(void) +{ + static_assert(PAGE_SIZE == SZ_4K || PAGE_SIZE == SZ_16K || + PAGE_SIZE == SZ_64K); + if (PAGE_SIZE == SZ_64K) + return ARM_LPAE_TCR_TG0_64K; + if (PAGE_SIZE == SZ_16K) + return ARM_LPAE_TCR_TG0_16K; + return ARM_LPAE_TCR_TG0_4K; +} + +VISIBLE_IF_KUNIT +void arm_smmu_make_sva_cd(struct arm_smmu_cd *target, + struct arm_smmu_master *master, struct mm_struct *mm, + u16 asid) +{ + u64 par; + + memset(target, 0, sizeof(*target)); + + par = cpuid_feature_extract_unsigned_field( + read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1), + ID_AA64MMFR0_EL1_PARANGE_SHIFT); + + target->data[0] = cpu_to_le64( + CTXDESC_CD_0_TCR_EPD1 | +#ifdef __BIG_ENDIAN + CTXDESC_CD_0_ENDI | +#endif + CTXDESC_CD_0_V | + FIELD_PREP(CTXDESC_CD_0_TCR_IPS, par) | + CTXDESC_CD_0_AA64 | + (master->stall_enabled ? CTXDESC_CD_0_S : 0) | + CTXDESC_CD_0_R | + CTXDESC_CD_0_A | + CTXDESC_CD_0_ASET | + FIELD_PREP(CTXDESC_CD_0_ASID, asid)); + + /* + * If no MM is passed then this creates a SVA entry that faults + * everything. arm_smmu_write_cd_entry() can hitlessly go between these + * two entries types since TTB0 is ignored by HW when EPD0 is set. + */ + if (mm) { + target->data[0] |= cpu_to_le64( + FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, + 64ULL - vabits_actual) | + FIELD_PREP(CTXDESC_CD_0_TCR_TG0, page_size_to_cd()) | + FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, + ARM_LPAE_TCR_RGN_WBWA) | + FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, + ARM_LPAE_TCR_RGN_WBWA) | + FIELD_PREP(CTXDESC_CD_0_TCR_SH0, ARM_LPAE_TCR_SH_IS)); + + target->data[1] = cpu_to_le64(virt_to_phys(mm->pgd) & + CTXDESC_CD_1_TTB0_MASK); + } else { + target->data[0] |= cpu_to_le64(CTXDESC_CD_0_TCR_EPD0); + + /* + * Disable stall and immediately generate an abort if stall + * disable is permitted. This speeds up cleanup for an unclean + * exit if the device is still doing a lot of DMA. + */ + if (!(master->smmu->features & ARM_SMMU_FEAT_STALL_FORCE)) + target->data[0] &= + cpu_to_le64(~(CTXDESC_CD_0_S | CTXDESC_CD_0_R)); + } + + /* + * MAIR value is pretty much constant and global, so we can just get it + * from the current CPU register + */ + target->data[3] = cpu_to_le64(read_sysreg(mair_el1)); +} + static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm) { u16 asid; int err = 0; - u64 tcr, par, reg; struct arm_smmu_ctx_desc *cd; struct arm_smmu_ctx_desc *ret = NULL; @@ -143,39 +223,6 @@ static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm) if (err) goto out_free_asid; - tcr = FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, 64ULL - vabits_actual) | - FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, ARM_LPAE_TCR_RGN_WBWA) | - FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, ARM_LPAE_TCR_RGN_WBWA) | - FIELD_PREP(CTXDESC_CD_0_TCR_SH0, ARM_LPAE_TCR_SH_IS) | - CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64; - - switch (PAGE_SIZE) { - case SZ_4K: - tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_4K); - break; - case SZ_16K: - tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_16K); - break; - case SZ_64K: - tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_64K); - break; - default: - WARN_ON(1); - err = -EINVAL; - goto out_free_asid; - } - - reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); - par = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_EL1_PARANGE_SHIFT); - tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_IPS, par); - - cd->ttbr = virt_to_phys(mm->pgd); - cd->tcr = tcr; - /* - * MAIR value is pretty much constant and global, so we can just get it - * from the current CPU register - */ - cd->mair = read_sysreg(mair_el1); cd->asid = asid; cd->mm = mm; @@ -253,6 +300,8 @@ static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn); struct arm_smmu_domain *smmu_domain = smmu_mn->domain; + struct arm_smmu_master *master; + unsigned long flags; mutex_lock(&sva_lock); if (smmu_mn->cleared) { @@ -264,8 +313,19 @@ static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) * DMA may still be running. Keep the cd valid to avoid C_BAD_CD events, * but disable translation. */ - arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm), - &quiet_cd); + spin_lock_irqsave(&smmu_domain->devices_lock, flags); + list_for_each_entry(master, &smmu_domain->devices, domain_head) { + struct arm_smmu_cd target; + struct arm_smmu_cd *cdptr; + + cdptr = arm_smmu_get_cd_ptr(master, mm_get_enqcmd_pasid(mm)); + if (WARN_ON(!cdptr)) + continue; + arm_smmu_make_sva_cd(&target, master, NULL, smmu_mn->cd->asid); + arm_smmu_write_cd_entry(master, mm_get_enqcmd_pasid(mm), cdptr, + &target); + } + spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_mn->cd->asid); arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0, 0); @@ -360,6 +420,8 @@ static int __arm_smmu_sva_bind(struct device *dev, ioasid_t pasid, struct mm_struct *mm) { int ret; + struct arm_smmu_cd target; + struct arm_smmu_cd *cdptr; struct arm_smmu_bond *bond; struct arm_smmu_master *master = dev_iommu_priv_get(dev); struct iommu_domain *domain = iommu_get_domain_for_dev(dev); @@ -386,9 +448,13 @@ static int __arm_smmu_sva_bind(struct device *dev, ioasid_t pasid, goto err_free_bond; } - ret = arm_smmu_write_ctx_desc(master, pasid, bond->smmu_mn->cd); - if (ret) + cdptr = arm_smmu_alloc_cd_ptr(master, mm_get_enqcmd_pasid(mm)); + if (!cdptr) { + ret = -ENOMEM; goto err_put_notifier; + } + arm_smmu_make_sva_cd(&target, master, mm, bond->smmu_mn->cd->asid); + arm_smmu_write_cd_entry(master, pasid, cdptr, &target); list_add(&bond->list, &master->bonds); return 0; @@ -546,7 +612,7 @@ void arm_smmu_sva_remove_dev_pasid(struct iommu_domain *domain, mutex_lock(&sva_lock); - arm_smmu_write_ctx_desc(master, id, NULL); + arm_smmu_clear_cd(master, id); list_for_each_entry(t, &master->bonds, list) { if (t->mm == mm) { @@ -569,6 +635,9 @@ static int arm_smmu_sva_set_dev_pasid(struct iommu_domain *domain, int ret = 0; struct mm_struct *mm = domain->mm; + if (mm_get_enqcmd_pasid(mm) != id) + return -EINVAL; + mutex_lock(&sva_lock); ret = __arm_smmu_sva_bind(dev, id, mm); mutex_unlock(&sva_lock); 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 new file mode 100644 index 000000000000..417804392ff0 --- /dev/null +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c @@ -0,0 +1,465 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2024 Google LLC. + */ +#include <kunit/test.h> +#include <linux/io-pgtable.h> + +#include "arm-smmu-v3.h" + +struct arm_smmu_test_writer { + struct arm_smmu_entry_writer writer; + struct kunit *test; + const __le64 *init_entry; + const __le64 *target_entry; + __le64 *entry; + + bool invalid_entry_written; + unsigned int num_syncs; +}; + +#define NUM_ENTRY_QWORDS 8 +#define NUM_EXPECTED_SYNCS(x) x + +static struct arm_smmu_ste bypass_ste; +static struct arm_smmu_ste abort_ste; +static struct arm_smmu_device smmu = { + .features = ARM_SMMU_FEAT_STALLS | ARM_SMMU_FEAT_ATTR_TYPES_OVR +}; +static struct mm_struct sva_mm = { + .pgd = (void *)0xdaedbeefdeadbeefULL, +}; + +static bool arm_smmu_entry_differs_in_used_bits(const __le64 *entry, + const __le64 *used_bits, + const __le64 *target, + unsigned int length) +{ + bool differs = false; + unsigned int i; + + for (i = 0; i < length; i++) { + if ((entry[i] & used_bits[i]) != target[i]) + differs = true; + } + return differs; +} + +static void +arm_smmu_test_writer_record_syncs(struct arm_smmu_entry_writer *writer) +{ + struct arm_smmu_test_writer *test_writer = + container_of(writer, struct arm_smmu_test_writer, writer); + __le64 *entry_used_bits; + + entry_used_bits = kunit_kzalloc( + test_writer->test, sizeof(*entry_used_bits) * NUM_ENTRY_QWORDS, + GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test_writer->test, entry_used_bits); + + pr_debug("STE value is now set to: "); + print_hex_dump_debug(" ", DUMP_PREFIX_NONE, 16, 8, + test_writer->entry, + NUM_ENTRY_QWORDS * sizeof(*test_writer->entry), + false); + + test_writer->num_syncs += 1; + if (!test_writer->entry[0]) { + test_writer->invalid_entry_written = true; + } else { + /* + * At any stage in a hitless transition, the entry must be + * equivalent to either the initial entry or the target entry + * when only considering the bits used by the current + * configuration. + */ + writer->ops->get_used(test_writer->entry, entry_used_bits); + KUNIT_EXPECT_FALSE( + test_writer->test, + arm_smmu_entry_differs_in_used_bits( + test_writer->entry, entry_used_bits, + test_writer->init_entry, NUM_ENTRY_QWORDS) && + arm_smmu_entry_differs_in_used_bits( + test_writer->entry, entry_used_bits, + test_writer->target_entry, + NUM_ENTRY_QWORDS)); + } +} + +static void +arm_smmu_v3_test_debug_print_used_bits(struct arm_smmu_entry_writer *writer, + const __le64 *ste) +{ + __le64 used_bits[NUM_ENTRY_QWORDS] = {}; + + arm_smmu_get_ste_used(ste, used_bits); + pr_debug("STE used bits: "); + print_hex_dump_debug(" ", DUMP_PREFIX_NONE, 16, 8, used_bits, + sizeof(used_bits), false); +} + +static const struct arm_smmu_entry_writer_ops test_ste_ops = { + .sync = arm_smmu_test_writer_record_syncs, + .get_used = arm_smmu_get_ste_used, +}; + +static const struct arm_smmu_entry_writer_ops test_cd_ops = { + .sync = arm_smmu_test_writer_record_syncs, + .get_used = arm_smmu_get_cd_used, +}; + +static void arm_smmu_v3_test_ste_expect_transition( + struct kunit *test, const struct arm_smmu_ste *cur, + const struct arm_smmu_ste *target, unsigned int num_syncs_expected, + bool hitless) +{ + struct arm_smmu_ste cur_copy = *cur; + struct arm_smmu_test_writer test_writer = { + .writer = { + .ops = &test_ste_ops, + }, + .test = test, + .init_entry = cur->data, + .target_entry = target->data, + .entry = cur_copy.data, + .num_syncs = 0, + .invalid_entry_written = false, + + }; + + pr_debug("STE initial value: "); + print_hex_dump_debug(" ", DUMP_PREFIX_NONE, 16, 8, cur_copy.data, + sizeof(cur_copy), false); + arm_smmu_v3_test_debug_print_used_bits(&test_writer.writer, cur->data); + pr_debug("STE target value: "); + print_hex_dump_debug(" ", DUMP_PREFIX_NONE, 16, 8, target->data, + sizeof(cur_copy), false); + arm_smmu_v3_test_debug_print_used_bits(&test_writer.writer, + target->data); + + arm_smmu_write_entry(&test_writer.writer, cur_copy.data, target->data); + + KUNIT_EXPECT_EQ(test, test_writer.invalid_entry_written, !hitless); + KUNIT_EXPECT_EQ(test, test_writer.num_syncs, num_syncs_expected); + KUNIT_EXPECT_MEMEQ(test, target->data, cur_copy.data, sizeof(cur_copy)); +} + +static void arm_smmu_v3_test_ste_expect_hitless_transition( + struct kunit *test, const struct arm_smmu_ste *cur, + const struct arm_smmu_ste *target, unsigned int num_syncs_expected) +{ + arm_smmu_v3_test_ste_expect_transition(test, cur, target, + num_syncs_expected, true); +} + +static const dma_addr_t fake_cdtab_dma_addr = 0xF0F0F0F0F0F0; + +static void arm_smmu_test_make_cdtable_ste(struct arm_smmu_ste *ste, + const dma_addr_t dma_addr) +{ + struct arm_smmu_master master = { + .cd_table.cdtab_dma = dma_addr, + .cd_table.s1cdmax = 0xFF, + .cd_table.s1fmt = STRTAB_STE_0_S1FMT_64K_L2, + .smmu = &smmu, + }; + + arm_smmu_make_cdtable_ste(ste, &master); +} + +static void arm_smmu_v3_write_ste_test_bypass_to_abort(struct kunit *test) +{ + /* + * Bypass STEs has used bits in the first two Qwords, while abort STEs + * only have used bits in the first QWord. Transitioning from bypass to + * abort requires two syncs: the first to set the first qword and make + * the STE into an abort, the second to clean up the second qword. + */ + arm_smmu_v3_test_ste_expect_hitless_transition( + test, &bypass_ste, &abort_ste, NUM_EXPECTED_SYNCS(2)); +} + +static void arm_smmu_v3_write_ste_test_abort_to_bypass(struct kunit *test) +{ + /* + * Transitioning from abort to bypass also requires two syncs: the first + * to set the second qword data required by the bypass STE, and the + * second to set the first qword and switch to bypass. + */ + arm_smmu_v3_test_ste_expect_hitless_transition( + test, &abort_ste, &bypass_ste, NUM_EXPECTED_SYNCS(2)); +} + +static void arm_smmu_v3_write_ste_test_cdtable_to_abort(struct kunit *test) +{ + struct arm_smmu_ste ste; + + arm_smmu_test_make_cdtable_ste(&ste, fake_cdtab_dma_addr); + arm_smmu_v3_test_ste_expect_hitless_transition(test, &ste, &abort_ste, + NUM_EXPECTED_SYNCS(2)); +} + +static void arm_smmu_v3_write_ste_test_abort_to_cdtable(struct kunit *test) +{ + struct arm_smmu_ste ste; + + arm_smmu_test_make_cdtable_ste(&ste, fake_cdtab_dma_addr); + arm_smmu_v3_test_ste_expect_hitless_transition(test, &abort_ste, &ste, + NUM_EXPECTED_SYNCS(2)); +} + +static void arm_smmu_v3_write_ste_test_cdtable_to_bypass(struct kunit *test) +{ + struct arm_smmu_ste ste; + + arm_smmu_test_make_cdtable_ste(&ste, fake_cdtab_dma_addr); + arm_smmu_v3_test_ste_expect_hitless_transition(test, &ste, &bypass_ste, + NUM_EXPECTED_SYNCS(3)); +} + +static void arm_smmu_v3_write_ste_test_bypass_to_cdtable(struct kunit *test) +{ + struct arm_smmu_ste ste; + + arm_smmu_test_make_cdtable_ste(&ste, fake_cdtab_dma_addr); + arm_smmu_v3_test_ste_expect_hitless_transition(test, &bypass_ste, &ste, + NUM_EXPECTED_SYNCS(3)); +} + +static void arm_smmu_test_make_s2_ste(struct arm_smmu_ste *ste, + bool ats_enabled) +{ + struct arm_smmu_master master = { + .smmu = &smmu, + .ats_enabled = ats_enabled, + }; + struct io_pgtable io_pgtable = {}; + struct arm_smmu_domain smmu_domain = { + .pgtbl_ops = &io_pgtable.ops, + }; + + io_pgtable.cfg.arm_lpae_s2_cfg.vttbr = 0xdaedbeefdeadbeefULL; + io_pgtable.cfg.arm_lpae_s2_cfg.vtcr.ps = 1; + io_pgtable.cfg.arm_lpae_s2_cfg.vtcr.tg = 2; + io_pgtable.cfg.arm_lpae_s2_cfg.vtcr.sh = 3; + io_pgtable.cfg.arm_lpae_s2_cfg.vtcr.orgn = 1; + io_pgtable.cfg.arm_lpae_s2_cfg.vtcr.irgn = 2; + io_pgtable.cfg.arm_lpae_s2_cfg.vtcr.sl = 3; + io_pgtable.cfg.arm_lpae_s2_cfg.vtcr.tsz = 4; + + arm_smmu_make_s2_domain_ste(ste, &master, &smmu_domain); +} + +static void arm_smmu_v3_write_ste_test_s2_to_abort(struct kunit *test) +{ + struct arm_smmu_ste ste; + + arm_smmu_test_make_s2_ste(&ste, true); + arm_smmu_v3_test_ste_expect_hitless_transition(test, &ste, &abort_ste, + NUM_EXPECTED_SYNCS(2)); +} + +static void arm_smmu_v3_write_ste_test_abort_to_s2(struct kunit *test) +{ + struct arm_smmu_ste ste; + + arm_smmu_test_make_s2_ste(&ste, true); + arm_smmu_v3_test_ste_expect_hitless_transition(test, &abort_ste, &ste, + NUM_EXPECTED_SYNCS(2)); +} + +static void arm_smmu_v3_write_ste_test_s2_to_bypass(struct kunit *test) +{ + struct arm_smmu_ste ste; + + arm_smmu_test_make_s2_ste(&ste, true); + arm_smmu_v3_test_ste_expect_hitless_transition(test, &ste, &bypass_ste, + NUM_EXPECTED_SYNCS(2)); +} + +static void arm_smmu_v3_write_ste_test_bypass_to_s2(struct kunit *test) +{ + struct arm_smmu_ste ste; + + arm_smmu_test_make_s2_ste(&ste, true); + arm_smmu_v3_test_ste_expect_hitless_transition(test, &bypass_ste, &ste, + NUM_EXPECTED_SYNCS(2)); +} + +static void arm_smmu_v3_test_cd_expect_transition( + struct kunit *test, const struct arm_smmu_cd *cur, + const struct arm_smmu_cd *target, unsigned int num_syncs_expected, + bool hitless) +{ + struct arm_smmu_cd cur_copy = *cur; + struct arm_smmu_test_writer test_writer = { + .writer = { + .ops = &test_cd_ops, + }, + .test = test, + .init_entry = cur->data, + .target_entry = target->data, + .entry = cur_copy.data, + .num_syncs = 0, + .invalid_entry_written = false, + + }; + + pr_debug("CD initial value: "); + print_hex_dump_debug(" ", DUMP_PREFIX_NONE, 16, 8, cur_copy.data, + sizeof(cur_copy), false); + arm_smmu_v3_test_debug_print_used_bits(&test_writer.writer, cur->data); + pr_debug("CD target value: "); + print_hex_dump_debug(" ", DUMP_PREFIX_NONE, 16, 8, target->data, + sizeof(cur_copy), false); + arm_smmu_v3_test_debug_print_used_bits(&test_writer.writer, + target->data); + + arm_smmu_write_entry(&test_writer.writer, cur_copy.data, target->data); + + KUNIT_EXPECT_EQ(test, test_writer.invalid_entry_written, !hitless); + KUNIT_EXPECT_EQ(test, test_writer.num_syncs, num_syncs_expected); + KUNIT_EXPECT_MEMEQ(test, target->data, cur_copy.data, sizeof(cur_copy)); +} + +static void arm_smmu_v3_test_cd_expect_non_hitless_transition( + struct kunit *test, const struct arm_smmu_cd *cur, + const struct arm_smmu_cd *target, unsigned int num_syncs_expected) +{ + arm_smmu_v3_test_cd_expect_transition(test, cur, target, + num_syncs_expected, false); +} + +static void arm_smmu_v3_test_cd_expect_hitless_transition( + struct kunit *test, const struct arm_smmu_cd *cur, + const struct arm_smmu_cd *target, unsigned int num_syncs_expected) +{ + arm_smmu_v3_test_cd_expect_transition(test, cur, target, + num_syncs_expected, true); +} + +static void arm_smmu_test_make_s1_cd(struct arm_smmu_cd *cd, unsigned int asid) +{ + struct arm_smmu_master master = { + .smmu = &smmu, + }; + struct io_pgtable io_pgtable = {}; + struct arm_smmu_domain smmu_domain = { + .pgtbl_ops = &io_pgtable.ops, + .cd = { + .asid = asid, + }, + }; + + io_pgtable.cfg.arm_lpae_s1_cfg.ttbr = 0xdaedbeefdeadbeefULL; + io_pgtable.cfg.arm_lpae_s1_cfg.tcr.ips = 1; + io_pgtable.cfg.arm_lpae_s1_cfg.tcr.tg = 2; + io_pgtable.cfg.arm_lpae_s1_cfg.tcr.sh = 3; + io_pgtable.cfg.arm_lpae_s1_cfg.tcr.orgn = 1; + io_pgtable.cfg.arm_lpae_s1_cfg.tcr.irgn = 2; + io_pgtable.cfg.arm_lpae_s1_cfg.tcr.tsz = 4; + io_pgtable.cfg.arm_lpae_s1_cfg.mair = 0xabcdef012345678ULL; + + arm_smmu_make_s1_cd(cd, &master, &smmu_domain); +} + +static void arm_smmu_v3_write_cd_test_s1_clear(struct kunit *test) +{ + struct arm_smmu_cd cd = {}; + struct arm_smmu_cd cd_2; + + arm_smmu_test_make_s1_cd(&cd_2, 1997); + arm_smmu_v3_test_cd_expect_non_hitless_transition( + test, &cd, &cd_2, NUM_EXPECTED_SYNCS(2)); + arm_smmu_v3_test_cd_expect_non_hitless_transition( + test, &cd_2, &cd, NUM_EXPECTED_SYNCS(2)); +} + +static void arm_smmu_v3_write_cd_test_s1_change_asid(struct kunit *test) +{ + struct arm_smmu_cd cd = {}; + struct arm_smmu_cd cd_2; + + arm_smmu_test_make_s1_cd(&cd, 778); + arm_smmu_test_make_s1_cd(&cd_2, 1997); + arm_smmu_v3_test_cd_expect_hitless_transition(test, &cd, &cd_2, + NUM_EXPECTED_SYNCS(1)); + arm_smmu_v3_test_cd_expect_hitless_transition(test, &cd_2, &cd, + NUM_EXPECTED_SYNCS(1)); +} + +static void arm_smmu_test_make_sva_cd(struct arm_smmu_cd *cd, unsigned int asid) +{ + struct arm_smmu_master master = { + .smmu = &smmu, + }; + + arm_smmu_make_sva_cd(cd, &master, &sva_mm, asid); +} + +static void arm_smmu_test_make_sva_release_cd(struct arm_smmu_cd *cd, + unsigned int asid) +{ + struct arm_smmu_master master = { + .smmu = &smmu, + }; + + arm_smmu_make_sva_cd(cd, &master, NULL, asid); +} + +static void arm_smmu_v3_write_cd_test_sva_clear(struct kunit *test) +{ + struct arm_smmu_cd cd = {}; + struct arm_smmu_cd cd_2; + + arm_smmu_test_make_sva_cd(&cd_2, 1997); + arm_smmu_v3_test_cd_expect_non_hitless_transition( + test, &cd, &cd_2, NUM_EXPECTED_SYNCS(2)); + arm_smmu_v3_test_cd_expect_non_hitless_transition( + test, &cd_2, &cd, NUM_EXPECTED_SYNCS(2)); +} + +static void arm_smmu_v3_write_cd_test_sva_release(struct kunit *test) +{ + struct arm_smmu_cd cd; + struct arm_smmu_cd cd_2; + + arm_smmu_test_make_sva_cd(&cd, 1997); + arm_smmu_test_make_sva_release_cd(&cd_2, 1997); + arm_smmu_v3_test_cd_expect_hitless_transition(test, &cd, &cd_2, + NUM_EXPECTED_SYNCS(2)); + arm_smmu_v3_test_cd_expect_hitless_transition(test, &cd_2, &cd, + NUM_EXPECTED_SYNCS(2)); +} + +static struct kunit_case arm_smmu_v3_test_cases[] = { + KUNIT_CASE(arm_smmu_v3_write_ste_test_bypass_to_abort), + KUNIT_CASE(arm_smmu_v3_write_ste_test_abort_to_bypass), + KUNIT_CASE(arm_smmu_v3_write_ste_test_cdtable_to_abort), + KUNIT_CASE(arm_smmu_v3_write_ste_test_abort_to_cdtable), + KUNIT_CASE(arm_smmu_v3_write_ste_test_cdtable_to_bypass), + KUNIT_CASE(arm_smmu_v3_write_ste_test_bypass_to_cdtable), + KUNIT_CASE(arm_smmu_v3_write_ste_test_s2_to_abort), + KUNIT_CASE(arm_smmu_v3_write_ste_test_abort_to_s2), + KUNIT_CASE(arm_smmu_v3_write_ste_test_s2_to_bypass), + KUNIT_CASE(arm_smmu_v3_write_ste_test_bypass_to_s2), + KUNIT_CASE(arm_smmu_v3_write_cd_test_s1_clear), + KUNIT_CASE(arm_smmu_v3_write_cd_test_s1_change_asid), + KUNIT_CASE(arm_smmu_v3_write_cd_test_sva_clear), + KUNIT_CASE(arm_smmu_v3_write_cd_test_sva_release), + {}, +}; + +static int arm_smmu_v3_test_suite_init(struct kunit_suite *test) +{ + arm_smmu_make_bypass_ste(&smmu, &bypass_ste); + arm_smmu_make_abort_ste(&abort_ste); + return 0; +} + +static struct kunit_suite arm_smmu_v3_test_module = { + .name = "arm-smmu-v3-kunit-test", + .suite_init = arm_smmu_v3_test_suite_init, + .test_cases = arm_smmu_v3_test_cases, +}; +kunit_test_suites(&arm_smmu_v3_test_module); 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 41f93c3ab160..1ad0937760c6 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -26,15 +26,11 @@ #include <linux/pci.h> #include <linux/pci-ats.h> #include <linux/platform_device.h> +#include <kunit/visibility.h> #include "arm-smmu-v3.h" #include "../../dma-iommu.h" -static bool disable_bypass = true; -module_param(disable_bypass, bool, 0444); -MODULE_PARM_DESC(disable_bypass, - "Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU."); - static bool disable_msipolling; module_param(disable_msipolling, bool, 0444); MODULE_PARM_DESC(disable_msipolling, @@ -47,8 +43,9 @@ 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); +#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] = { @@ -76,12 +73,6 @@ struct arm_smmu_option_prop { DEFINE_XARRAY_ALLOC1(arm_smmu_asid_xa); DEFINE_MUTEX(arm_smmu_asid_lock); -/* - * Special value used by SVA when a process dies, to quiesce a CD without - * disabling it. - */ -struct arm_smmu_ctx_desc quiet_cd = { 0 }; - static struct arm_smmu_option_prop arm_smmu_options[] = { { ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" }, { ARM_SMMU_OPT_PAGE0_REGS_ONLY, "cavium,cn9900-broken-page1-regspace"}, @@ -90,6 +81,7 @@ static struct arm_smmu_option_prop arm_smmu_options[] = { static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain, struct arm_smmu_device *smmu); +static int arm_smmu_alloc_cd_tables(struct arm_smmu_master *master); static void parse_driver_options(struct arm_smmu_device *smmu) { @@ -977,43 +969,43 @@ 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) +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->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 |