[v2 PATCH] iommu/arm-smmu-v3: Fix L1 stream table index calculation for 32-bit sid size

[Yang Shi]

The commit ce410410f1a7 ("iommu/arm-smmu-v3: Add arm_smmu_strtab_l1/2_idx()")
calculated the last index of L1 stream table by 1 << smmu->sid_bits. 1
is 32 bit value.
However some platforms, for example, AmpereOne, have 32-bit stream id size.
This resulted in ouf-of-bound shift.  The disassembly of shift is:

    ldr     w2, [x19, 828]  //, smmu_7(D)->sid_bits
    mov     w20, 1
    lsl     w20, w20, w2

According to ARM spec, if the registers are 32 bit, the instruction actually
does:
    dest = src << (shift % 32)

So it actually shifted by zero bit.

This caused v6.12-rc1 failed to boot on AmpereOne and other platform [1].

UBSAN also reported:

UBSAN: shift-out-of-bounds in drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c:3628:29
shift exponent 32 is too large for 32-bit type 'int'
CPU: 70 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.12.0-rc1 #4
Hardware name: ZOLLNER SUNMOONLAKE/SunMoon Lake, BIOS 00.00. 2024-08-28 18:42:45 08/28/2024
Call trace:
 dump_backtrace+0xdc/0x140
 show_stack+0x20/0x40
 dump_stack_lvl+0x60/0x80
 dump_stack+0x18/0x28
 ubsan_epilogue+0x10/0x48
 __ubsan_handle_shift_out_of_bounds+0xd8/0x1a0
 arm_smmu_init_structures+0x374/0x3c8
 arm_smmu_device_probe+0x208/0x600
 platform_probe+0x70/0xe8
 really_probe+0xc8/0x3a0
 __driver_probe_device+0x84/0x160
 driver_probe_device+0x44/0x130
 __driver_attach+0xcc/0x208
 bus_for_each_dev+0x84/0x100
 driver_attach+0x2c/0x40
 bus_add_driver+0x158/0x290
 driver_register+0x70/0x138
 __platform_driver_register+0x2c/0x40
 arm_smmu_driver_init+0x28/0x40
 do_one_initcall+0x60/0x318
 do_initcalls+0x198/0x1e0
 kernel_init_freeable+0x18c/0x1e8
 kernel_init+0x28/0x160
 ret_from_fork+0x10/0x20

Using 64 bit immediate when doing shift can solve the problem.  The
disassembly after the fix looks like:
    ldr     w20, [x19, 828] //, smmu_7(D)->sid_bits
    mov     x0, 1
    lsl     x0, x0, x20

There are a couple of problematic places, extracted the shift into a helper.

[1] https://lore.kernel.org/lkml/d4b53bbb-333a-45b9-9eb0-23ddd0820a14@xxxxxxx/
Fixes: ce410410f1a7 ("iommu/arm-smmu-v3: Add arm_smmu_strtab_l1/2_idx()")
Tested-by: James Morse <james.morse@xxxxxxx>
Signed-off-by: Yang Shi <yang@xxxxxxxxxxxxxxxxxxxxxx>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 8 +++++---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 5 +++++
 2 files changed, 10 insertions(+), 3 deletions(-)

v2: * Extracted the shift into a helper per Jason Gunthorpe.
    * Covered more places per Nicolin Chen and Jason Gunthorpe.
    * Used 1ULL instead of 1UL to guarantee 64 bit per Robin Murphy.
    * Made the subject more general since this is not AmpereOne specific
      problem per the report from James Morse.
    * Collected t-b tag from James Morse.
    * Added Fixes tag in commit log.

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 737c5b882355..4eafd9f04808 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3624,8 +3624,9 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
 {
 	u32 l1size;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+	unsigned int max_sid = arm_smmu_strtab_max_sid(smmu);
 	unsigned int last_sid_idx =
-		arm_smmu_strtab_l1_idx((1 << smmu->sid_bits) - 1);
+		arm_smmu_strtab_l1_idx(max_sid - 1);
 
 	/* Calculate the L1 size, capped to the SIDSIZE. */
 	cfg->l2.num_l1_ents = min(last_sid_idx + 1, STRTAB_MAX_L1_ENTRIES);
@@ -3657,8 +3658,9 @@ static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
 {
 	u32 size;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+	unsigned int max_sid = arm_smmu_strtab_max_sid(smmu);
 
-	size = (1 << smmu->sid_bits) * sizeof(struct arm_smmu_ste);
+	size = max_sid * sizeof(struct arm_smmu_ste);
 	cfg->linear.table = dmam_alloc_coherent(smmu->dev, size,
 						&cfg->linear.ste_dma,
 						GFP_KERNEL);
@@ -3668,7 +3670,7 @@ static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
 			size);
 		return -ENOMEM;
 	}
-	cfg->linear.num_ents = 1 << smmu->sid_bits;
+	cfg->linear.num_ents = max_sid;
 
 	arm_smmu_init_initial_stes(cfg->linear.table, cfg->linear.num_ents);
 	return 0;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 1e9952ca989f..f7e8465c629a 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -853,6 +853,11 @@ struct arm_smmu_master_domain {
 	ioasid_t ssid;
 };
 
+static inline unsigned int arm_smmu_strtab_max_sid(struct arm_smmu_device *smmu)
+{
+	return (1ULL << smmu->sid_bits);
+}
+
 static inline struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
 {
 	return container_of(dom, struct arm_smmu_domain, domain);
-- 
2.41.0