* [PATCH 1/8] iommu/io-pgtable-arm: Rationalise TTBRn handling
2020-01-10 15:28 [PATCH 0/8] Finish off the split page table prep work Will Deacon
@ 2020-01-10 15:28 ` Will Deacon
2020-01-10 15:28 ` [PATCH 2/8] iommu/io-pgtable-arm: Support non-coherent stage-2 page tables Will Deacon
` (6 subsequent siblings)
7 siblings, 0 replies; 11+ messages in thread
From: Will Deacon @ 2020-01-10 15:28 UTC (permalink / raw)
To: iommu
Cc: Will Deacon, Jordan Crouse, kernel-team, Robin Murphy,
linux-arm-kernel
From: Robin Murphy <robin.murphy@arm.com>
TTBR1 values have so far been redundant since no users implement any
support for split address spaces. Crucially, though, one of the main
reasons for wanting to do so is to be able to manage each half entirely
independently, e.g. context-switching one set of mappings without
disturbing the other. Thus it seems unlikely that tying two tables
together in a single io_pgtable_cfg would ever be particularly desirable
or useful.
Streamline the configs to just a single conceptual TTBR value
representing the allocated table. This paves the way for future users to
support split address spaces by simply allocating a table and dealing
with the detailed TTBRn logistics themselves.
Tested-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
[will: Keep v7s non-coherent mappings explicitly outer-shareable]
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/arm-smmu-v3.c | 2 +-
drivers/iommu/arm-smmu.c | 9 ++++-----
drivers/iommu/io-pgtable-arm-v7s.c | 17 ++++++++---------
drivers/iommu/io-pgtable-arm.c | 5 ++---
drivers/iommu/ipmmu-vmsa.c | 2 +-
drivers/iommu/msm_iommu.c | 4 ++--
drivers/iommu/mtk_iommu.c | 4 ++--
drivers/iommu/qcom_iommu.c | 3 +--
include/linux/io-pgtable.h | 4 ++--
9 files changed, 23 insertions(+), 27 deletions(-)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index aa7e53023585..cf2ae065a6c2 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2166,7 +2166,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
}
cfg->cd.asid = (u16)asid;
- cfg->cd.ttbr = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
+ cfg->cd.ttbr = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
cfg->cd.tcr = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
cfg->cd.mair = pgtbl_cfg->arm_lpae_s1_cfg.mair;
return 0;
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 46b87740d708..72640e045268 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -553,13 +553,12 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
/* TTBRs */
if (stage1) {
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
- cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr[0];
- cb->ttbr[1] = pgtbl_cfg->arm_v7s_cfg.ttbr[1];
+ cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr;
+ cb->ttbr[1] = 0;
} else {
- cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
+ cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
cb->ttbr[0] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
- cb->ttbr[1] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
- cb->ttbr[1] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
+ cb->ttbr[1] = FIELD_PREP(TTBRn_ASID, cfg->asid);
}
} else {
cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 7c3bd2c3cdca..714cb406b0a8 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -822,15 +822,14 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
/* Ensure the empty pgd is visible before any actual TTBR write */
wmb();
- /* TTBRs */
- cfg->arm_v7s_cfg.ttbr[0] = virt_to_phys(data->pgd) |
- ARM_V7S_TTBR_S | ARM_V7S_TTBR_NOS |
- (cfg->coherent_walk ?
- (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
- ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
- (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
- ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
- cfg->arm_v7s_cfg.ttbr[1] = 0;
+ /* TTBR */
+ cfg->arm_v7s_cfg.ttbr = virt_to_phys(data->pgd) |
+ ARM_V7S_TTBR_S | ARM_V7S_TTBR_NOS |
+ (cfg->coherent_walk ?
+ (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
+ ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
+ (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
+ ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
return &data->iop;
out_free_data:
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index bdf47f745268..7b422b9fe05b 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -872,9 +872,8 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
/* Ensure the empty pgd is visible before any actual TTBR write */
wmb();
- /* TTBRs */
- cfg->arm_lpae_s1_cfg.ttbr[0] = virt_to_phys(data->pgd);
- cfg->arm_lpae_s1_cfg.ttbr[1] = 0;
+ /* TTBR */
+ cfg->arm_lpae_s1_cfg.ttbr = virt_to_phys(data->pgd);
return &data->iop;
out_free_data:
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index d02edd2751f3..ecb3f9464dd5 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -374,7 +374,7 @@ static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain)
u32 tmp;
/* TTBR0 */
- ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr[0];
+ ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr;
ipmmu_ctx_write_root(domain, IMTTLBR0, ttbr);
ipmmu_ctx_write_root(domain, IMTTUBR0, ttbr >> 32);
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 93f14bca26ee..94a6df1bddd6 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -279,8 +279,8 @@ static void __program_context(void __iomem *base, int ctx,
SET_V2PCFG(base, ctx, 0x3);
SET_TTBCR(base, ctx, priv->cfg.arm_v7s_cfg.tcr);
- SET_TTBR0(base, ctx, priv->cfg.arm_v7s_cfg.ttbr[0]);
- SET_TTBR1(base, ctx, priv->cfg.arm_v7s_cfg.ttbr[1]);
+ SET_TTBR0(base, ctx, priv->cfg.arm_v7s_cfg.ttbr);
+ SET_TTBR1(base, ctx, 0);
/* Set prrr and nmrr */
SET_PRRR(base, ctx, priv->cfg.arm_v7s_cfg.prrr);
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 6fc1f5ecf91e..95945f467c03 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -367,7 +367,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
/* Update the pgtable base address register of the M4U HW */
if (!data->m4u_dom) {
data->m4u_dom = dom;
- writel(dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
+ writel(dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
data->base + REG_MMU_PT_BASE_ADDR);
}
@@ -765,7 +765,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
if (m4u_dom)
- writel(m4u_dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
+ writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
base + REG_MMU_PT_BASE_ADDR);
return 0;
}
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 52f38292df5b..c200bc066257 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -269,10 +269,9 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
/* TTBRs */
iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
- pgtbl_cfg.arm_lpae_s1_cfg.ttbr[0] |
+ pgtbl_cfg.arm_lpae_s1_cfg.ttbr |
FIELD_PREP(TTBRn_ASID, ctx->asid));
iommu_writeq(ctx, ARM_SMMU_CB_TTBR1,
- pgtbl_cfg.arm_lpae_s1_cfg.ttbr[1] |
FIELD_PREP(TTBRn_ASID, ctx->asid));
/* TCR */
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index ee21eedafe98..53bca5343f52 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -100,7 +100,7 @@ struct io_pgtable_cfg {
/* Low-level data specific to the table format */
union {
struct {
- u64 ttbr[2];
+ u64 ttbr;
u64 tcr;
u64 mair;
} arm_lpae_s1_cfg;
@@ -111,7 +111,7 @@ struct io_pgtable_cfg {
} arm_lpae_s2_cfg;
struct {
- u32 ttbr[2];
+ u32 ttbr;
u32 tcr;
u32 nmrr;
u32 prrr;
--
2.25.0.rc1.283.g88dfdc4193-goog
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 2/8] iommu/io-pgtable-arm: Support non-coherent stage-2 page tables
2020-01-10 15:28 [PATCH 0/8] Finish off the split page table prep work Will Deacon
2020-01-10 15:28 ` [PATCH 1/8] iommu/io-pgtable-arm: Rationalise TTBRn handling Will Deacon
@ 2020-01-10 15:28 ` Will Deacon
2020-01-10 15:28 ` [PATCH 3/8] iommu/io-pgtable-arm: Ensure non-cacheable mappings are Outer Shareable Will Deacon
` (5 subsequent siblings)
7 siblings, 0 replies; 11+ messages in thread
From: Will Deacon @ 2020-01-10 15:28 UTC (permalink / raw)
To: iommu
Cc: kernel-team, Robin Murphy, Bjorn Andersson, Jordan Crouse,
Will Deacon, linux-arm-kernel
Commit 9e6ea59f3ff3 ("iommu/io-pgtable: Support non-coherent page tables")
added support for non-coherent page-table walks to the Arm IOMMU page-table
backends. Unfortunately, it left the stage-2 allocator unchanged, so let's
hook that up in the same way.
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/io-pgtable-arm.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 7b422b9fe05b..ab440b52a5f4 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -910,10 +910,16 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
}
/* VTCR */
- reg = ARM_64_LPAE_S2_TCR_RES1 |
- (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
- (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
- (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+ reg = ARM_64_LPAE_S2_TCR_RES1;
+ if (cfg->coherent_walk) {
+ reg |= (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
+ (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
+ (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+ } else {
+ reg |= (ARM_LPAE_TCR_SH_OS << ARM_LPAE_TCR_SH0_SHIFT) |
+ (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_IRGN0_SHIFT) |
+ (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_ORGN0_SHIFT);
+ }
sl = data->start_level;
--
2.25.0.rc1.283.g88dfdc4193-goog
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 3/8] iommu/io-pgtable-arm: Ensure non-cacheable mappings are Outer Shareable
2020-01-10 15:28 [PATCH 0/8] Finish off the split page table prep work Will Deacon
2020-01-10 15:28 ` [PATCH 1/8] iommu/io-pgtable-arm: Rationalise TTBRn handling Will Deacon
2020-01-10 15:28 ` [PATCH 2/8] iommu/io-pgtable-arm: Support non-coherent stage-2 page tables Will Deacon
@ 2020-01-10 15:28 ` Will Deacon
2020-01-10 15:28 ` [PATCH 4/8] iommu/io-pgtable-arm: Ensure ARM_64_LPAE_S2_TCR_RES1 is unsigned Will Deacon
` (4 subsequent siblings)
7 siblings, 0 replies; 11+ messages in thread
From: Will Deacon @ 2020-01-10 15:28 UTC (permalink / raw)
To: iommu
Cc: Will Deacon, Jordan Crouse, kernel-team, Robin Murphy,
linux-arm-kernel
The Armv7 ARM states that Normal, Non-cacheable mappings must explicitly
be marked as Outer Shareable in order to avoid UNPREDICTABLE behaviour:
| Overlaying the shareability attribute (B3-1377, ARM DDI 0406C.c)
|
| A memory region with a resultant memory type attribute of Normal, and
| a resultant cacheability attribute of Inner Non-cacheable, Outer
| Non-cacheable, must have a resultant shareability attribute of Outer
| Shareable, otherwise shareability is UNPREDICTABLE
Although this requirement doesn't appear to exist in the Armv8 docs,
where the 'SH' field is simply ignored in this case, it's
straightforward enough to set it here.
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/io-pgtable-arm.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index ab440b52a5f4..4b437ead2300 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -303,9 +303,8 @@ static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
if (data->iop.fmt != ARM_MALI_LPAE)
pte |= ARM_LPAE_PTE_AF;
- pte |= ARM_LPAE_PTE_SH_IS;
- pte |= paddr_to_iopte(paddr, data);
+ pte |= paddr_to_iopte(paddr, data);
__arm_lpae_set_pte(ptep, pte, &data->iop.cfg);
}
@@ -463,6 +462,11 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
if (prot & IOMMU_NOEXEC)
pte |= ARM_LPAE_PTE_XN;
+ if (prot & IOMMU_CACHE)
+ pte |= ARM_LPAE_PTE_SH_IS;
+ else
+ pte |= ARM_LPAE_PTE_SH_OS;
+
return pte;
}
--
2.25.0.rc1.283.g88dfdc4193-goog
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 4/8] iommu/io-pgtable-arm: Ensure ARM_64_LPAE_S2_TCR_RES1 is unsigned
2020-01-10 15:28 [PATCH 0/8] Finish off the split page table prep work Will Deacon
` (2 preceding siblings ...)
2020-01-10 15:28 ` [PATCH 3/8] iommu/io-pgtable-arm: Ensure non-cacheable mappings are Outer Shareable Will Deacon
@ 2020-01-10 15:28 ` Will Deacon
2020-01-10 15:28 ` [PATCH 5/8] iommu/io-pgtable-arm: Rationalise TCR handling Will Deacon
` (3 subsequent siblings)
7 siblings, 0 replies; 11+ messages in thread
From: Will Deacon @ 2020-01-10 15:28 UTC (permalink / raw)
To: iommu
Cc: Will Deacon, Jordan Crouse, kernel-team, Robin Murphy,
linux-arm-kernel
ARM_64_LPAE_S2_TCR_RES1 is intended to map to bit 31 of the VTCR register,
which is required to be set to 1 by the architecture. Unfortunately, we
accidentally treat this as a signed quantity which means we also set the
upper 32 bits of the VTCR to one, and they are required to be zero.
Treat ARM_64_LPAE_S2_TCR_RES1 as unsigned to avoid the unwanted
sign-extension up to 64 bits.
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/io-pgtable-arm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 4b437ead2300..89216bf37282 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -101,7 +101,7 @@
/* Register bits */
#define ARM_32_LPAE_TCR_EAE (1 << 31)
-#define ARM_64_LPAE_S2_TCR_RES1 (1 << 31)
+#define ARM_64_LPAE_S2_TCR_RES1 (1U << 31)
#define ARM_LPAE_TCR_EPD1 (1 << 23)
--
2.25.0.rc1.283.g88dfdc4193-goog
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 5/8] iommu/io-pgtable-arm: Rationalise TCR handling
2020-01-10 15:28 [PATCH 0/8] Finish off the split page table prep work Will Deacon
` (3 preceding siblings ...)
2020-01-10 15:28 ` [PATCH 4/8] iommu/io-pgtable-arm: Ensure ARM_64_LPAE_S2_TCR_RES1 is unsigned Will Deacon
@ 2020-01-10 15:28 ` Will Deacon
2020-01-10 15:28 ` [PATCH 6/8] iommu/arm-smmu: Rename public #defines under ARM_SMMU_ namespace Will Deacon
` (2 subsequent siblings)
7 siblings, 0 replies; 11+ messages in thread
From: Will Deacon @ 2020-01-10 15:28 UTC (permalink / raw)
To: iommu
Cc: Will Deacon, Jordan Crouse, kernel-team, Robin Murphy,
linux-arm-kernel
From: Robin Murphy <robin.murphy@arm.com>
Although it's conceptually nice for the io_pgtable_cfg to provide a
standard VMSA TCR value, the reality is that no VMSA-compliant IOMMU
looks exactly like an Arm CPU, and they all have various other TCR
controls which io-pgtable can't be expected to understand. Thus since
there is an expectation that drivers will have to add to the given TCR
value anyway, let's strip it down to just the essentials that are
directly relevant to io-pgtable's inner workings - namely the various
sizes and the walk attributes.
Tested-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
[will: Add missing include of bitfield.h]
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/arm-smmu-v3.c | 41 +++----------
drivers/iommu/arm-smmu.c | 7 ++-
drivers/iommu/arm-smmu.h | 28 +++++++++
drivers/iommu/io-pgtable-arm-v7s.c | 6 +-
drivers/iommu/io-pgtable-arm.c | 98 ++++++++++++------------------
drivers/iommu/io-pgtable.c | 2 +-
drivers/iommu/qcom_iommu.c | 8 +--
include/linux/io-pgtable.h | 9 ++-
8 files changed, 95 insertions(+), 104 deletions(-)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index cf2ae065a6c2..d127974afdb7 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -260,27 +260,18 @@
/* Context descriptor (stage-1 only) */
#define CTXDESC_CD_DWORDS 8
#define CTXDESC_CD_0_TCR_T0SZ GENMASK_ULL(5, 0)
-#define ARM64_TCR_T0SZ GENMASK_ULL(5, 0)
#define CTXDESC_CD_0_TCR_TG0 GENMASK_ULL(7, 6)
-#define ARM64_TCR_TG0 GENMASK_ULL(15, 14)
#define CTXDESC_CD_0_TCR_IRGN0 GENMASK_ULL(9, 8)
-#define ARM64_TCR_IRGN0 GENMASK_ULL(9, 8)
#define CTXDESC_CD_0_TCR_ORGN0 GENMASK_ULL(11, 10)
-#define ARM64_TCR_ORGN0 GENMASK_ULL(11, 10)
#define CTXDESC_CD_0_TCR_SH0 GENMASK_ULL(13, 12)
-#define ARM64_TCR_SH0 GENMASK_ULL(13, 12)
#define CTXDESC_CD_0_TCR_EPD0 (1ULL << 14)
-#define ARM64_TCR_EPD0 (1ULL << 7)
#define CTXDESC_CD_0_TCR_EPD1 (1ULL << 30)
-#define ARM64_TCR_EPD1 (1ULL << 23)
#define CTXDESC_CD_0_ENDI (1UL << 15)
#define CTXDESC_CD_0_V (1UL << 31)
#define CTXDESC_CD_0_TCR_IPS GENMASK_ULL(34, 32)
-#define ARM64_TCR_IPS GENMASK_ULL(34, 32)
#define CTXDESC_CD_0_TCR_TBI0 (1ULL << 38)
-#define ARM64_TCR_TBI0 (1ULL << 37)
#define CTXDESC_CD_0_AA64 (1UL << 41)
#define CTXDESC_CD_0_S (1UL << 44)
@@ -291,10 +282,6 @@
#define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4)
-/* Convert between AArch64 (CPU) TCR format and SMMU CD format */
-#define ARM_SMMU_TCR2CD(tcr, fld) FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \
- FIELD_GET(ARM64_TCR_##fld, tcr))
-
/* Command queue */
#define CMDQ_ENT_SZ_SHIFT 4
#define CMDQ_ENT_DWORDS ((1 << CMDQ_ENT_SZ_SHIFT) >> 3)
@@ -1439,23 +1426,6 @@ static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
}
/* Context descriptor manipulation functions */
-static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr)
-{
- u64 val = 0;
-
- /* Repack the TCR. Just care about TTBR0 for now */
- val |= ARM_SMMU_TCR2CD(tcr, T0SZ);
- val |= ARM_SMMU_TCR2CD(tcr, TG0);
- val |= ARM_SMMU_TCR2CD(tcr, IRGN0);
- val |= ARM_SMMU_TCR2CD(tcr, ORGN0);
- val |= ARM_SMMU_TCR2CD(tcr, SH0);
- val |= ARM_SMMU_TCR2CD(tcr, EPD0);
- val |= ARM_SMMU_TCR2CD(tcr, EPD1);
- val |= ARM_SMMU_TCR2CD(tcr, IPS);
-
- return val;
-}
-
static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
struct arm_smmu_s1_cfg *cfg)
{
@@ -1465,7 +1435,7 @@ static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
* We don't need to issue any invalidation here, as we'll invalidate
* the STE when installing the new entry anyway.
*/
- val = arm_smmu_cpu_tcr_to_cd(cfg->cd.tcr) |
+ val = cfg->cd.tcr |
#ifdef __BIG_ENDIAN
CTXDESC_CD_0_ENDI |
#endif
@@ -2151,6 +2121,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
int asid;
struct arm_smmu_device *smmu = smmu_domain->smmu;
struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+ typeof(&pgtbl_cfg->arm_lpae_s1_cfg.tcr) tcr = &pgtbl_cfg->arm_lpae_s1_cfg.tcr;
asid = arm_smmu_bitmap_alloc(smmu->asid_map, smmu->asid_bits);
if (asid < 0)
@@ -2167,7 +2138,13 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
cfg->cd.asid = (u16)asid;
cfg->cd.ttbr = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
- cfg->cd.tcr = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
+ cfg->cd.tcr = FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, tcr->tsz) |
+ FIELD_PREP(CTXDESC_CD_0_TCR_TG0, tcr->tg) |
+ FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, tcr->irgn) |
+ FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, tcr->orgn) |
+ FIELD_PREP(CTXDESC_CD_0_TCR_SH0, tcr->sh) |
+ FIELD_PREP(CTXDESC_CD_0_TCR_IPS, tcr->ips) |
+ CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;
cfg->cd.mair = pgtbl_cfg->arm_lpae_s1_cfg.mair;
return 0;
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 72640e045268..e65eb60812ec 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -540,11 +540,12 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
cb->tcr[0] = pgtbl_cfg->arm_v7s_cfg.tcr;
} else {
- cb->tcr[0] = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
- cb->tcr[1] = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
- cb->tcr[1] |= FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM);
+ cb->tcr[0] = arm_smmu_lpae_tcr(pgtbl_cfg);
+ cb->tcr[1] = arm_smmu_lpae_tcr2(pgtbl_cfg);
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
cb->tcr[1] |= TCR2_AS;
+ else
+ cb->tcr[0] |= TCR_EAE;
}
} else {
cb->tcr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 62b9f0cec49b..aade2b0ae175 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -11,6 +11,7 @@
#define _ARM_SMMU_H
#include <linux/atomic.h>
+#include <linux/bitfield.h>
#include <linux/bits.h>
#include <linux/clk.h>
#include <linux/device.h>
@@ -158,12 +159,24 @@ enum arm_smmu_cbar_type {
#define TCR2_SEP GENMASK(17, 15)
#define TCR2_SEP_UPSTREAM 0x7
#define TCR2_AS BIT(4)
+#define TCR2_PASIZE GENMASK(3, 0)
#define ARM_SMMU_CB_TTBR0 0x20
#define ARM_SMMU_CB_TTBR1 0x28
#define TTBRn_ASID GENMASK_ULL(63, 48)
+/* arm64 headers leak this somehow :( */
+#undef TCR_T0SZ
+
#define ARM_SMMU_CB_TCR 0x30
+#define TCR_EAE BIT(31)
+#define TCR_EPD1 BIT(23)
+#define TCR_TG0 GENMASK(15, 14)
+#define TCR_SH0 GENMASK(13, 12)
+#define TCR_ORGN0 GENMASK(11, 10)
+#define TCR_IRGN0 GENMASK(9, 8)
+#define TCR_T0SZ GENMASK(5, 0)
+
#define ARM_SMMU_CB_CONTEXTIDR 0x34
#define ARM_SMMU_CB_S1_MAIR0 0x38
#define ARM_SMMU_CB_S1_MAIR1 0x3c
@@ -318,6 +331,21 @@ struct arm_smmu_domain {
struct iommu_domain domain;
};
+static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg)
+{
+ return TCR_EPD1 |
+ FIELD_PREP(TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
+ FIELD_PREP(TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
+ FIELD_PREP(TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
+ FIELD_PREP(TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
+ FIELD_PREP(TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
+}
+
+static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg)
+{
+ return FIELD_PREP(TCR2_PASIZE, cfg->arm_lpae_s1_cfg.tcr.ips) |
+ FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM);
+}
/* Implementation details, yay! */
struct arm_smmu_impl {
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 714cb406b0a8..ccedf50e5998 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -149,8 +149,6 @@
#define ARM_V7S_TTBR_IRGN_ATTR(attr) \
((((attr) & 0x1) << 6) | (((attr) & 0x2) >> 1))
-#define ARM_V7S_TCR_PD1 BIT(5)
-
#ifdef CONFIG_ZONE_DMA32
#define ARM_V7S_TABLE_GFP_DMA GFP_DMA32
#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA32
@@ -798,8 +796,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
*/
cfg->pgsize_bitmap &= SZ_4K | SZ_64K | SZ_1M | SZ_16M;
- /* TCR: T0SZ=0, disable TTBR1 */
- cfg->arm_v7s_cfg.tcr = ARM_V7S_TCR_PD1;
+ /* TCR: T0SZ=0, EAE=0 (if applicable) */
+ cfg->arm_v7s_cfg.tcr = 0;
/*
* TEX remap: the indices used map to the closest equivalent types
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 89216bf37282..78ec0ee5c59c 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -100,40 +100,32 @@
#define ARM_LPAE_PTE_MEMATTR_DEV (((arm_lpae_iopte)0x1) << 2)
/* Register bits */
-#define ARM_32_LPAE_TCR_EAE (1 << 31)
-#define ARM_64_LPAE_S2_TCR_RES1 (1U << 31)
+#define ARM_64_LPAE_VTCR_RES1 (1U << 31)
-#define ARM_LPAE_TCR_EPD1 (1 << 23)
-
-#define ARM_LPAE_TCR_TG0_4K (0 << 14)
-#define ARM_LPAE_TCR_TG0_64K (1 << 14)
-#define ARM_LPAE_TCR_TG0_16K (2 << 14)
+#define ARM_LPAE_VTCR_TG0_SHIFT 14
+#define ARM_LPAE_TCR_TG0_4K 0
+#define ARM_LPAE_TCR_TG0_64K 1
+#define ARM_LPAE_TCR_TG0_16K 2
#define ARM_LPAE_TCR_SH0_SHIFT 12
-#define ARM_LPAE_TCR_SH0_MASK 0x3
#define ARM_LPAE_TCR_SH_NS 0
#define ARM_LPAE_TCR_SH_OS 2
#define ARM_LPAE_TCR_SH_IS 3
#define ARM_LPAE_TCR_ORGN0_SHIFT 10
#define ARM_LPAE_TCR_IRGN0_SHIFT 8
-#define ARM_LPAE_TCR_RGN_MASK 0x3
#define ARM_LPAE_TCR_RGN_NC 0
#define ARM_LPAE_TCR_RGN_WBWA 1
#define ARM_LPAE_TCR_RGN_WT 2
#define ARM_LPAE_TCR_RGN_WB 3
-#define ARM_LPAE_TCR_SL0_SHIFT 6
-#define ARM_LPAE_TCR_SL0_MASK 0x3
+#define ARM_LPAE_VTCR_SL0_SHIFT 6
+#define ARM_LPAE_VTCR_SL0_MASK 0x3
#define ARM_LPAE_TCR_T0SZ_SHIFT 0
-#define ARM_LPAE_TCR_SZ_MASK 0xf
-
-#define ARM_LPAE_TCR_PS_SHIFT 16
-#define ARM_LPAE_TCR_PS_MASK 0x7
-#define ARM_LPAE_TCR_IPS_SHIFT 32
-#define ARM_LPAE_TCR_IPS_MASK 0x7
+#define ARM_LPAE_VTCR_PS_SHIFT 16
+#define ARM_LPAE_VTCR_PS_MASK 0x7
#define ARM_LPAE_TCR_PS_32_BIT 0x0ULL
#define ARM_LPAE_TCR_PS_36_BIT 0x1ULL
@@ -791,6 +783,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
{
u64 reg;
struct arm_lpae_io_pgtable *data;
+ typeof(&cfg->arm_lpae_s1_cfg.tcr) tcr = &cfg->arm_lpae_s1_cfg.tcr;
if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
IO_PGTABLE_QUIRK_NON_STRICT))
@@ -802,58 +795,54 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
/* TCR */
if (cfg->coherent_walk) {
- reg = (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
- (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
- (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+ tcr->sh = ARM_LPAE_TCR_SH_IS;
+ tcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+ tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
} else {
- reg = (ARM_LPAE_TCR_SH_OS << ARM_LPAE_TCR_SH0_SHIFT) |
- (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_IRGN0_SHIFT) |
- (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_ORGN0_SHIFT);
+ tcr->sh = ARM_LPAE_TCR_SH_OS;
+ tcr->irgn = ARM_LPAE_TCR_RGN_NC;
+ tcr->orgn = ARM_LPAE_TCR_RGN_NC;
}
switch (ARM_LPAE_GRANULE(data)) {
case SZ_4K:
- reg |= ARM_LPAE_TCR_TG0_4K;
+ tcr->tg = ARM_LPAE_TCR_TG0_4K;
break;
case SZ_16K:
- reg |= ARM_LPAE_TCR_TG0_16K;
+ tcr->tg = ARM_LPAE_TCR_TG0_16K;
break;
case SZ_64K:
- reg |= ARM_LPAE_TCR_TG0_64K;
+ tcr->tg = ARM_LPAE_TCR_TG0_64K;
break;
}
switch (cfg->oas) {
case 32:
- reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+ tcr->ips = ARM_LPAE_TCR_PS_32_BIT;
break;
case 36:
- reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+ tcr->ips = ARM_LPAE_TCR_PS_36_BIT;
break;
case 40:
- reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+ tcr->ips = ARM_LPAE_TCR_PS_40_BIT;
break;
case 42:
- reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+ tcr->ips = ARM_LPAE_TCR_PS_42_BIT;
break;
case 44:
- reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+ tcr->ips = ARM_LPAE_TCR_PS_44_BIT;
break;
case 48:
- reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+ tcr->ips = ARM_LPAE_TCR_PS_48_BIT;
break;
case 52:
- reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+ tcr->ips = ARM_LPAE_TCR_PS_52_BIT;
break;
default:
goto out_free_data;
}
- reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
-
- /* Disable speculative walks through TTBR1 */
- reg |= ARM_LPAE_TCR_EPD1;
- cfg->arm_lpae_s1_cfg.tcr = reg;
+ tcr->tsz = 64ULL - cfg->ias;
/* MAIRs */
reg = (ARM_LPAE_MAIR_ATTR_NC
@@ -914,7 +903,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
}
/* VTCR */
- reg = ARM_64_LPAE_S2_TCR_RES1;
+ reg = ARM_64_LPAE_VTCR_RES1;
if (cfg->coherent_walk) {
reg |= (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
(ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
@@ -929,45 +918,45 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
switch (ARM_LPAE_GRANULE(data)) {
case SZ_4K:
- reg |= ARM_LPAE_TCR_TG0_4K;
+ reg |= (ARM_LPAE_TCR_TG0_4K << ARM_LPAE_VTCR_TG0_SHIFT);
sl++; /* SL0 format is different for 4K granule size */
break;
case SZ_16K:
- reg |= ARM_LPAE_TCR_TG0_16K;
+ reg |= (ARM_LPAE_TCR_TG0_16K << ARM_LPAE_VTCR_TG0_SHIFT);
break;
case SZ_64K:
- reg |= ARM_LPAE_TCR_TG0_64K;
+ reg |= (ARM_LPAE_TCR_TG0_64K << ARM_LPAE_VTCR_TG0_SHIFT);
break;
}
switch (cfg->oas) {
case 32:
- reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_PS_SHIFT);
+ reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_VTCR_PS_SHIFT);
break;
case 36:
- reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_PS_SHIFT);
+ reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_VTCR_PS_SHIFT);
break;
case 40:
- reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_PS_SHIFT);
+ reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_VTCR_PS_SHIFT);
break;
case 42:
- reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_PS_SHIFT);
+ reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_VTCR_PS_SHIFT);
break;
case 44:
- reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_PS_SHIFT);
+ reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_VTCR_PS_SHIFT);
break;
case 48:
- reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT);
+ reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_VTCR_PS_SHIFT);
break;
case 52:
- reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_PS_SHIFT);
+ reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_VTCR_PS_SHIFT);
break;
default:
goto out_free_data;
}
reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
- reg |= (~sl & ARM_LPAE_TCR_SL0_MASK) << ARM_LPAE_TCR_SL0_SHIFT;
+ reg |= (~sl & ARM_LPAE_VTCR_SL0_MASK) << ARM_LPAE_VTCR_SL0_SHIFT;
cfg->arm_lpae_s2_cfg.vtcr = reg;
/* Allocate pgd pages */
@@ -991,19 +980,12 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
static struct io_pgtable *
arm_32_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
{
- struct io_pgtable *iop;
-
if (cfg->ias > 32 || cfg->oas > 40)
return NULL;
cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
- iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
- if (iop) {
- cfg->arm_lpae_s1_cfg.tcr |= ARM_32_LPAE_TCR_EAE;
- cfg->arm_lpae_s1_cfg.tcr &= 0xffffffff;
- }
- return iop;
+ return arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
}
static struct io_pgtable *
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index ced53e5b72b5..94394c81468f 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -63,7 +63,7 @@ void free_io_pgtable_ops(struct io_pgtable_ops *ops)
if (!ops)
return;
- iop = container_of(ops, struct io_pgtable, ops);
+ iop = io_pgtable_ops_to_pgtable(ops);
io_pgtable_tlb_flush_all(iop);
io_pgtable_init_table[iop->fmt]->free(iop);
}
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index c200bc066257..2eeaf2eec946 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -271,15 +271,13 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
pgtbl_cfg.arm_lpae_s1_cfg.ttbr |
FIELD_PREP(TTBRn_ASID, ctx->asid));
- iommu_writeq(ctx, ARM_SMMU_CB_TTBR1,
- FIELD_PREP(TTBRn_ASID, ctx->asid));
+ iommu_writeq(ctx, ARM_SMMU_CB_TTBR1, 0);
/* TCR */
iommu_writel(ctx, ARM_SMMU_CB_TCR2,
- (pgtbl_cfg.arm_lpae_s1_cfg.tcr >> 32) |
- FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM));
+ arm_smmu_lpae_tcr2(&pgtbl_cfg));
iommu_writel(ctx, ARM_SMMU_CB_TCR,
- pgtbl_cfg.arm_lpae_s1_cfg.tcr);
+ arm_smmu_lpae_tcr(&pgtbl_cfg) | TCR_EAE);
/* MAIRs (stage-1 only) */
iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0,
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 53bca5343f52..6ae104cedfd7 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -101,7 +101,14 @@ struct io_pgtable_cfg {
union {
struct {
u64 ttbr;
- u64 tcr;
+ struct {
+ u32 ips:3;
+ u32 tg:2;
+ u32 sh:2;
+ u32 orgn:2;
+ u32 irgn:2;
+ u32 tsz:6;
+ } tcr;
u64 mair;
} arm_lpae_s1_cfg;
--
2.25.0.rc1.283.g88dfdc4193-goog
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 6/8] iommu/arm-smmu: Rename public #defines under ARM_SMMU_ namespace
2020-01-10 15:28 [PATCH 0/8] Finish off the split page table prep work Will Deacon
` (4 preceding siblings ...)
2020-01-10 15:28 ` [PATCH 5/8] iommu/io-pgtable-arm: Rationalise TCR handling Will Deacon
@ 2020-01-10 15:28 ` Will Deacon
2020-01-10 15:28 ` [PATCH 7/8] iommu/io-pgtable-arm: Rationalise VTCR handling Will Deacon
2020-01-10 15:28 ` [PATCH 8/8] iommu/io-pgtable-arm: Prepare for TTBR1 usage Will Deacon
7 siblings, 0 replies; 11+ messages in thread
From: Will Deacon @ 2020-01-10 15:28 UTC (permalink / raw)
To: iommu
Cc: Will Deacon, Jordan Crouse, kernel-team, Robin Murphy,
linux-arm-kernel
Now that we have arm-smmu.h defining various SMMU constants, ensure that
they are namespaced with the ARM_SMMU_ prefix in order to avoid conflicts
with the CPU, such as the one we're currently bodging around with the
TCR.
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/arm-smmu-impl.c | 2 +-
drivers/iommu/arm-smmu.c | 157 ++++++++++++------------
drivers/iommu/arm-smmu.h | 217 +++++++++++++++++-----------------
drivers/iommu/qcom_iommu.c | 16 +--
4 files changed, 204 insertions(+), 188 deletions(-)
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index b2fe72a8f019..74d97a886e93 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -119,7 +119,7 @@ int arm_mmu500_reset(struct arm_smmu_device *smmu)
* Secure has also cleared SACR.CACHE_LOCK for this to take effect...
*/
reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID7);
- major = FIELD_GET(ID7_MAJOR, reg);
+ major = FIELD_GET(ARM_SMMU_ID7_MAJOR, reg);
reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sACR);
if (major >= 2)
reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index e65eb60812ec..214be09f6ded 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -271,7 +271,7 @@ static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
reg = arm_smmu_readl(smmu, page, status);
- if (!(reg & sTLBGSTATUS_GSACTIVE))
+ if (!(reg & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
return;
cpu_relax();
}
@@ -478,7 +478,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
int idx = smmu_domain->cfg.cbndx;
fsr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSR);
- if (!(fsr & FSR_FAULT))
+ if (!(fsr & ARM_SMMU_FSR_FAULT))
return IRQ_NONE;
fsynr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSYNR0);
@@ -510,7 +510,7 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
if (__ratelimit(&rs)) {
if (IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT) &&
- (gfsr & sGFSR_USF))
+ (gfsr & ARM_SMMU_sGFSR_USF))
dev_err(smmu->dev,
"Blocked unknown Stream ID 0x%hx; boot with \"arm-smmu.disable_bypass=0\" to allow, but this may have security implications\n",
(u16)gfsynr1);
@@ -543,9 +543,9 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
cb->tcr[0] = arm_smmu_lpae_tcr(pgtbl_cfg);
cb->tcr[1] = arm_smmu_lpae_tcr2(pgtbl_cfg);
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
- cb->tcr[1] |= TCR2_AS;
+ cb->tcr[1] |= ARM_SMMU_TCR2_AS;
else
- cb->tcr[0] |= TCR_EAE;
+ cb->tcr[0] |= ARM_SMMU_TCR_EAE;
}
} else {
cb->tcr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
@@ -558,8 +558,10 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
cb->ttbr[1] = 0;
} else {
cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
- cb->ttbr[0] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
- cb->ttbr[1] = FIELD_PREP(TTBRn_ASID, cfg->asid);
+ cb->ttbr[0] |= FIELD_PREP(ARM_SMMU_TTBRn_ASID,
+ cfg->asid);
+ cb->ttbr[1] = FIELD_PREP(ARM_SMMU_TTBRn_ASID,
+ cfg->asid);
}
} else {
cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
@@ -595,31 +597,33 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
/* CBA2R */
if (smmu->version > ARM_SMMU_V1) {
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
- reg = CBA2R_VA64;
+ reg = ARM_SMMU_CBA2R_VA64;
else
reg = 0;
/* 16-bit VMIDs live in CBA2R */
if (smmu->features & ARM_SMMU_FEAT_VMID16)
- reg |= FIELD_PREP(CBA2R_VMID16, cfg->vmid);
+ reg |= FIELD_PREP(ARM_SMMU_CBA2R_VMID16, cfg->vmid);
arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBA2R(idx), reg);
}
/* CBAR */
- reg = FIELD_PREP(CBAR_TYPE, cfg->cbar);
+ reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, cfg->cbar);
if (smmu->version < ARM_SMMU_V2)
- reg |= FIELD_PREP(CBAR_IRPTNDX, cfg->irptndx);
+ reg |= FIELD_PREP(ARM_SMMU_CBAR_IRPTNDX, cfg->irptndx);
/*
* Use the weakest shareability/memory types, so they are
* overridden by the ttbcr/pte.
*/
if (stage1) {
- reg |= FIELD_PREP(CBAR_S1_BPSHCFG, CBAR_S1_BPSHCFG_NSH) |
- FIELD_PREP(CBAR_S1_MEMATTR, CBAR_S1_MEMATTR_WB);
+ reg |= FIELD_PREP(ARM_SMMU_CBAR_S1_BPSHCFG,
+ ARM_SMMU_CBAR_S1_BPSHCFG_NSH) |
+ FIELD_PREP(ARM_SMMU_CBAR_S1_MEMATTR,
+ ARM_SMMU_CBAR_S1_MEMATTR_WB);
} else if (!(smmu->features & ARM_SMMU_FEAT_VMID16)) {
/* 8-bit VMIDs live in CBAR */
- reg |= FIELD_PREP(CBAR_VMID, cfg->vmid);
+ reg |= FIELD_PREP(ARM_SMMU_CBAR_VMID, cfg->vmid);
}
arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(idx), reg);
@@ -651,11 +655,12 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
}
/* SCTLR */
- reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE | SCTLR_M;
+ reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE | ARM_SMMU_SCTLR_AFE |
+ ARM_SMMU_SCTLR_TRE | ARM_SMMU_SCTLR_M;
if (stage1)
- reg |= SCTLR_S1_ASIDPNE;
+ reg |= ARM_SMMU_SCTLR_S1_ASIDPNE;
if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
- reg |= SCTLR_E;
+ reg |= ARM_SMMU_SCTLR_E;
arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg);
}
@@ -837,7 +842,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
if (ret < 0) {
dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
cfg->irptndx, irq);
- cfg->irptndx = INVALID_IRPTNDX;
+ cfg->irptndx = ARM_SMMU_INVALID_IRPTNDX;
}
mutex_unlock(&smmu_domain->init_mutex);
@@ -875,7 +880,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
smmu->cbs[cfg->cbndx].cfg = NULL;
arm_smmu_write_context_bank(smmu, cfg->cbndx);
- if (cfg->irptndx != INVALID_IRPTNDX) {
+ if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) {
irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
devm_free_irq(smmu->dev, irq, domain);
}
@@ -931,23 +936,24 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
static void arm_smmu_write_smr(struct arm_smmu_device *smmu, int idx)
{
struct arm_smmu_smr *smr = smmu->smrs + idx;
- u32 reg = FIELD_PREP(SMR_ID, smr->id) | FIELD_PREP(SMR_MASK, smr->mask);
+ u32 reg = FIELD_PREP(ARM_SMMU_SMR_ID, smr->id) |
+ FIELD_PREP(ARM_SMMU_SMR_MASK, smr->mask);
if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid)
- reg |= SMR_VALID;
+ reg |= ARM_SMMU_SMR_VALID;
arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(idx), reg);
}
static void arm_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx)
{
struct arm_smmu_s2cr *s2cr = smmu->s2crs + idx;
- u32 reg = FIELD_PREP(S2CR_TYPE, s2cr->type) |
- FIELD_PREP(S2CR_CBNDX, s2cr->cbndx) |
- FIELD_PREP(S2CR_PRIVCFG, s2cr->privcfg);
+ u32 reg = FIELD_PREP(ARM_SMMU_S2CR_TYPE, s2cr->type) |
+ FIELD_PREP(ARM_SMMU_S2CR_CBNDX, s2cr->cbndx) |
+ FIELD_PREP(ARM_SMMU_S2CR_PRIVCFG, s2cr->privcfg);
if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs &&
smmu->smrs[idx].valid)
- reg |= S2CR_EXIDVALID;
+ reg |= ARM_SMMU_S2CR_EXIDVALID;
arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_S2CR(idx), reg);
}
@@ -974,15 +980,15 @@ static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu)
* bits are set, so check each one separately. We can reject
* masters later if they try to claim IDs outside these masks.
*/
- smr = FIELD_PREP(SMR_ID, smmu->streamid_mask);
+ smr = FIELD_PREP(ARM_SMMU_SMR_ID, smmu->streamid_mask);
arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(0), smr);
smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(0));
- smmu->streamid_mask = FIELD_GET(SMR_ID, smr);
+ smmu->streamid_mask = FIELD_GET(ARM_SMMU_SMR_ID, smr);
- smr = FIELD_PREP(SMR_MASK, smmu->streamid_mask);
+ smr = FIELD_PREP(ARM_SMMU_SMR_MASK, smmu->streamid_mask);
arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(0), smr);
smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(0));
- smmu->smr_mask_mask = FIELD_GET(SMR_MASK, smr);
+ smmu->smr_mask_mask = FIELD_GET(ARM_SMMU_SMR_MASK, smr);
}
static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask)
@@ -1051,8 +1057,8 @@ static int arm_smmu_master_alloc_smes(struct device *dev)
mutex_lock(&smmu->stream_map_mutex);
/* Figure out a viable stream map entry allocation */
for_each_cfg_sme(fwspec, i, idx) {
- u16 sid = FIELD_GET(SMR_ID, fwspec->ids[i]);
- u16 mask = FIELD_GET(SMR_MASK, fwspec->ids[i]);
+ u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
+ u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]);
if (idx != INVALID_SMENDX) {
ret = -EEXIST;
@@ -1296,7 +1302,8 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_ATS1PR, va);
reg = arm_smmu_page(smmu, ARM_SMMU_CB(smmu, idx)) + ARM_SMMU_CB_ATSR;
- if (readl_poll_timeout_atomic(reg, tmp, !(tmp & ATSR_ACTIVE), 5, 50)) {
+ if (readl_poll_timeout_atomic(reg, tmp, !(tmp & ARM_SMMU_ATSR_ACTIVE),
+ 5, 50)) {
spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
dev_err(dev,
"iova to phys timed out on %pad. Falling back to software table walk.\n",
@@ -1306,7 +1313,7 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
phys = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_PAR);
spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
- if (phys & CB_PAR_F) {
+ if (phys & ARM_SMMU_CB_PAR_F) {
dev_err(dev, "translation fault!\n");
dev_err(dev, "PAR = 0x%llx\n", phys);
return 0;
@@ -1387,8 +1394,8 @@ static int arm_smmu_add_device(struct device *dev)
ret = -EINVAL;
for (i = 0; i < fwspec->num_ids; i++) {
- u16 sid = FIELD_GET(SMR_ID, fwspec->ids[i]);
- u16 mask = FIELD_GET(SMR_MASK, fwspec->ids[i]);
+ u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
+ u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]);
if (sid & ~smmu->streamid_mask) {
dev_err(dev, "stream ID 0x%x out of range for SMMU (0x%x)\n",
@@ -1569,12 +1576,12 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
u32 mask, fwid = 0;
if (args->args_count > 0)
- fwid |= FIELD_PREP(SMR_ID, args->args[0]);
+ fwid |= FIELD_PREP(ARM_SMMU_SMR_ID, args->args[0]);
if (args->args_count > 1)
- fwid |= FIELD_PREP(SMR_MASK, args->args[1]);
+ fwid |= FIELD_PREP(ARM_SMMU_SMR_MASK, args->args[1]);
else if (!of_property_read_u32(args->np, "stream-match-mask", &mask))
- fwid |= FIELD_PREP(SMR_MASK, mask);
+ fwid |= FIELD_PREP(ARM_SMMU_SMR_MASK, mask);
return iommu_fwspec_add_ids(dev, &fwid, 1);
}
@@ -1644,7 +1651,7 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
/* Make sure all context banks are disabled and clear CB_FSR */
for (i = 0; i < smmu->num_context_banks; ++i) {
arm_smmu_write_context_bank(smmu, i);
- arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_FSR, FSR_FAULT);
+ arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_FSR, ARM_SMMU_FSR_FAULT);
}
/* Invalidate the TLB, just in case */
@@ -1654,29 +1661,30 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sCR0);
/* Enable fault reporting */
- reg |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE);
+ reg |= (ARM_SMMU_sCR0_GFRE | ARM_SMMU_sCR0_GFIE |
+ ARM_SMMU_sCR0_GCFGFRE | ARM_SMMU_sCR0_GCFGFIE);
/* Disable TLB broadcasting. */
- reg |= (sCR0_VMIDPNE | sCR0_PTM);
+ reg |= (ARM_SMMU_sCR0_VMIDPNE | ARM_SMMU_sCR0_PTM);
/* Enable client access, handling unmatched streams as appropriate */
- reg &= ~sCR0_CLIENTPD;
+ reg &= ~ARM_SMMU_sCR0_CLIENTPD;
if (disable_bypass)
- reg |= sCR0_USFCFG;
+ reg |= ARM_SMMU_sCR0_USFCFG;
else
- reg &= ~sCR0_USFCFG;
+ reg &= ~ARM_SMMU_sCR0_USFCFG;
/* Disable forced broadcasting */
- reg &= ~sCR0_FB;
+ reg &= ~ARM_SMMU_sCR0_FB;
/* Don't upgrade barriers */
- reg &= ~(sCR0_BSU);
+ reg &= ~(ARM_SMMU_sCR0_BSU);
if (smmu->features & ARM_SMMU_FEAT_VMID16)
- reg |= sCR0_VMID16EN;
+ reg |= ARM_SMMU_sCR0_VMID16EN;
if (smmu->features & ARM_SMMU_FEAT_EXIDS)
- reg |= sCR0_EXIDENABLE;
+ reg |= ARM_SMMU_sCR0_EXIDENABLE;
if (smmu->impl && smmu->impl->reset)
smmu->impl->reset(smmu);
@@ -1721,21 +1729,21 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
/* Restrict available stages based on module parameter */
if (force_stage == 1)
- id &= ~(ID0_S2TS | ID0_NTS);
+ id &= ~(ARM_SMMU_ID0_S2TS | ARM_SMMU_ID0_NTS);
else if (force_stage == 2)
- id &= ~(ID0_S1TS | ID0_NTS);
+ id &= ~(ARM_SMMU_ID0_S1TS | ARM_SMMU_ID0_NTS);
- if (id & ID0_S1TS) {
+ if (id & ARM_SMMU_ID0_S1TS) {
smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
dev_notice(smmu->dev, "\tstage 1 translation\n");
}
- if (id & ID0_S2TS) {
+ if (id & ARM_SMMU_ID0_S2TS) {
smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
dev_notice(smmu->dev, "\tstage 2 translation\n");
}
- if (id & ID0_NTS) {
+ if (id & ARM_SMMU_ID0_NTS) {
smmu->features |= ARM_SMMU_FEAT_TRANS_NESTED;
dev_notice(smmu->dev, "\tnested translation\n");
}
@@ -1746,8 +1754,8 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
return -ENODEV;
}
- if ((id & ID0_S1TS) &&
- ((smmu->version < ARM_SMMU_V2) || !(id & ID0_ATOSNS))) {
+ if ((id & ARM_SMMU_ID0_S1TS) &&
+ ((smmu->version < ARM_SMMU_V2) || !(id & ARM_SMMU_ID0_ATOSNS))) {
smmu->features |= ARM_SMMU_FEAT_TRANS_OPS;
dev_notice(smmu->dev, "\taddress translation ops\n");
}
@@ -1758,7 +1766,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
* Fortunately, this also opens up a workaround for systems where the
* ID register value has ended up configured incorrectly.
*/
- cttw_reg = !!(id & ID0_CTTW);
+ cttw_reg = !!(id & ARM_SMMU_ID0_CTTW);
if (cttw_fw || cttw_reg)
dev_notice(smmu->dev, "\t%scoherent table walk\n",
cttw_fw ? "" : "non-");
@@ -1767,16 +1775,16 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
"\t(IDR0.CTTW overridden by FW configuration)\n");
/* Max. number of entries we have for stream matching/indexing */
- if (smmu->version == ARM_SMMU_V2 && id & ID0_EXIDS) {
+ if (smmu->version == ARM_SMMU_V2 && id & ARM_SMMU_ID0_EXIDS) {
smmu->features |= ARM_SMMU_FEAT_EXIDS;
size = 1 << 16;
} else {
- size = 1 << FIELD_GET(ID0_NUMSIDB, id);
+ size = 1 << FIELD_GET(ARM_SMMU_ID0_NUMSIDB, id);
}
smmu->streamid_mask = size - 1;
- if (id & ID0_SMS) {
+ if (id & ARM_SMMU_ID0_SMS) {
smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
- size = FIELD_GET(ID0_NUMSMRG, id);
+ size = FIELD_GET(ARM_SMMU_ID0_NUMSMRG, id);
if (size == 0) {
dev_err(smmu->dev,
"stream-matching supported, but no SMRs present!\n");
@@ -1804,18 +1812,19 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
mutex_init(&smmu->stream_map_mutex);
spin_lock_init(&smmu->global_sync_lock);
- if (smmu->version < ARM_SMMU_V2 || !(id & ID0_PTFS_NO_AARCH32)) {
+ if (smmu->version < ARM_SMMU_V2 ||
+ !(id & ARM_SMMU_ID0_PTFS_NO_AARCH32)) {
smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_L;
- if (!(id & ID0_PTFS_NO_AARCH32S))
+ if (!(id & ARM_SMMU_ID0_PTFS_NO_AARCH32S))
smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_S;
}
/* ID1 */
id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID1);
- smmu->pgshift = (id & ID1_PAGESIZE) ? 16 : 12;
+ smmu->pgshift = (id & ARM_SMMU_ID1_PAGESIZE) ? 16 : 12;
/* Check for size mismatch of SMMU address space from mapped region */
- size = 1 << (FIELD_GET(ID1_NUMPAGENDXB, id) + 1);
+ size = 1 << (FIELD_GET(ARM_SMMU_ID1_NUMPAGENDXB, id) + 1);
if (smmu->numpage != 2 * size << smmu->pgshift)
dev_warn(smmu->dev,
"SMMU address space size (0x%x) differs from mapped region size (0x%x)!\n",
@@ -1823,8 +1832,8 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
/* Now properly encode NUMPAGE to subsequently derive SMMU_CB_BASE */
smmu->numpage = size;
- smmu->num_s2_context_banks = FIELD_GET(ID1_NUMS2CB, id);
- smmu->num_context_banks = FIELD_GET(ID1_NUMCB, id);
+ smmu->num_s2_context_banks = FIELD_GET(ARM_SMMU_ID1_NUMS2CB, id);
+ smmu->num_context_banks = FIELD_GET(ARM_SMMU_ID1_NUMCB, id);
if (smmu->num_s2_context_banks > smmu->num_context_banks) {
dev_err(smmu->dev, "impossible number of S2 context banks!\n");
return -ENODEV;
@@ -1838,14 +1847,14 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
/* ID2 */
id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID2);
- size = arm_smmu_id_size_to_bits(FIELD_GET(ID2_IAS, id));
+ size = arm_smmu_id_size_to_bits(FIELD_GET(ARM_SMMU_ID2_IAS, id));
smmu->ipa_size = size;
/* The output mask is also applied for bypass */
- size = arm_smmu_id_size_to_bits(FIELD_GET(ID2_OAS, id));
+ size = arm_smmu_id_size_to_bits(FIELD_GET(ARM_SMMU_ID2_OAS, id));
smmu->pa_size = size;
- if (id & ID2_VMID16)
+ if (id & ARM_SMMU_ID2_VMID16)
smmu->features |= ARM_SMMU_FEAT_VMID16;
/*
@@ -1862,13 +1871,13 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
if (smmu->version == ARM_SMMU_V1_64K)
smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K;
} else {
- size = FIELD_GET(ID2_UBS, id);
+ size = FIELD_GET(ARM_SMMU_ID2_UBS, id);
smmu->va_size = arm_smmu_id_size_to_bits(size);
- if (id & ID2_PTFS_4K)
+ if (id & ARM_SMMU_ID2_PTFS_4K)
smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_4K;
- if (id & ID2_PTFS_16K)
+ if (id & ARM_SMMU_ID2_PTFS_16K)
smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_16K;
- if (id & ID2_PTFS_64K)
+ if (id & ARM_SMMU_ID2_PTFS_64K)
smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K;
}
@@ -2245,7 +2254,7 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
arm_smmu_rpm_get(smmu);
/* Turn the thing off */
- arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, sCR0_CLIENTPD);
+ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, ARM_SMMU_sCR0_CLIENTPD);
arm_smmu_rpm_put(smmu);
if (pm_runtime_enabled(smmu->dev))
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index aade2b0ae175..6501f38a5966 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -24,51 +24,51 @@
/* Configuration registers */
#define ARM_SMMU_GR0_sCR0 0x0
-#define sCR0_VMID16EN BIT(31)
-#define sCR0_BSU GENMASK(15, 14)
-#define sCR0_FB BIT(13)
-#define sCR0_PTM BIT(12)
-#define sCR0_VMIDPNE BIT(11)
-#define sCR0_USFCFG BIT(10)
-#define sCR0_GCFGFIE BIT(5)
-#define sCR0_GCFGFRE BIT(4)
-#define sCR0_EXIDENABLE BIT(3)
-#define sCR0_GFIE BIT(2)
-#define sCR0_GFRE BIT(1)
-#define sCR0_CLIENTPD BIT(0)
+#define ARM_SMMU_sCR0_VMID16EN BIT(31)
+#define ARM_SMMU_sCR0_BSU GENMASK(15, 14)
+#define ARM_SMMU_sCR0_FB BIT(13)
+#define ARM_SMMU_sCR0_PTM BIT(12)
+#define ARM_SMMU_sCR0_VMIDPNE BIT(11)
+#define ARM_SMMU_sCR0_USFCFG BIT(10)
+#define ARM_SMMU_sCR0_GCFGFIE BIT(5)
+#define ARM_SMMU_sCR0_GCFGFRE BIT(4)
+#define ARM_SMMU_sCR0_EXIDENABLE BIT(3)
+#define ARM_SMMU_sCR0_GFIE BIT(2)
+#define ARM_SMMU_sCR0_GFRE BIT(1)
+#define ARM_SMMU_sCR0_CLIENTPD BIT(0)
/* Auxiliary Configuration register */
#define ARM_SMMU_GR0_sACR 0x10
/* Identification registers */
#define ARM_SMMU_GR0_ID0 0x20
-#define ID0_S1TS BIT(30)
-#define ID0_S2TS BIT(29)
-#define ID0_NTS BIT(28)
-#define ID0_SMS BIT(27)
-#define ID0_ATOSNS BIT(26)
-#define ID0_PTFS_NO_AARCH32 BIT(25)
-#define ID0_PTFS_NO_AARCH32S BIT(24)
-#define ID0_NUMIRPT GENMASK(23, 16)
-#define ID0_CTTW BIT(14)
-#define ID0_NUMSIDB GENMASK(12, 9)
-#define ID0_EXIDS BIT(8)
-#define ID0_NUMSMRG GENMASK(7, 0)
+#define ARM_SMMU_ID0_S1TS BIT(30)
+#define ARM_SMMU_ID0_S2TS BIT(29)
+#define ARM_SMMU_ID0_NTS BIT(28)
+#define ARM_SMMU_ID0_SMS BIT(27)
+#define ARM_SMMU_ID0_ATOSNS BIT(26)
+#define ARM_SMMU_ID0_PTFS_NO_AARCH32 BIT(25)
+#define ARM_SMMU_ID0_PTFS_NO_AARCH32S BIT(24)
+#define ARM_SMMU_ID0_NUMIRPT GENMASK(23, 16)
+#define ARM_SMMU_ID0_CTTW BIT(14)
+#define ARM_SMMU_ID0_NUMSIDB GENMASK(12, 9)
+#define ARM_SMMU_ID0_EXIDS BIT(8)
+#define ARM_SMMU_ID0_NUMSMRG GENMASK(7, 0)
#define ARM_SMMU_GR0_ID1 0x24
-#define ID1_PAGESIZE BIT(31)
-#define ID1_NUMPAGENDXB GENMASK(30, 28)
-#define ID1_NUMS2CB GENMASK(23, 16)
-#define ID1_NUMCB GENMASK(7, 0)
+#define ARM_SMMU_ID1_PAGESIZE BIT(31)
+#define ARM_SMMU_ID1_NUMPAGENDXB GENMASK(30, 28)
+#define ARM_SMMU_ID1_NUMS2CB GENMASK(23, 16)
+#define ARM_SMMU_ID1_NUMCB GENMASK(7, 0)
#define ARM_SMMU_GR0_ID2 0x28
-#define ID2_VMID16 BIT(15)
-#define ID2_PTFS_64K BIT(14)
-#define ID2_PTFS_16K BIT(13)
-#define ID2_PTFS_4K BIT(12)
-#define ID2_UBS GENMASK(11, 8)
-#define ID2_OAS GENMASK(7, 4)
-#define ID2_IAS GENMASK(3, 0)
+#define ARM_SMMU_ID2_VMID16 BIT(15)
+#define ARM_SMMU_ID2_PTFS_64K BIT(14)
+#define ARM_SMMU_ID2_PTFS_16K BIT(13)
+#define ARM_SMMU_ID2_PTFS_4K BIT(12)
+#define ARM_SMMU_ID2_UBS GENMASK(11, 8)
+#define ARM_SMMU_ID2_OAS GENMASK(7, 4)
+#define ARM_SMMU_ID2_IAS GENMASK(3, 0)
#define ARM_SMMU_GR0_ID3 0x2c
#define ARM_SMMU_GR0_ID4 0x30
@@ -76,11 +76,11 @@
#define ARM_SMMU_GR0_ID6 0x38
#define ARM_SMMU_GR0_ID7 0x3c
-#define ID7_MAJOR GENMASK(7, 4)
-#define ID7_MINOR GENMASK(3, 0)
+#define ARM_SMMU_ID7_MAJOR GENMASK(7, 4)
+#define ARM_SMMU_ID7_MINOR GENMASK(3, 0)
#define ARM_SMMU_GR0_sGFSR 0x48
-#define sGFSR_USF BIT(1)
+#define ARM_SMMU_sGFSR_USF BIT(1)
#define ARM_SMMU_GR0_sGFSYNR0 0x50
#define ARM_SMMU_GR0_sGFSYNR1 0x54
@@ -93,118 +93,123 @@
#define ARM_SMMU_GR0_sTLBGSYNC 0x70
#define ARM_SMMU_GR0_sTLBGSTATUS 0x74
-#define sTLBGSTATUS_GSACTIVE BIT(0)
+#define ARM_SMMU_sTLBGSTATUS_GSACTIVE BIT(0)
/* Stream mapping registers */
#define ARM_SMMU_GR0_SMR(n) (0x800 + ((n) << 2))
-#define SMR_VALID BIT(31)
-#define SMR_MASK GENMASK(31, 16)
-#define SMR_ID GENMASK(15, 0)
+#define ARM_SMMU_SMR_VALID BIT(31)
+#define ARM_SMMU_SMR_MASK GENMASK(31, 16)
+#define ARM_SMMU_SMR_ID GENMASK(15, 0)
#define ARM_SMMU_GR0_S2CR(n) (0xc00 + ((n) << 2))
-#define S2CR_PRIVCFG GENMASK(25, 24)
+#define ARM_SMMU_S2CR_PRIVCFG GENMASK(25, 24)
enum arm_smmu_s2cr_privcfg {
S2CR_PRIVCFG_DEFAULT,
S2CR_PRIVCFG_DIPAN,
S2CR_PRIVCFG_UNPRIV,
S2CR_PRIVCFG_PRIV,
};
-#define S2CR_TYPE GENMASK(17, 16)
+#define ARM_SMMU_S2CR_TYPE GENMASK(17, 16)
enum arm_smmu_s2cr_type {
S2CR_TYPE_TRANS,
S2CR_TYPE_BYPASS,
S2CR_TYPE_FAULT,
};
-#define S2CR_EXIDVALID BIT(10)
-#define S2CR_CBNDX GENMASK(7, 0)
+#define ARM_SMMU_S2CR_EXIDVALID BIT(10)
+#define ARM_SMMU_S2CR_CBNDX GENMASK(7, 0)
/* Context bank attribute registers */
#define ARM_SMMU_GR1_CBAR(n) (0x0 + ((n) << 2))
-#define CBAR_IRPTNDX GENMASK(31, 24)
-#define CBAR_TYPE GENMASK(17, 16)
+#define ARM_SMMU_CBAR_IRPTNDX GENMASK(31, 24)
+#define ARM_SMMU_CBAR_TYPE GENMASK(17, 16)
enum arm_smmu_cbar_type {
CBAR_TYPE_S2_TRANS,
CBAR_TYPE_S1_TRANS_S2_BYPASS,
CBAR_TYPE_S1_TRANS_S2_FAULT,
CBAR_TYPE_S1_TRANS_S2_TRANS,
};
-#define CBAR_S1_MEMATTR GENMASK(15, 12)
-#define CBAR_S1_MEMATTR_WB 0xf
-#define CBAR_S1_BPSHCFG GENMASK(9, 8)
-#define CBAR_S1_BPSHCFG_NSH 3
-#define CBAR_VMID GENMASK(7, 0)
+#define ARM_SMMU_CBAR_S1_MEMATTR GENMASK(15, 12)
+#define ARM_SMMU_CBAR_S1_MEMATTR_WB 0xf
+#define ARM_SMMU_CBAR_S1_BPSHCFG GENMASK(9, 8)
+#define ARM_SMMU_CBAR_S1_BPSHCFG_NSH 3
+#define ARM_SMMU_CBAR_VMID GENMASK(7, 0)
#define ARM_SMMU_GR1_CBFRSYNRA(n) (0x400 + ((n) << 2))
#define ARM_SMMU_GR1_CBA2R(n) (0x800 + ((n) << 2))
-#define CBA2R_VMID16 GENMASK(31, 16)
-#define CBA2R_VA64 BIT(0)
+#define ARM_SMMU_CBA2R_VMID16 GENMASK(31, 16)
+#define ARM_SMMU_CBA2R_VA64 BIT(0)
#define ARM_SMMU_CB_SCTLR 0x0
-#define SCTLR_S1_ASIDPNE BIT(12)
-#define SCTLR_CFCFG BIT(7)
-#define SCTLR_CFIE BIT(6)
-#define SCTLR_CFRE BIT(5)
-#define SCTLR_E BIT(4)
-#define SCTLR_AFE BIT(2)
-#define SCTLR_TRE BIT(1)
-#define SCTLR_M BIT(0)
+#define ARM_SMMU_SCTLR_S1_ASIDPNE BIT(12)
+#define ARM_SMMU_SCTLR_CFCFG BIT(7)
+#define ARM_SMMU_SCTLR_CFIE BIT(6)
+#define ARM_SMMU_SCTLR_CFRE BIT(5)
+#define ARM_SMMU_SCTLR_E BIT(4)
+#define ARM_SMMU_SCTLR_AFE BIT(2)
+#define ARM_SMMU_SCTLR_TRE BIT(1)
+#define ARM_SMMU_SCTLR_M BIT(0)
#define ARM_SMMU_CB_ACTLR 0x4
#define ARM_SMMU_CB_RESUME 0x8
-#define RESUME_TERMINATE BIT(0)
+#define ARM_SMMU_RESUME_TERMINATE BIT(0)
#define ARM_SMMU_CB_TCR2 0x10
-#define TCR2_SEP GENMASK(17, 15)
-#define TCR2_SEP_UPSTREAM 0x7
-#define TCR2_AS BIT(4)
-#define TCR2_PASIZE GENMASK(3, 0)
+#define ARM_SMMU_TCR2_SEP GENMASK(17, 15)
+#define ARM_SMMU_TCR2_SEP_UPSTREAM 0x7
+#define ARM_SMMU_TCR2_AS BIT(4)
+#define ARM_SMMU_TCR2_PASIZE GENMASK(3, 0)
#define ARM_SMMU_CB_TTBR0 0x20
#define ARM_SMMU_CB_TTBR1 0x28
-#define TTBRn_ASID GENMASK_ULL(63, 48)
-
-/* arm64 headers leak this somehow :( */
-#undef TCR_T0SZ
+#define ARM_SMMU_TTBRn_ASID GENMASK_ULL(63, 48)
#define ARM_SMMU_CB_TCR 0x30
-#define TCR_EAE BIT(31)
-#define TCR_EPD1 BIT(23)
-#define TCR_TG0 GENMASK(15, 14)
-#define TCR_SH0 GENMASK(13, 12)
-#define TCR_ORGN0 GENMASK(11, 10)
-#define TCR_IRGN0 GENMASK(9, 8)
-#define TCR_T0SZ GENMASK(5, 0)
+#define ARM_SMMU_TCR_EAE BIT(31)
+#define ARM_SMMU_TCR_EPD1 BIT(23)
+#define ARM_SMMU_TCR_TG0 GENMASK(15, 14)
+#define ARM_SMMU_TCR_SH0 GENMASK(13, 12)
+#define ARM_SMMU_TCR_ORGN0 GENMASK(11, 10)
+#define ARM_SMMU_TCR_IRGN0 GENMASK(9, 8)
+#define ARM_SMMU_TCR_T0SZ GENMASK(5, 0)
#define ARM_SMMU_CB_CONTEXTIDR 0x34
#define ARM_SMMU_CB_S1_MAIR0 0x38
#define ARM_SMMU_CB_S1_MAIR1 0x3c
#define ARM_SMMU_CB_PAR 0x50
-#define CB_PAR_F BIT(0)
+#define ARM_SMMU_CB_PAR_F BIT(0)
#define ARM_SMMU_CB_FSR 0x58
-#define FSR_MULTI BIT(31)
-#define FSR_SS BIT(30)
-#define FSR_UUT BIT(8)
-#define FSR_ASF BIT(7)
-#define FSR_TLBLKF BIT(6)
-#define FSR_TLBMCF BIT(5)
-#define FSR_EF BIT(4)
-#define FSR_PF BIT(3)
-#define FSR_AFF BIT(2)
-#define FSR_TF BIT(1)
-
-#define FSR_IGN (FSR_AFF | FSR_ASF | \
- FSR_TLBMCF | FSR_TLBLKF)
-#define FSR_FAULT (FSR_MULTI | FSR_SS | FSR_UUT | \
- FSR_EF | FSR_PF | FSR_TF | FSR_IGN)
+#define ARM_SMMU_FSR_MULTI BIT(31)
+#define ARM_SMMU_FSR_SS BIT(30)
+#define ARM_SMMU_FSR_UUT BIT(8)
+#define ARM_SMMU_FSR_ASF BIT(7)
+#define ARM_SMMU_FSR_TLBLKF BIT(6)
+#define ARM_SMMU_FSR_TLBMCF BIT(5)
+#define ARM_SMMU_FSR_EF BIT(4)
+#define ARM_SMMU_FSR_PF BIT(3)
+#define ARM_SMMU_FSR_AFF BIT(2)
+#define ARM_SMMU_FSR_TF BIT(1)
+
+#define ARM_SMMU_FSR_IGN (ARM_SMMU_FSR_AFF | \
+ ARM_SMMU_FSR_ASF | \
+ ARM_SMMU_FSR_TLBMCF | \
+ ARM_SMMU_FSR_TLBLKF)
+
+#define ARM_SMMU_FSR_FAULT (ARM_SMMU_FSR_MULTI | \
+ ARM_SMMU_FSR_SS | \
+ ARM_SMMU_FSR_UUT | \
+ ARM_SMMU_FSR_EF | \
+ ARM_SMMU_FSR_PF | \
+ ARM_SMMU_FSR_TF | \
+ ARM_SMMU_FSR_IGN)
#define ARM_SMMU_CB_FAR 0x60
#define ARM_SMMU_CB_FSYNR0 0x68
-#define FSYNR0_WNR BIT(4)
+#define ARM_SMMU_FSYNR0_WNR BIT(4)
#define ARM_SMMU_CB_S1_TLBIVA 0x600
#define ARM_SMMU_CB_S1_TLBIASID 0x610
@@ -216,7 +221,7 @@ enum arm_smmu_cbar_type {
#define ARM_SMMU_CB_ATS1PR 0x800
#define ARM_SMMU_CB_ATSR 0x8f0
-#define ATSR_ACTIVE BIT(0)
+#define ARM_SMMU_ATSR_ACTIVE BIT(0)
/* Maximum number of context banks per SMMU */
@@ -310,7 +315,7 @@ struct arm_smmu_cfg {
enum arm_smmu_cbar_type cbar;
enum arm_smmu_context_fmt fmt;
};
-#define INVALID_IRPTNDX 0xff
+#define ARM_SMMU_INVALID_IRPTNDX 0xff
enum arm_smmu_domain_stage {
ARM_SMMU_DOMAIN_S1 = 0,
@@ -333,18 +338,18 @@ struct arm_smmu_domain {
static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg)
{
- return TCR_EPD1 |
- FIELD_PREP(TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
- FIELD_PREP(TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
- FIELD_PREP(TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
- FIELD_PREP(TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
- FIELD_PREP(TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
+ return ARM_SMMU_TCR_EPD1 |
+ FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
+ FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
+ FIELD_PREP(ARM_SMMU_TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
+ FIELD_PREP(ARM_SMMU_TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
+ FIELD_PREP(ARM_SMMU_TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
}
static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg)
{
- return FIELD_PREP(TCR2_PASIZE, cfg->arm_lpae_s1_cfg.tcr.ips) |
- FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM);
+ return FIELD_PREP(ARM_SMMU_TCR2_PASIZE, cfg->arm_lpae_s1_cfg.tcr.ips) |
+ FIELD_PREP(ARM_SMMU_TCR2_SEP, ARM_SMMU_TCR2_SEP_UPSTREAM);
}
/* Implementation details, yay! */
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 2eeaf2eec946..39759db4f003 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -201,7 +201,7 @@ static irqreturn_t qcom_iommu_fault(int irq, void *dev)
fsr = iommu_readl(ctx, ARM_SMMU_CB_FSR);
- if (!(fsr & FSR_FAULT))
+ if (!(fsr & ARM_SMMU_FSR_FAULT))
return IRQ_NONE;
fsynr = iommu_readl(ctx, ARM_SMMU_CB_FSYNR0);
@@ -215,7 +215,7 @@ static irqreturn_t qcom_iommu_fault(int irq, void *dev)
}
iommu_writel(ctx, ARM_SMMU_CB_FSR, fsr);
- iommu_writel(ctx, ARM_SMMU_CB_RESUME, RESUME_TERMINATE);
+ iommu_writel(ctx, ARM_SMMU_CB_RESUME, ARM_SMMU_RESUME_TERMINATE);
return IRQ_HANDLED;
}
@@ -270,14 +270,14 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
/* TTBRs */
iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
pgtbl_cfg.arm_lpae_s1_cfg.ttbr |
- FIELD_PREP(TTBRn_ASID, ctx->asid));
+ FIELD_PREP(ARM_SMMU_TTBRn_ASID, ctx->asid));
iommu_writeq(ctx, ARM_SMMU_CB_TTBR1, 0);
/* TCR */
iommu_writel(ctx, ARM_SMMU_CB_TCR2,
arm_smmu_lpae_tcr2(&pgtbl_cfg));
iommu_writel(ctx, ARM_SMMU_CB_TCR,
- arm_smmu_lpae_tcr(&pgtbl_cfg) | TCR_EAE);
+ arm_smmu_lpae_tcr(&pgtbl_cfg) | ARM_SMMU_TCR_EAE);
/* MAIRs (stage-1 only) */
iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0,
@@ -286,11 +286,13 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
pgtbl_cfg.arm_lpae_s1_cfg.mair >> 32);
/* SCTLR */
- reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE |
- SCTLR_M | SCTLR_S1_ASIDPNE | SCTLR_CFCFG;
+ reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE |
+ ARM_SMMU_SCTLR_AFE | ARM_SMMU_SCTLR_TRE |
+ ARM_SMMU_SCTLR_M | ARM_SMMU_SCTLR_S1_ASIDPNE |
+ ARM_SMMU_SCTLR_CFCFG;
if (IS_ENABLED(CONFIG_BIG_ENDIAN))
- reg |= SCTLR_E;
+ reg |= ARM_SMMU_SCTLR_E;
iommu_writel(ctx, ARM_SMMU_CB_SCTLR, reg);
--
2.25.0.rc1.283.g88dfdc4193-goog
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 7/8] iommu/io-pgtable-arm: Rationalise VTCR handling
2020-01-10 15:28 [PATCH 0/8] Finish off the split page table prep work Will Deacon
` (5 preceding siblings ...)
2020-01-10 15:28 ` [PATCH 6/8] iommu/arm-smmu: Rename public #defines under ARM_SMMU_ namespace Will Deacon
@ 2020-01-10 15:28 ` Will Deacon
2020-01-10 15:28 ` [PATCH 8/8] iommu/io-pgtable-arm: Prepare for TTBR1 usage Will Deacon
7 siblings, 0 replies; 11+ messages in thread
From: Will Deacon @ 2020-01-10 15:28 UTC (permalink / raw)
To: iommu
Cc: Will Deacon, Jordan Crouse, kernel-team, Robin Murphy,
linux-arm-kernel
Commit 05a648cd2dd7 ("iommu/io-pgtable-arm: Rationalise TCR handling")
reworked the way in which the TCR register value is returned from the
io-pgtable code when targetting the Arm long-descriptor format, in
preparation for allowing page-tables to target TTBR1.
As it turns out, the new interface is a lot nicer to use, so do the same
conversion for the VTCR register even though there is only a single base
register for stage-2 translation.
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/arm-smmu-v3.c | 17 +++++++++-
drivers/iommu/arm-smmu.c | 2 +-
drivers/iommu/arm-smmu.h | 21 +++++++++++++
drivers/iommu/io-pgtable-arm.c | 57 +++++++++++++---------------------
include/linux/io-pgtable.h | 10 +++++-
5 files changed, 68 insertions(+), 39 deletions(-)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index d127974afdb7..4443e1890077 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -250,6 +250,13 @@
#define STRTAB_STE_2_S2VMID GENMASK_ULL(15, 0)
#define STRTAB_STE_2_VTCR GENMASK_ULL(50, 32)
+#define STRTAB_STE_2_VTCR_S2T0SZ GENMASK_ULL(5, 0)
+#define STRTAB_STE_2_VTCR_S2SL0 GENMASK_ULL(7, 6)
+#define STRTAB_STE_2_VTCR_S2IR0 GENMASK_ULL(9, 8)
+#define STRTAB_STE_2_VTCR_S2OR0 GENMASK_ULL(11, 10)
+#define STRTAB_STE_2_VTCR_S2SH0 GENMASK_ULL(13, 12)
+#define STRTAB_STE_2_VTCR_S2TG GENMASK_ULL(15, 14)
+#define STRTAB_STE_2_VTCR_S2PS GENMASK_ULL(18, 16)
#define STRTAB_STE_2_S2AA64 (1UL << 51)
#define STRTAB_STE_2_S2ENDI (1UL << 52)
#define STRTAB_STE_2_S2PTW (1UL << 54)
@@ -2159,14 +2166,22 @@ static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
int vmid;
struct arm_smmu_device *smmu = smmu_domain->smmu;
struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
+ typeof(&pgtbl_cfg->arm_lpae_s2_cfg.vtcr) vtcr;
vmid = arm_smmu_bitmap_alloc(smmu->vmid_map, smmu->vmid_bits);
if (vmid < 0)
return vmid;
+ vtcr = &pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
cfg->vmid = (u16)vmid;
cfg->vttbr = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
- cfg->vtcr = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+ cfg->vtcr = FIELD_PREP(STRTAB_STE_2_VTCR_S2T0SZ, vtcr->tsz) |
+ FIELD_PREP(STRTAB_STE_2_VTCR_S2SL0, vtcr->sl) |
+ FIELD_PREP(STRTAB_STE_2_VTCR_S2IR0, vtcr->irgn) |
+ FIELD_PREP(STRTAB_STE_2_VTCR_S2OR0, vtcr->orgn) |
+ FIELD_PREP(STRTAB_STE_2_VTCR_S2SH0, vtcr->sh) |
+ FIELD_PREP(STRTAB_STE_2_VTCR_S2TG, vtcr->tg) |
+ FIELD_PREP(STRTAB_STE_2_VTCR_S2PS, vtcr->ps);
return 0;
}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 214be09f6ded..f067783ebd59 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -548,7 +548,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
cb->tcr[0] |= ARM_SMMU_TCR_EAE;
}
} else {
- cb->tcr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+ cb->tcr[0] = arm_smmu_lpae_vtcr(pgtbl_cfg);
}
/* TTBRs */
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 6501f38a5966..8d1cd54d82a6 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -174,6 +174,15 @@ enum arm_smmu_cbar_type {
#define ARM_SMMU_TCR_IRGN0 GENMASK(9, 8)
#define ARM_SMMU_TCR_T0SZ GENMASK(5, 0)
+#define ARM_SMMU_VTCR_RES1 BIT(31)
+#define ARM_SMMU_VTCR_PS GENMASK(18, 16)
+#define ARM_SMMU_VTCR_TG0 ARM_SMMU_TCR_TG0
+#define ARM_SMMU_VTCR_SH0 ARM_SMMU_TCR_SH0
+#define ARM_SMMU_VTCR_ORGN0 ARM_SMMU_TCR_ORGN0
+#define ARM_SMMU_VTCR_IRGN0 ARM_SMMU_TCR_IRGN0
+#define ARM_SMMU_VTCR_SL0 GENMASK(7, 6)
+#define ARM_SMMU_VTCR_T0SZ ARM_SMMU_TCR_T0SZ
+
#define ARM_SMMU_CB_CONTEXTIDR 0x34
#define ARM_SMMU_CB_S1_MAIR0 0x38
#define ARM_SMMU_CB_S1_MAIR1 0x3c
@@ -352,6 +361,18 @@ static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg)
FIELD_PREP(ARM_SMMU_TCR2_SEP, ARM_SMMU_TCR2_SEP_UPSTREAM);
}
+static inline u32 arm_smmu_lpae_vtcr(struct io_pgtable_cfg *cfg)
+{
+ return ARM_SMMU_VTCR_RES1 |
+ FIELD_PREP(ARM_SMMU_VTCR_PS, cfg->arm_lpae_s2_cfg.vtcr.ps) |
+ FIELD_PREP(ARM_SMMU_VTCR_TG0, cfg->arm_lpae_s2_cfg.vtcr.tg) |
+ FIELD_PREP(ARM_SMMU_VTCR_SH0, cfg->arm_lpae_s2_cfg.vtcr.sh) |
+ FIELD_PREP(ARM_SMMU_VTCR_ORGN0, cfg->arm_lpae_s2_cfg.vtcr.orgn) |
+ FIELD_PREP(ARM_SMMU_VTCR_IRGN0, cfg->arm_lpae_s2_cfg.vtcr.irgn) |
+ FIELD_PREP(ARM_SMMU_VTCR_SL0, cfg->arm_lpae_s2_cfg.vtcr.sl) |
+ FIELD_PREP(ARM_SMMU_VTCR_T0SZ, cfg->arm_lpae_s2_cfg.vtcr.tsz);
+}
+
/* Implementation details, yay! */
struct arm_smmu_impl {
u32 (*read_reg)(struct arm_smmu_device *smmu, int page, int offset);
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 78ec0ee5c59c..846963c87e0f 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -100,26 +100,19 @@
#define ARM_LPAE_PTE_MEMATTR_DEV (((arm_lpae_iopte)0x1) << 2)
/* Register bits */
-#define ARM_64_LPAE_VTCR_RES1 (1U << 31)
-
-#define ARM_LPAE_VTCR_TG0_SHIFT 14
#define ARM_LPAE_TCR_TG0_4K 0
#define ARM_LPAE_TCR_TG0_64K 1
#define ARM_LPAE_TCR_TG0_16K 2
-#define ARM_LPAE_TCR_SH0_SHIFT 12
#define ARM_LPAE_TCR_SH_NS 0
#define ARM_LPAE_TCR_SH_OS 2
#define ARM_LPAE_TCR_SH_IS 3
-#define ARM_LPAE_TCR_ORGN0_SHIFT 10
-#define ARM_LPAE_TCR_IRGN0_SHIFT 8
#define ARM_LPAE_TCR_RGN_NC 0
#define ARM_LPAE_TCR_RGN_WBWA 1
#define ARM_LPAE_TCR_RGN_WT 2
#define ARM_LPAE_TCR_RGN_WB 3
-#define ARM_LPAE_VTCR_SL0_SHIFT 6
#define ARM_LPAE_VTCR_SL0_MASK 0x3
#define ARM_LPAE_TCR_T0SZ_SHIFT 0
@@ -877,8 +870,9 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
static struct io_pgtable *
arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
{
- u64 reg, sl;
+ u64 sl;
struct arm_lpae_io_pgtable *data;
+ typeof(&cfg->arm_lpae_s2_cfg.vtcr) vtcr = &cfg->arm_lpae_s2_cfg.vtcr;
/* The NS quirk doesn't apply at stage 2 */
if (cfg->quirks & ~(IO_PGTABLE_QUIRK_NON_STRICT))
@@ -903,61 +897,59 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
}
/* VTCR */
- reg = ARM_64_LPAE_VTCR_RES1;
if (cfg->coherent_walk) {
- reg |= (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
- (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
- (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+ vtcr->sh = ARM_LPAE_TCR_SH_IS;
+ vtcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+ vtcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
} else {
- reg |= (ARM_LPAE_TCR_SH_OS << ARM_LPAE_TCR_SH0_SHIFT) |
- (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_IRGN0_SHIFT) |
- (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_ORGN0_SHIFT);
+ vtcr->sh = ARM_LPAE_TCR_SH_OS;
+ vtcr->irgn = ARM_LPAE_TCR_RGN_NC;
+ vtcr->orgn = ARM_LPAE_TCR_RGN_NC;
}
sl = data->start_level;
switch (ARM_LPAE_GRANULE(data)) {
case SZ_4K:
- reg |= (ARM_LPAE_TCR_TG0_4K << ARM_LPAE_VTCR_TG0_SHIFT);
+ vtcr->tg = ARM_LPAE_TCR_TG0_4K;
sl++; /* SL0 format is different for 4K granule size */
break;
case SZ_16K:
- reg |= (ARM_LPAE_TCR_TG0_16K << ARM_LPAE_VTCR_TG0_SHIFT);
+ vtcr->tg = ARM_LPAE_TCR_TG0_16K;
break;
case SZ_64K:
- reg |= (ARM_LPAE_TCR_TG0_64K << ARM_LPAE_VTCR_TG0_SHIFT);
+ vtcr->tg = ARM_LPAE_TCR_TG0_64K;
break;
}
switch (cfg->oas) {
case 32:
- reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+ vtcr->ps = ARM_LPAE_TCR_PS_32_BIT;
break;
case 36:
- reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+ vtcr->ps = ARM_LPAE_TCR_PS_36_BIT;
break;
case 40:
- reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+ vtcr->ps = ARM_LPAE_TCR_PS_40_BIT;
break;
case 42:
- reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+ vtcr->ps = ARM_LPAE_TCR_PS_42_BIT;
break;
case 44:
- reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+ vtcr->ps = ARM_LPAE_TCR_PS_44_BIT;
break;
case 48:
- reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+ vtcr->ps = ARM_LPAE_TCR_PS_48_BIT;
break;
case 52:
- reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_VTCR_PS_SHIFT);
+ vtcr->ps = ARM_LPAE_TCR_PS_52_BIT;
break;
default:
goto out_free_data;
}
- reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
- reg |= (~sl & ARM_LPAE_VTCR_SL0_MASK) << ARM_LPAE_VTCR_SL0_SHIFT;
- cfg->arm_lpae_s2_cfg.vtcr = reg;
+ vtcr->tsz = 64ULL - cfg->ias;
+ vtcr->sl = ~sl & ARM_LPAE_VTCR_SL0_MASK;
/* Allocate pgd pages */
data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
@@ -984,24 +976,17 @@ arm_32_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
return NULL;
cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-
return arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
}
static struct io_pgtable *
arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
{
- struct io_pgtable *iop;
-
if (cfg->ias > 40 || cfg->oas > 40)
return NULL;
cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
- iop = arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
- if (iop)
- cfg->arm_lpae_s2_cfg.vtcr &= 0xffffffff;
-
- return iop;
+ return arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
}
static struct io_pgtable *
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 6ae104cedfd7..40c1b7745fb6 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -114,7 +114,15 @@ struct io_pgtable_cfg {
struct {
u64 vttbr;
- u64 vtcr;
+ struct {
+ u32 ps:3;
+ u32 tg:2;
+ u32 sh:2;
+ u32 orgn:2;
+ u32 irgn:2;
+ u32 sl:2;
+ u32 tsz:6;
+ } vtcr;
} arm_lpae_s2_cfg;
struct {
--
2.25.0.rc1.283.g88dfdc4193-goog
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 8/8] iommu/io-pgtable-arm: Prepare for TTBR1 usage
2020-01-10 15:28 [PATCH 0/8] Finish off the split page table prep work Will Deacon
` (6 preceding siblings ...)
2020-01-10 15:28 ` [PATCH 7/8] iommu/io-pgtable-arm: Rationalise VTCR handling Will Deacon
@ 2020-01-10 15:28 ` Will Deacon
2020-02-19 12:27 ` Stephan Gerhold
7 siblings, 1 reply; 11+ messages in thread
From: Will Deacon @ 2020-01-10 15:28 UTC (permalink / raw)
To: iommu
Cc: Will Deacon, Jordan Crouse, kernel-team, Robin Murphy,
linux-arm-kernel
From: Robin Murphy <robin.murphy@arm.com>
Now that we can correctly extract top-level indices without relying on
the remaining upper bits being zero, the only remaining impediments to
using a given table for TTBR1 are the address validation on map/unmap
and the awkward TCR translation granule format. Add a quirk so that we
can do the right thing at those points.
Tested-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/io-pgtable-arm.c | 25 +++++++++++++++++++------
include/linux/io-pgtable.h | 4 ++++
2 files changed, 23 insertions(+), 6 deletions(-)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 846963c87e0f..5e966ef0bacf 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -104,6 +104,10 @@
#define ARM_LPAE_TCR_TG0_64K 1
#define ARM_LPAE_TCR_TG0_16K 2
+#define ARM_LPAE_TCR_TG1_16K 1
+#define ARM_LPAE_TCR_TG1_4K 2
+#define ARM_LPAE_TCR_TG1_64K 3
+
#define ARM_LPAE_TCR_SH_NS 0
#define ARM_LPAE_TCR_SH_OS 2
#define ARM_LPAE_TCR_SH_IS 3
@@ -463,6 +467,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
arm_lpae_iopte *ptep = data->pgd;
int ret, lvl = data->start_level;
arm_lpae_iopte prot;
+ long iaext = (long)iova >> cfg->ias;
/* If no access, then nothing to do */
if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
@@ -471,7 +476,9 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
return -EINVAL;
- if (WARN_ON(iova >> data->iop.cfg.ias || paddr >> data->iop.cfg.oas))
+ if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+ iaext = ~iaext;
+ if (WARN_ON(iaext || paddr >> cfg->oas))
return -ERANGE;
prot = arm_lpae_prot_to_pte(data, iommu_prot);
@@ -637,11 +644,14 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
struct io_pgtable_cfg *cfg = &data->iop.cfg;
arm_lpae_iopte *ptep = data->pgd;
+ long iaext = (long)iova >> cfg->ias;
if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
return 0;
- if (WARN_ON(iova >> data->iop.cfg.ias))
+ if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+ iaext = ~iaext;
+ if (WARN_ON(iaext))
return 0;
return __arm_lpae_unmap(data, gather, iova, size, data->start_level, ptep);
@@ -777,9 +787,11 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
u64 reg;
struct arm_lpae_io_pgtable *data;
typeof(&cfg->arm_lpae_s1_cfg.tcr) tcr = &cfg->arm_lpae_s1_cfg.tcr;
+ bool tg1;
if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
- IO_PGTABLE_QUIRK_NON_STRICT))
+ IO_PGTABLE_QUIRK_NON_STRICT |
+ IO_PGTABLE_QUIRK_ARM_TTBR1))
return NULL;
data = arm_lpae_alloc_pgtable(cfg);
@@ -797,15 +809,16 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
tcr->orgn = ARM_LPAE_TCR_RGN_NC;
}
+ tg1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1;
switch (ARM_LPAE_GRANULE(data)) {
case SZ_4K:
- tcr->tg = ARM_LPAE_TCR_TG0_4K;
+ tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_4K : ARM_LPAE_TCR_TG0_4K;
break;
case SZ_16K:
- tcr->tg = ARM_LPAE_TCR_TG0_16K;
+ tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_16K : ARM_LPAE_TCR_TG0_16K;
break;
case SZ_64K:
- tcr->tg = ARM_LPAE_TCR_TG0_64K;
+ tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_64K : ARM_LPAE_TCR_TG0_64K;
break;
}
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 40c1b7745fb6..53d53c6c2be9 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -83,12 +83,16 @@ struct io_pgtable_cfg {
* IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
* on unmap, for DMA domains using the flush queue mechanism for
* delayed invalidation.
+ *
+ * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table
+ * for use in the upper half of a split address space.
*/
#define IO_PGTABLE_QUIRK_ARM_NS BIT(0)
#define IO_PGTABLE_QUIRK_NO_PERMS BIT(1)
#define IO_PGTABLE_QUIRK_TLBI_ON_MAP BIT(2)
#define IO_PGTABLE_QUIRK_ARM_MTK_EXT BIT(3)
#define IO_PGTABLE_QUIRK_NON_STRICT BIT(4)
+ #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5)
unsigned long quirks;
unsigned long pgsize_bitmap;
unsigned int ias;
--
2.25.0.rc1.283.g88dfdc4193-goog
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCH 8/8] iommu/io-pgtable-arm: Prepare for TTBR1 usage
2020-01-10 15:28 ` [PATCH 8/8] iommu/io-pgtable-arm: Prepare for TTBR1 usage Will Deacon
@ 2020-02-19 12:27 ` Stephan Gerhold
2020-02-19 17:51 ` Robin Murphy
0 siblings, 1 reply; 11+ messages in thread
From: Stephan Gerhold @ 2020-02-19 12:27 UTC (permalink / raw)
To: Will Deacon, Robin Murphy; +Cc: iommu, kernel-team, linux-arm-kernel
Hi Will, Hi Robin,
On Fri, Jan 10, 2020 at 03:28:52PM +0000, Will Deacon wrote:
> From: Robin Murphy <robin.murphy@arm.com>
>
> Now that we can correctly extract top-level indices without relying on
> the remaining upper bits being zero, the only remaining impediments to
> using a given table for TTBR1 are the address validation on map/unmap
> and the awkward TCR translation granule format. Add a quirk so that we
> can do the right thing at those points.
>
> Tested-by: Jordan Crouse <jcrouse@codeaurora.org>
> Signed-off-by: Robin Murphy <robin.murphy@arm.com>
> Signed-off-by: Will Deacon <will@kernel.org>
> ---
> drivers/iommu/io-pgtable-arm.c | 25 +++++++++++++++++++------
> include/linux/io-pgtable.h | 4 ++++
> 2 files changed, 23 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index 846963c87e0f..5e966ef0bacf 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -104,6 +104,10 @@
> #define ARM_LPAE_TCR_TG0_64K 1
> #define ARM_LPAE_TCR_TG0_16K 2
>
> +#define ARM_LPAE_TCR_TG1_16K 1
> +#define ARM_LPAE_TCR_TG1_4K 2
> +#define ARM_LPAE_TCR_TG1_64K 3
> +
> #define ARM_LPAE_TCR_SH_NS 0
> #define ARM_LPAE_TCR_SH_OS 2
> #define ARM_LPAE_TCR_SH_IS 3
> @@ -463,6 +467,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
> arm_lpae_iopte *ptep = data->pgd;
> int ret, lvl = data->start_level;
> arm_lpae_iopte prot;
> + long iaext = (long)iova >> cfg->ias;
>
> /* If no access, then nothing to do */
> if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
> @@ -471,7 +476,9 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
> if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
> return -EINVAL;
>
> - if (WARN_ON(iova >> data->iop.cfg.ias || paddr >> data->iop.cfg.oas))
> + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
> + iaext = ~iaext;
> + if (WARN_ON(iaext || paddr >> cfg->oas))
> return -ERANGE;
>
> prot = arm_lpae_prot_to_pte(data, iommu_prot);
> @@ -637,11 +644,14 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
> struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
> struct io_pgtable_cfg *cfg = &data->iop.cfg;
> arm_lpae_iopte *ptep = data->pgd;
> + long iaext = (long)iova >> cfg->ias;
>
> if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
> return 0;
>
> - if (WARN_ON(iova >> data->iop.cfg.ias))
> + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
> + iaext = ~iaext;
> + if (WARN_ON(iaext))
> return 0;
>
> return __arm_lpae_unmap(data, gather, iova, size, data->start_level, ptep);
This part of the patch seems to break io-pgtable-arm.c on ARM32 to some
extent. I have a device using qcom_iommu that could normally run ARM64,
but I'm unable to because of outdated (signed) firmware. :(
So it's running a lot of code that would normally run only on ARM64.
It used to work quite well but now qcom-venus fails to probe on:
if (WARN_ON(iaext || paddr >> cfg->oas))
(I added some debug prints for clarity.)
qcom-venus 1d00000.video-codec: Adding to iommu group 0
arm-lpae io-pgtable: quirks: 0x0
arm-lpae io-pgtable: arm_lpae_map: iova: 0xdd800000, paddr: 0xebe3f000, iaext: 0xffffffff, paddr >> oas: 0x0
------------[ cut here ]------------
WARNING: CPU: 0 PID: 954 at drivers/iommu/io-pgtable-arm.c:487 arm_lpae_map+0xe4/0x510
Hardware name: Generic DT based system
...
[<c04bafb0>] (arm_lpae_map) from [<c04bcd6c>] (qcom_iommu_map+0x50/0x78)
[<c04bcd6c>] (qcom_iommu_map) from [<c04b7290>] (__iommu_map+0xe8/0x1cc)
[<c04b7290>] (__iommu_map) from [<c04b7bbc>] (__iommu_map_sg+0xa8/0x118)
[<c04b7bbc>] (__iommu_map_sg) from [<c04b7c64>] (iommu_map_sg_atomic+0x18/0x20)
[<c04b7c64>] (iommu_map_sg_atomic) from [<c04b94f8>] (iommu_dma_alloc+0x4dc/0x5a0)
[<c04b94f8>] (iommu_dma_alloc) from [<c0196a50>] (dma_alloc_attrs+0x104/0x114)
[<c0196a50>] (dma_alloc_attrs) from [<bf302c60>] (venus_hfi_create+0xa4/0x260 [venus_core])
[<bf302c60>] (venus_hfi_create [venus_core]) from [<bf2fe6cc>] (venus_probe+0x1e4/0x328 [venus_core])
[<bf2fe6cc>] (venus_probe [venus_core]) from [<c04c8eb4>] (platform_drv_probe+0x48/0x98)
...
Exception stack(0xc2587fa8 to 0xc2587ff0)
7fa0: b6f3dc70 b5051010 b5051010 0017388c b6e645b0 b6e645b0
7fc0: b6f3dc70 b5051010 00020000 00000080 b6e30790 be84ea54 0046ac91 00000000
7fe0: b6e75f1c be84e940 b6e5fb51 b6eec8a4
---[ end trace 2a0ed284f6d82f16 ]---
qcom-venus: probe of 1d00000.video-codec failed with error -12
Note that iaext = 0xffffffff != 0.
It seems to be some int/long size problem that only happens with larger
iova addresses on 32-bit systems.
Without the (long) cast for iova everything is working correctly again:
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 983b08477e64..f7ecc763c706 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -468,7 +468,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
arm_lpae_iopte *ptep = data->pgd;
int ret, lvl = data->start_level;
arm_lpae_iopte prot;
- long iaext = (long)iova >> cfg->ias;
+ long iaext = iova >> cfg->ias;
/* If no access, then nothing to do */
if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
@@ -645,7 +645,7 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
struct io_pgtable_cfg *cfg = &data->iop.cfg;
arm_lpae_iopte *ptep = data->pgd;
- long iaext = (long)iova >> cfg->ias;
+ long iaext = iova >> cfg->ias;
if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
return 0;
But I'm not sure if this is really the correct "fix"...
This problem can be also easily reproduced by enabling
IOMMU_IO_PGTABLE_LPAE_SELFTEST on ARM32.
(Shouldn't there be some system that runs these automatically? ;))
Without this patch all of them are passing:
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 32
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 36
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 40
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 42
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 44
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 48
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 32
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 36
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 40
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 42
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 44
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 48
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 32
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 36
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 40
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 42
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 44
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 48
arm-lpae io-pgtable: selftest: completed with 18 PASS 0 FAIL
But with this patch 6 of them are failing (with a similar warning as
I posted above):
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 32
------------[ cut here ]------------
WARNING: CPU: 3 PID: 1 at drivers/iommu/io-pgtable-arm.c:482 arm_lpae_map+0xa4/0x4e4
Hardware name: Generic DT based system
[<c01104ac>] (unwind_backtrace) from [<c010c0b4>] (show_stack+0x10/0x14)
[<c010c0b4>] (show_stack) from [<c06cfb34>] (dump_stack+0x90/0xa4)
[<c06cfb34>] (dump_stack) from [<c012d76c>] (__warn+0xb8/0xd4)
[<c012d76c>] (__warn) from [<c012d7ec>] (warn_slowpath_fmt+0x64/0xbc)
[<c012d7ec>] (warn_slowpath_fmt) from [<c04baf70>] (arm_lpae_map+0xa4/0x4e4)
[<c04baf70>] (arm_lpae_map) from [<c0a1de3c>] (arm_lpae_do_selftests+0x234/0x688)
[<c0a1de3c>] (arm_lpae_do_selftests) from [<c0102788>] (do_one_initcall+0x50/0x1b8)
[<c0102788>] (do_one_initcall) from [<c0a0148c>] (kernel_init_freeable+0x1ec/0x25c)
[<c0a0148c>] (kernel_init_freeable) from [<c06e6dc4>] (kernel_init+0x8/0x110)
[<c06e6dc4>] (kernel_init) from [<c01010e8>] (ret_from_fork+0x14/0x2c)
Exception stack(0xee867fb0 to 0xee867ff8)
7fa0: 00000000 00000000 00000000 00000000
7fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
7fe0: 00000000 00000000 00000000 00000000 00000013 00000000
---[ end trace 89e831c50a111e7c ]---
------------[ cut here ]------------
WARNING: CPU: 3 PID: 1 at drivers/iommu/io-pgtable-arm.c:1182 arm_lpae_do_selftests+0x4b8/0x688
selftest: test failed for fmt idx 0
Hardware name: Generic DT based system
[<c01104ac>] (unwind_backtrace) from [<c010c0b4>] (show_stack+0x10/0x14)
[<c010c0b4>] (show_stack) from [<c06cfb34>] (dump_stack+0x90/0xa4)
[<c06cfb34>] (dump_stack) from [<c012d76c>] (__warn+0xb8/0xd4)
[<c012d76c>] (__warn) from [<c012d820>] (warn_slowpath_fmt+0x98/0xbc)
[<c012d820>] (warn_slowpath_fmt) from [<c0a1e0c0>] (arm_lpae_do_selftests+0x4b8/0x688)
[<c0a1e0c0>] (arm_lpae_do_selftests) from [<c0102788>] (do_one_initcall+0x50/0x1b8)
[<c0102788>] (do_one_initcall) from [<c0a0148c>] (kernel_init_freeable+0x1ec/0x25c)
[<c0a0148c>] (kernel_init_freeable) from [<c06e6dc4>] (kernel_init+0x8/0x110)
[<c06e6dc4>] (kernel_init) from [<c01010e8>] (ret_from_fork+0x14/0x2c)
Exception stack(0xee867fb0 to 0xee867ff8)
7fa0: 00000000 00000000 00000000 00000000
7fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
7fe0: 00000000 00000000 00000000 00000000 00000013 00000000
---[ end trace 89e831c50a111e7d ]---
arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 32-bit
arm-lpae io-pgtable: data: 3 levels, 0x20 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 36
[warning as above]
arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 36-bit
arm-lpae io-pgtable: data: 3 levels, 0x200 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 40
[warning as above]
arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 40-bit
arm-lpae io-pgtable: data: 4 levels, 0x10 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 42
[warning as above]
arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 42-bit
arm-lpae io-pgtable: data: 4 levels, 0x40 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 44
[warning as above]
arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 44-bit
arm-lpae io-pgtable: data: 4 levels, 0x100 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 48
[warning as above]
arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 48-bit
arm-lpae io-pgtable: data: 4 levels, 0x1000 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 32
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 36
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 40
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 42
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 44
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 48
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 32
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 36
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 40
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 42
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 44
arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 48
arm-lpae io-pgtable: selftest: completed with 12 PASS 6 FAIL
Any suggestions how to fix this properly?
Thanks,
Stephan
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCH 8/8] iommu/io-pgtable-arm: Prepare for TTBR1 usage
2020-02-19 12:27 ` Stephan Gerhold
@ 2020-02-19 17:51 ` Robin Murphy
0 siblings, 0 replies; 11+ messages in thread
From: Robin Murphy @ 2020-02-19 17:51 UTC (permalink / raw)
To: Stephan Gerhold, Will Deacon; +Cc: iommu, kernel-team, linux-arm-kernel
On 19/02/2020 12:27 pm, Stephan Gerhold wrote:
> Hi Will, Hi Robin,
>
> On Fri, Jan 10, 2020 at 03:28:52PM +0000, Will Deacon wrote:
>> From: Robin Murphy <robin.murphy@arm.com>
>>
>> Now that we can correctly extract top-level indices without relying on
>> the remaining upper bits being zero, the only remaining impediments to
>> using a given table for TTBR1 are the address validation on map/unmap
>> and the awkward TCR translation granule format. Add a quirk so that we
>> can do the right thing at those points.
>>
>> Tested-by: Jordan Crouse <jcrouse@codeaurora.org>
>> Signed-off-by: Robin Murphy <robin.murphy@arm.com>
>> Signed-off-by: Will Deacon <will@kernel.org>
>> ---
>> drivers/iommu/io-pgtable-arm.c | 25 +++++++++++++++++++------
>> include/linux/io-pgtable.h | 4 ++++
>> 2 files changed, 23 insertions(+), 6 deletions(-)
>>
>> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
>> index 846963c87e0f..5e966ef0bacf 100644
>> --- a/drivers/iommu/io-pgtable-arm.c
>> +++ b/drivers/iommu/io-pgtable-arm.c
>> @@ -104,6 +104,10 @@
>> #define ARM_LPAE_TCR_TG0_64K 1
>> #define ARM_LPAE_TCR_TG0_16K 2
>>
>> +#define ARM_LPAE_TCR_TG1_16K 1
>> +#define ARM_LPAE_TCR_TG1_4K 2
>> +#define ARM_LPAE_TCR_TG1_64K 3
>> +
>> #define ARM_LPAE_TCR_SH_NS 0
>> #define ARM_LPAE_TCR_SH_OS 2
>> #define ARM_LPAE_TCR_SH_IS 3
>> @@ -463,6 +467,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
>> arm_lpae_iopte *ptep = data->pgd;
>> int ret, lvl = data->start_level;
>> arm_lpae_iopte prot;
>> + long iaext = (long)iova >> cfg->ias;
>>
>> /* If no access, then nothing to do */
>> if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
>> @@ -471,7 +476,9 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
>> if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
>> return -EINVAL;
>>
>> - if (WARN_ON(iova >> data->iop.cfg.ias || paddr >> data->iop.cfg.oas))
>> + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
>> + iaext = ~iaext;
>> + if (WARN_ON(iaext || paddr >> cfg->oas))
>> return -ERANGE;
>>
>> prot = arm_lpae_prot_to_pte(data, iommu_prot);
>> @@ -637,11 +644,14 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
>> struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
>> struct io_pgtable_cfg *cfg = &data->iop.cfg;
>> arm_lpae_iopte *ptep = data->pgd;
>> + long iaext = (long)iova >> cfg->ias;
>>
>> if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
>> return 0;
>>
>> - if (WARN_ON(iova >> data->iop.cfg.ias))
>> + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
>> + iaext = ~iaext;
>> + if (WARN_ON(iaext))
>> return 0;
>>
>> return __arm_lpae_unmap(data, gather, iova, size, data->start_level, ptep);
>
> This part of the patch seems to break io-pgtable-arm.c on ARM32 to some
> extent. I have a device using qcom_iommu that could normally run ARM64,
> but I'm unable to because of outdated (signed) firmware. :(
> So it's running a lot of code that would normally run only on ARM64.
>
> It used to work quite well but now qcom-venus fails to probe on:
> if (WARN_ON(iaext || paddr >> cfg->oas))
> (I added some debug prints for clarity.)
>
> qcom-venus 1d00000.video-codec: Adding to iommu group 0
> arm-lpae io-pgtable: quirks: 0x0
> arm-lpae io-pgtable: arm_lpae_map: iova: 0xdd800000, paddr: 0xebe3f000, iaext: 0xffffffff, paddr >> oas: 0x0
> ------------[ cut here ]------------
> WARNING: CPU: 0 PID: 954 at drivers/iommu/io-pgtable-arm.c:487 arm_lpae_map+0xe4/0x510
> Hardware name: Generic DT based system
> ...
> [<c04bafb0>] (arm_lpae_map) from [<c04bcd6c>] (qcom_iommu_map+0x50/0x78)
> [<c04bcd6c>] (qcom_iommu_map) from [<c04b7290>] (__iommu_map+0xe8/0x1cc)
> [<c04b7290>] (__iommu_map) from [<c04b7bbc>] (__iommu_map_sg+0xa8/0x118)
> [<c04b7bbc>] (__iommu_map_sg) from [<c04b7c64>] (iommu_map_sg_atomic+0x18/0x20)
> [<c04b7c64>] (iommu_map_sg_atomic) from [<c04b94f8>] (iommu_dma_alloc+0x4dc/0x5a0)
> [<c04b94f8>] (iommu_dma_alloc) from [<c0196a50>] (dma_alloc_attrs+0x104/0x114)
> [<c0196a50>] (dma_alloc_attrs) from [<bf302c60>] (venus_hfi_create+0xa4/0x260 [venus_core])
> [<bf302c60>] (venus_hfi_create [venus_core]) from [<bf2fe6cc>] (venus_probe+0x1e4/0x328 [venus_core])
> [<bf2fe6cc>] (venus_probe [venus_core]) from [<c04c8eb4>] (platform_drv_probe+0x48/0x98)
> ...
> Exception stack(0xc2587fa8 to 0xc2587ff0)
> 7fa0: b6f3dc70 b5051010 b5051010 0017388c b6e645b0 b6e645b0
> 7fc0: b6f3dc70 b5051010 00020000 00000080 b6e30790 be84ea54 0046ac91 00000000
> 7fe0: b6e75f1c be84e940 b6e5fb51 b6eec8a4
> ---[ end trace 2a0ed284f6d82f16 ]---
> qcom-venus: probe of 1d00000.video-codec failed with error -12
>
> Note that iaext = 0xffffffff != 0.
> It seems to be some int/long size problem that only happens with larger
> iova addresses on 32-bit systems.
>
> Without the (long) cast for iova everything is working correctly again:
>
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index 983b08477e64..f7ecc763c706 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -468,7 +468,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
> arm_lpae_iopte *ptep = data->pgd;
> int ret, lvl = data->start_level;
> arm_lpae_iopte prot;
> - long iaext = (long)iova >> cfg->ias;
> + long iaext = iova >> cfg->ias;
>
> /* If no access, then nothing to do */
> if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
> @@ -645,7 +645,7 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
> struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
> struct io_pgtable_cfg *cfg = &data->iop.cfg;
> arm_lpae_iopte *ptep = data->pgd;
> - long iaext = (long)iova >> cfg->ias;
> + long iaext = iova >> cfg->ias;
>
> if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
> return 0;
>
> But I'm not sure if this is really the correct "fix"...
No, that would end up breaking the TTBR1 case. The quirk isn't intended
to be supported on 32-bit platforms, but somehow it's slipped through
that this sign-extension still affects them (and goes wrong to boot),
sorry about that.
I think quick fixes would be either to replace the "(long)" cast with
"(s64)(u64)", or to just elide the iaext check altogether when 32-bit
longs make it impossible to pass an out-of-range IOVA anyway. I'll have
a think and see what works out nicest.
> This problem can be also easily reproduced by enabling
> IOMMU_IO_PGTABLE_LPAE_SELFTEST on ARM32.
> (Shouldn't there be some system that runs these automatically? ;))
>
> Without this patch all of them are passing:
>
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 32
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 36
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 40
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 42
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 44
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 48
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 32
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 36
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 40
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 42
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 44
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 48
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 32
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 36
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 40
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 42
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 44
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 48
> arm-lpae io-pgtable: selftest: completed with 18 PASS 0 FAIL
Hmm, we probably shouldn't be running IAS > 32 tests on 32-bit, given
that such configs are effectively impossible to use.
Robin.
>
> But with this patch 6 of them are failing (with a similar warning as
> I posted above):
>
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 32
> ------------[ cut here ]------------
> WARNING: CPU: 3 PID: 1 at drivers/iommu/io-pgtable-arm.c:482 arm_lpae_map+0xa4/0x4e4
> Hardware name: Generic DT based system
> [<c01104ac>] (unwind_backtrace) from [<c010c0b4>] (show_stack+0x10/0x14)
> [<c010c0b4>] (show_stack) from [<c06cfb34>] (dump_stack+0x90/0xa4)
> [<c06cfb34>] (dump_stack) from [<c012d76c>] (__warn+0xb8/0xd4)
> [<c012d76c>] (__warn) from [<c012d7ec>] (warn_slowpath_fmt+0x64/0xbc)
> [<c012d7ec>] (warn_slowpath_fmt) from [<c04baf70>] (arm_lpae_map+0xa4/0x4e4)
> [<c04baf70>] (arm_lpae_map) from [<c0a1de3c>] (arm_lpae_do_selftests+0x234/0x688)
> [<c0a1de3c>] (arm_lpae_do_selftests) from [<c0102788>] (do_one_initcall+0x50/0x1b8)
> [<c0102788>] (do_one_initcall) from [<c0a0148c>] (kernel_init_freeable+0x1ec/0x25c)
> [<c0a0148c>] (kernel_init_freeable) from [<c06e6dc4>] (kernel_init+0x8/0x110)
> [<c06e6dc4>] (kernel_init) from [<c01010e8>] (ret_from_fork+0x14/0x2c)
> Exception stack(0xee867fb0 to 0xee867ff8)
> 7fa0: 00000000 00000000 00000000 00000000
> 7fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
> 7fe0: 00000000 00000000 00000000 00000000 00000013 00000000
> ---[ end trace 89e831c50a111e7c ]---
> ------------[ cut here ]------------
> WARNING: CPU: 3 PID: 1 at drivers/iommu/io-pgtable-arm.c:1182 arm_lpae_do_selftests+0x4b8/0x688
> selftest: test failed for fmt idx 0
> Hardware name: Generic DT based system
> [<c01104ac>] (unwind_backtrace) from [<c010c0b4>] (show_stack+0x10/0x14)
> [<c010c0b4>] (show_stack) from [<c06cfb34>] (dump_stack+0x90/0xa4)
> [<c06cfb34>] (dump_stack) from [<c012d76c>] (__warn+0xb8/0xd4)
> [<c012d76c>] (__warn) from [<c012d820>] (warn_slowpath_fmt+0x98/0xbc)
> [<c012d820>] (warn_slowpath_fmt) from [<c0a1e0c0>] (arm_lpae_do_selftests+0x4b8/0x688)
> [<c0a1e0c0>] (arm_lpae_do_selftests) from [<c0102788>] (do_one_initcall+0x50/0x1b8)
> [<c0102788>] (do_one_initcall) from [<c0a0148c>] (kernel_init_freeable+0x1ec/0x25c)
> [<c0a0148c>] (kernel_init_freeable) from [<c06e6dc4>] (kernel_init+0x8/0x110)
> [<c06e6dc4>] (kernel_init) from [<c01010e8>] (ret_from_fork+0x14/0x2c)
> Exception stack(0xee867fb0 to 0xee867ff8)
> 7fa0: 00000000 00000000 00000000 00000000
> 7fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
> 7fe0: 00000000 00000000 00000000 00000000 00000013 00000000
> ---[ end trace 89e831c50a111e7d ]---
> arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 32-bit
> arm-lpae io-pgtable: data: 3 levels, 0x20 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 36
> [warning as above]
> arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 36-bit
> arm-lpae io-pgtable: data: 3 levels, 0x200 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 40
> [warning as above]
> arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 40-bit
> arm-lpae io-pgtable: data: 4 levels, 0x10 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 42
> [warning as above]
> arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 42-bit
> arm-lpae io-pgtable: data: 4 levels, 0x40 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 44
> [warning as above]
> arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 44-bit
> arm-lpae io-pgtable: data: 4 levels, 0x100 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x40201000, IAS 48
> [warning as above]
> arm-lpae io-pgtable: cfg: pgsize_bitmap 0x40201000, ias 48-bit
> arm-lpae io-pgtable: data: 4 levels, 0x1000 pgd_size, 12 pg_shift, 9 bits_per_level, pgd @ (ptrval)
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 32
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 36
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 40
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 42
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 44
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x02004000, IAS 48
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 32
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 36
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 40
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 42
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 44
> arm-lpae io-pgtable: selftest: pgsize_bitmap 0x20010000, IAS 48
> arm-lpae io-pgtable: selftest: completed with 12 PASS 6 FAIL
>
> Any suggestions how to fix this properly?
>
> Thanks,
> Stephan
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 11+ messages in thread