iommu/amd: Support for HATdis and HATS features
Subsystems (2)
cover iommu/amd: Support for HATdis and HATS features
This series comprises two features:
HATDis: When host address translation is not supported by the IOMMU, the IVHD->attr[HATDis] bit is set. For instance, QEMU emulated vIOMMU does not support dma tranlation for VFIO passthrough device. Support has been added to check this bit and switch to guest page table mode, if supported. This feature is useful for cases where only interrupt remapping is required.
EFR[HATS]: These bits indicate the maximum level supported for host page table by the IOMMU. Modifications have been made to adjust the maximum host page table level, starting with level 4. If these bits are set to 11b, the driver will attempt to use the guest page table.
If guest page table mode is not supported, the driver will fail to probe devices for DMA translations.
The interrupt remapping will continue to be supported.
Ankit Soni (2):
iommu/amd: Add HATDis feature support iommu/amd: Add efr[HATS] max v1 page table level
drivers/iommu/amd/amd_iommu.h | 2 ++ drivers/iommu/amd/amd_iommu_types.h | 7 +++++- drivers/iommu/amd/init.c | 39 +++++++++++++++++++++++++++-- drivers/iommu/amd/io_pgtable.c | 4 +-- drivers/iommu/amd/iommu.c | 15 ++++++++++- 5 files changed, 61 insertions(+), 6 deletions(-)
Signature · 1 line
2.43.0
PATCH 1/2 iommu/amd: Add HATDis feature support
Current AMD IOMMU assumes Host Address Translation (HAT) is always supported, and Linux kernel enables this capability by default. However, in case of emulated and virtualized IOMMU, this might not be the case. For example,current QEMU-emulated AMD vIOMMU does not support host translation for VFIO pass-through device, but the interrupt remapping support is required for x2APIC (i.e. kvm-msi-ext-dest-id is also not supported by the guest OS). This would require the guest kernel to boot with guest kernel option iommu=pt to by-pass the initialization of host (v1) table.
The AMD I/O Virtualization Technology (IOMMU) Specification Rev 3.10 [1] introduces a new flag 'HATDis' in the IVHD 11h IOMMU attributes to indicate that HAT is not supported on a particular IOMMU instance.
Therefore, modifies the AMD IOMMU driver to detect the new HATDis attributes, and disable host translation and switch to use guest translation if it is available. Otherwise, the driver will disable DMA translation.
[1] https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/specifications/48882_IOMMU.pdf
--- drivers/iommu/amd/amd_iommu.h | 1 + drivers/iommu/amd/amd_iommu_types.h | 6 +++++- drivers/iommu/amd/init.c | 23 +++++++++++++++++++++-- drivers/iommu/amd/iommu.c | 13 +++++++++++++ 4 files changed, 40 insertions(+), 3 deletions(-)
drivers/iommu/amd/amd_iommu.h +1 -0
@@ -43,6 +43,7 @@ extern int amd_iommu_guest_ir;extern enum protection_domain_mode amd_iommu_pgtable;extern int amd_iommu_gpt_level;extern unsigned long amd_iommu_pgsize_bitmap; +extern bool amd_iommu_hatdis;/* Protection domain ops */ void amd_iommu_init_identity_domain (void );
drivers/iommu/amd/amd_iommu_types.h +5 -1
@@ -460,6 +460,9 @@/* IOMMU Feature Reporting Field (for IVHD type 10h */ #define IOMMU_FEAT_GASUP_SHIFT 6 +/* IOMMU HATDIS for IVHD type 11h and 40h */ +#define IOMMU_IVHD_ATTR_HATDIS_SHIFT 0 +/* IOMMU Extended Feature Register (EFR) */ #define IOMMU_EFR_XTSUP_SHIFT 2#define IOMMU_EFR_GASUP_SHIFT 7
@@ -558,7 +561,8 @@ struct amd_io_pgtable { };enum protection_domain_mode { -PD_MODE_V1 =1 , +PD_MODE_NONE , +PD_MODE_V1 ,PD_MODE_V2 , };
drivers/iommu/amd/init.c +21 -2
@@ -151,7 +151,7 @@ struct ivmd_header {bool amd_iommu_dump;bool amd_iommu_irq_remap__read_mostly ; -enum protection_domain_mode amd_iommu_pgtable =PD_MODE_V1 ; +enum protection_domain_mode amd_iommu_pgtable =PD_MODE_NONE ;/* Guest page table level */ int amd_iommu_gpt_level =PAGE_MODE_4_LEVEL ;
@@ -168,6 +168,9 @@ static int amd_iommu_target_ivhd_type;u64 amd_iommu_efr;u64 amd_iommu_efr2; +/* dma translation not supported*/ +bool amd_iommu_hatdis; +/* SNP is enabled on the system? */ bool amd_iommu_snp_en;EXPORT_SYMBOL (amd_iommu_snp_en);
@@ -1798,6 +1801,11 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h,if (h->efr_reg &BIT (IOMMU_EFR_XTSUP_SHIFT )) amd_iommu_xt_mode =IRQ_REMAP_X2APIC_MODE ; +if (h->efr_attr &BIT (IOMMU_IVHD_ATTR_HATDIS_SHIFT )) { +pr_warn_once ("Host Address Translation is not supported.\n" ); + amd_iommu_hatdis = true; + } +early_iommu_features_init (iommu, h);break ;
@@ -2582,7 +2590,7 @@ static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg)u32 devid;struct dev_table_entry *dev_table = pci_seg->dev_table; -if (dev_table ==NULL ) +if (!dev_table || amd_iommu_pgtable ==PD_MODE_NONE )return ;for (devid =0 ; devid <= pci_seg->last_bdf; ++devid) {
@@ -3095,6 +3103,17 @@ static int __init early_amd_iommu_init(void) } } +if (amd_iommu_hatdis) { +if (amd_iommu_v2_pgtbl_supported ()) + amd_iommu_pgtable =PD_MODE_V2 ; + }else if (amd_iommu_pgtable ==PD_MODE_NONE ) +/* +* If v1 page table is supported (i.e., amd_iommu_hatdis == 0) +* and page table type is not specified in command line, then +* use v1 page table. +*/ + amd_iommu_pgtable =PD_MODE_V1 ; +/* Disable any previously enabled IOMMUs */ if (!is_kdump_kernel () || amd_iommu_disabled)disable_iommus ();
drivers/iommu/amd/iommu.c +13 -0
@@ -2393,6 +2393,13 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev) pci_max_pasids(to_pci_dev(dev))); } +if (amd_iommu_pgtable ==PD_MODE_NONE ) { +pr_warn_once ("%s: DMA translation not supported by iommu.\n" , + __func__); + iommu_dev =ERR_PTR (-ENODEV ); + goto out_err; + } + out_err:iommu_completion_wait (iommu);
@@ -2480,6 +2487,9 @@ static int pdom_setup_pgtable(struct protection_domain *domain,case PD_MODE_V2 : fmt =AMD_IOMMU_V2 ;break ; +case PD_MODE_NONE : +WARN_ON_ONCE (1 ); +return -EPERM ; } domain->iop.pgtbl.cfg.amd.nid =dev_to_node (dev);
@@ -2501,6 +2511,9 @@ static inline u64 dma_max_address(enum protection_domain_mode pgtable)static bool amd_iommu_hd_support (struct amd_iommu *iommu) { +if (amd_iommu_hatdis) +return false; +return iommu && (iommu->features &FEATURE_HDSUP ); }
Signature · 1 line
2.43.0
Re: [PATCH 1/2] iommu/amd: Add HATDis feature support
Quoted 3 lines · Ankit Soni
Current AMD IOMMU assumes Host Address Translation (HAT) is always supported, and Linux kernel enables this capability by default. However, in case of emulated and virtualized IOMMU, this might not be the case.
+Alejandro as he is filling that gap
Quoted 8 lines
For example,current QEMU-emulated AMD vIOMMU does not support host translation for VFIO pass-through device, but the interrupt remapping support is required for x2APIC (i.e. kvm-msi-ext-dest-id is also not supported by the guest OS). This would require the guest kernel to boot with guest kernel option iommu=pt to by-pass the initialization of host (v1) table.
The AMD I/O Virtualization Technology (IOMMU) Specification Rev 3.10 [1]>
introduces a new flag 'HATDis' in the IVHD 11h IOMMU attributes to indicate
Quoted 145 lines
that HAT is not supported on a particular IOMMU instance.
Therefore, modifies the AMD IOMMU driver to detect the new HATDis attributes, and disable host translation and switch to use guest translation if it is available. Otherwise, the driver will disable DMA translation.
[1] https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/specifications/48882_IOMMU.pdf
Reviewed-by Suravee Suthikulpanit <[email protected]>Signed-off-by Ankit Soni <[email protected]>--- drivers/iommu/amd/amd_iommu.h | 1 + drivers/iommu/amd/amd_iommu_types.h | 6 +++++- drivers/iommu/amd/init.c | 23 +++++++++++++++++++++-- drivers/iommu/amd/iommu.c | 13 +++++++++++++ 4 files changed, 40 insertions(+), 3 deletions(-)drivers/iommu/amd/amd_iommu.h +1
-0@@ -43,6 +43,7 @@ extern int amd_iommu_guest_ir;extern enum protection_domain_mode amd_iommu_pgtable;extern int amd_iommu_gpt_level;extern unsigned long amd_iommu_pgsize_bitmap; +extern bool amd_iommu_hatdis;/* Protection domain ops */ void amd_iommu_init_identity_domain (void );drivers/iommu/amd/amd_iommu_types.h +5
-1@@ -460,6 +460,9 @@/* IOMMU Feature Reporting Field (for IVHD type 10h */ #define IOMMU_FEAT_GASUP_SHIFT 6 +/* IOMMU HATDIS for IVHD type 11h and 40h */ +#define IOMMU_IVHD_ATTR_HATDIS_SHIFT 0 +/* IOMMU Extended Feature Register (EFR) */ #define IOMMU_EFR_XTSUP_SHIFT 2#define IOMMU_EFR_GASUP_SHIFT 7@@ -558,7 +561,8 @@ struct amd_io_pgtable { };enum protection_domain_mode { -PD_MODE_V1 =1 , +PD_MODE_NONE , +PD_MODE_V1 ,PD_MODE_V2 , };drivers/iommu/amd/init.c +21
-2@@ -151,7 +151,7 @@ struct ivmd_header {bool amd_iommu_dump;bool amd_iommu_irq_remap__read_mostly ; -enum protection_domain_mode amd_iommu_pgtable =PD_MODE_V1 ; +enum protection_domain_mode amd_iommu_pgtable =PD_MODE_NONE ;/* Guest page table level */ int amd_iommu_gpt_level =PAGE_MODE_4_LEVEL ;@@ -168,6 +168,9 @@ static int amd_iommu_target_ivhd_type;u64 amd_iommu_efr;u64 amd_iommu_efr2; +/* dma translation not supported*/ +bool amd_iommu_hatdis; +/* SNP is enabled on the system? */ bool amd_iommu_snp_en;EXPORT_SYMBOL (amd_iommu_snp_en);@@ -1798,6 +1801,11 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h,if (h->efr_reg &BIT (IOMMU_EFR_XTSUP_SHIFT )) amd_iommu_xt_mode =IRQ_REMAP_X2APIC_MODE ; +if (h->efr_attr &BIT (IOMMU_IVHD_ATTR_HATDIS_SHIFT )) { +pr_warn_once ("Host Address Translation is not supported.\n" ); + amd_iommu_hatdis = true; + } +early_iommu_features_init (iommu, h);break ;@@ -2582,7 +2590,7 @@ static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg)u32 devid;struct dev_table_entry *dev_table = pci_seg->dev_table; -if (dev_table ==NULL ) +if (!dev_table || amd_iommu_pgtable ==PD_MODE_NONE )return ;for (devid =0 ; devid <= pci_seg->last_bdf; ++devid) {@@ -3095,6 +3103,17 @@ static int __init early_amd_iommu_init(void) } } +if (amd_iommu_hatdis) { +if (amd_iommu_v2_pgtbl_supported ()) + amd_iommu_pgtable =PD_MODE_V2 ; + }else if (amd_iommu_pgtable ==PD_MODE_NONE ) +/* +* If v1 page table is supported (i.e., amd_iommu_hatdis == 0) +* and page table type is not specified in command line, then +* use v1 page table. +*/ + amd_iommu_pgtable =PD_MODE_V1 ; +/* Disable any previously enabled IOMMUs */ if (!is_kdump_kernel () || amd_iommu_disabled)disable_iommus ();drivers/iommu/amd/iommu.c +10
-0@@ -2393,6 +2393,13 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev) pci_max_pasids(to_pci_dev(dev))); } +if (amd_iommu_pgtable ==PD_MODE_NONE ) { +pr_warn_once ("%s: DMA translation not supported by iommu.\n" , + __func__); + iommu_dev =ERR_PTR (-ENODEV ); + goto out_err; + } + out_err:iommu_completion_wait (iommu);@@ -2480,6 +2487,9 @@ static int pdom_setup_pgtable(struct protection_domain *domain,case PD_MODE_V2 : fmt =AMD_IOMMU_V2 ;break ; +case PD_MODE_NONE : +WARN_ON_ONCE (1 ); +return -EPERM ; } domain->iop.pgtbl.cfg.amd.nid =dev_to_node (dev);
drivers/iommu/amd/iommu.c static inline u64 dma_max_address(enum protection_domain_mode pgtable) · line 2519
Quoted 9 lines
drivers/iommu/amd/iommu.c +3
-0@@ -2501,6 +2511,9 @@ static inline u64 dma_max_address(enum protection_domain_mode pgtable)static bool amd_iommu_hd_support (struct amd_iommu *iommu) { +if (amd_iommu_hatdis) +return false; +return iommu && (iommu->features &FEATURE_HDSUP ); }
It's strange we seem to somehow have host translation disabled, while it advertises other translation-related features like the normal case.
In any case we should probably follow Intel's example (which does similar thing to HATSDis) where we only call invoke IOMMU groups iommu_device_register()/iommu_device_sysfs_add() with DMA translation enabled? That should simplify most of the patch as those codepaths are not reachable via kernel/userspace? Unless I am missing something ofc
See also commit c40aaaac10 ("iommu/vt-d: Gracefully handle DMAR units with no supported address widths"). I am not sure what else is the closest example here besides intel-iommu equivalent.
Re: [PATCH 1/2] iommu/amd: Add HATDis feature support
Hi Joao,
Thank you for review this patch.
Quoted 10 lines · Joao Martins
drivers/iommu/amd/iommu.c static inline u64 dma_max_address(enum protection_domain_mode pgtable) · line 2518
Quoted 7 lines
{
drivers/iommu/amd/iommu.c +3
-0+if (amd_iommu_hatdis) +return false; +return iommu && (iommu->features &FEATURE_HDSUP ); }It's strange we seem to somehow have host translation disabled, while it advertises other translation-related features like the normal case.
If HATDis bit is enabled driver will ignore host(v1) page table related field, this includes nested page table.
Quoted 10 lines
In any case we should probably follow Intel's example (which does similar thing to HATSDis) where we only call invoke IOMMU groups iommu_device_register()/iommu_device_sysfs_add() with DMA translation enabled? That should simplify most of the patch as those codepaths are not reachable via kernel/userspace? Unless I am missing something ofc
See also commit
c40aaaac10("iommu/vt-d: Gracefully handle DMAR units with no supported address widths"). I am not sure what else is the closest example here besides intel-iommu equivalent.
With intel patch you mentioned above, it seems that it is mostly handling "second stage translation support" disable, which will eventually disable dma translation. And in AMD case, HATDis bit indicates host(v1) translation is not available, then attempt to use guest(v2) translation, and if both page table modes are not available then disable dma tranlation.
Thanks,
-Ankit
Re: [PATCH 1/2] iommu/amd: Add HATDis feature support
Quoted 15 lines · Ankit Soni
Hi Joao,
Thank you for review this patch.Quoted 10 lines · Joao Martins
drivers/iommu/amd/iommu.c static inline u64 dma_max_address(enum protection_domain_mode pgtable) · line 2518
Quoted 7 lines
{
drivers/iommu/amd/iommu.c +3
-0+if (amd_iommu_hatdis) +return false; +return iommu && (iommu->features &FEATURE_HDSUP ); }It's strange we seem to somehow have host translation disabled, while it advertises other translation-related features like the normal case.
Quoted 3 lines
If HATDis bit is enabled driver will ignore host(v1) page table related field, this includes nested page table.
OK, I thought it was both actually
Quoted 11 lines
Quoted 10 lines
In any case we should probably follow Intel's example (which does similar thing to HATSDis) where we only call invoke IOMMU groups iommu_device_register()/iommu_device_sysfs_add() with DMA translation enabled? That should simplify most of the patch as those codepaths are not reachable via kernel/userspace? Unless I am missing something ofc
See also commit
c40aaaac10("iommu/vt-d: Gracefully handle DMAR units with no supported address widths"). I am not sure what else is the closest example here besides intel-iommu equivalent.
Quoted 5 lines
With intel patch you mentioned above, it seems that it is mostly handling "second stage translation support" disable, which will eventually disable dma translation. And in AMD case, HATDis bit indicates host(v1) translation is not available, then attempt to use guest(v2) translation, and if both page table modes are not available then disable dma tranlation.
OK, I guess it makes sense if HATDis is v1 only.
My other call out was that when we disable dma-translation all together (aka both modes), then we shouldn't advertise the IOMMU groups (internally and to userspace) by not calling iommu_device_register()/iommu_device_sysfs_add().
Joao
Re: [PATCH 1/2] iommu/amd: Add HATDis feature support
Hi,
Quoted 6 lines · Joao Martins
Quoted 5 lines
With intel patch you mentioned above, it seems that it is mostly handling "second stage translation support" disable, which will eventually disable dma translation. And in AMD case, HATDis bit indicates host(v1) translation is not available, then attempt to use guest(v2) translation, and if both page table modes are not available then disable dma tranlation.
Quoted 7 lines
OK, I guess it makes sense if HATDis is v1 only.
My other call out was that when we disable dma-translation all together (aka both modes), then we shouldn't advertise the IOMMU groups (internally and to userspace) by not calling iommu_device_register()/iommu_device_sysfs_add().
Joao
Sorry for the late reply. I had cross-checked it; if the probe fails, then IOMMU groups will not be populated, and eventually, it will not have significance for calling iommu_device_register()/iommu_device_sysfs_add().
-Ankit
Re: [PATCH 1/2] iommu/amd: Add HATDis feature support
Quoted 9 lines · Ankit Soni
Quoted 8 lines · Joao Martins
Quoted 5 lines
With intel patch you mentioned above, it seems that it is mostly handling "second stage translation support" disable, which will eventually disable dma translation. And in AMD case, HATDis bit indicates host(v1) translation is not available, then attempt to use guest(v2) translation, and if both page table modes are not available then disable dma tranlation.
OK, I guess it makes sense if HATDis is v1 only.
Quoted 9 lines
Quoted 4 lines
My other call out was that when we disable dma-translation all together (aka both modes), then we shouldn't advertise the IOMMU groups (internally and to userspace) by not calling iommu_device_register()/iommu_device_sysfs_add().
Sorry for the late reply. I had cross-checked it; if the probe fails, then IOMMU groups will not be populated, and eventually, it will not have significance for calling iommu_device_register()/iommu_device_sysfs_add().
It would nonetheless populate a ivhd entry in sysfs needlessly but with an empty devices list (qemu diff at the tail end for how I checked it; it's only missing the ILLEGAL_DEVICE_TABLE_ENTRY event being generated, but enough to check the first patch with sw iommu) e.g. as far as I checked:
$ find /sys | grep ivhd /sys/class/iommu/ivhd0 /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0 /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/uevent /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu/cap /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu/features /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/devices /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/device /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/subsystem
-->8--
hw/i386/acpi-build.c +0 -0
@@ -2326,7 +2326,11 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker,
const char *oem_id,
/* IOMMU info */
build_append_int_noprefix(table_data, 0, 2);
/* IOMMU Attributes */- build_append_int_noprefix(table_data, 0, 4);
+ if (!s->dma_translation) {
+ build_append_int_noprefix(table_data, (1UL << 0) /* HATDis */, 4);
+ } else {
+ build_append_int_noprefix(table_data, 0, 4);
+ }
/* EFR Register Image */
build_append_int_noprefix(table_data,
amdvi_extended_feature_register(s),hw/i386/amd_iommu.c +3 -0
@@ -83,6 +83,9 @@ uint64_t amdvi_extended_feature_register(AMDVIState *s)if (s->xtsup) { feature |=AMDVI_FEATURE_XT ; } +if (!s->dma_translation) { + feature |=AMDVI_HATS_MODE_RESERVED ; + }return feature; }
@@ -1665,6 +1668,7 @@ static void amdvi_sysbus_realize(DeviceState *dev, Error
**errp)
}
static Property amdvi_properties[] = {
+ DEFINE_PROP_BOOL("dma-translation", AMDVIState, dma_translation, true),
DEFINE_PROP_BOOL("xtsup", AMDVIState, xtsup, false), DEFINE_PROP_END_OF_LIST(),
};
hw/i386/amd_iommu.h +2 -0
@@ -169,6 +169,7 @@/* AMDVI paging mode */ #define AMDVI_GATS_MODE (2ULL << 12)#define AMDVI_HATS_MODE (2ULL << 10) +#define AMDVI_HATS_MODE_RESERVED (2ULL << 11)/* IOTLB */ #define AMDVI_IOTLB_MAX_SIZE 1024
@@ -371,6 +372,7 @@ struct AMDVIState {/* Interrupt remapping */ bool ga_enabled;bool xtsup; +bool dma_translation; };uint64_t amdvi_extended_feature_register (AMDVIState *s);
Re: [PATCH 1/2] iommu/amd: Add HATDis feature support
Hi,
Quoted 25 lines · Joao Martins
Quoted 9 lines · Ankit Soni
Quoted 8 lines · Joao Martins
Quoted 5 lines
With intel patch you mentioned above, it seems that it is mostly handling "second stage translation support" disable, which will eventually disable dma translation. And in AMD case, HATDis bit indicates host(v1) translation is not available, then attempt to use guest(v2) translation, and if both page table modes are not available then disable dma tranlation.
OK, I guess it makes sense if HATDis is v1 only.
Quoted 9 lines
Quoted 4 lines
My other call out was that when we disable dma-translation all together (aka both modes), then we shouldn't advertise the IOMMU groups (internally and to userspace) by not calling iommu_device_register()/iommu_device_sysfs_add().
Sorry for the late reply. I had cross-checked it; if the probe fails, then IOMMU groups will not be populated, and eventually, it will not have significance for calling iommu_device_register()/iommu_device_sysfs_add().
It would nonetheless populate a ivhd entry in sysfs needlessly but with an empty devices list (qemu diff at the tail end for how I checked it; it's only missing the
ILLEGAL_DEVICE_TABLE_ENTRYevent being generated, but enough to check the first patch with sw iommu) e.g. as far as I checked:
Quoted 11 lines
$ find /sys | grep ivhd /sys/class/iommu/ivhd0 /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0 /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/uevent /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu/cap /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu/features /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/devices /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/device /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/subsystem
I was assuming, since iommu is still active for interrupt remapping, user may need info for cap and feature using /sys fs. @vasant: can you please suggest on this?
Quoted 56 lines
-->8--
hw/i386/acpi-build.c +5
-1@@ -2326,7 +2326,11 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker,const char *oem_id,/* IOMMU info */ build_append_int_noprefix(table_data, 0, 2);/* IOMMU Attributes */ -build_append_int_noprefix (table_data,0 ,4 ); +if (!s->dma_translation) { +build_append_int_noprefix (table_data, (1UL <<0 )/* HATDis */ ,4 ); + }else { +build_append_int_noprefix (table_data,0 ,4 ); + }/* EFR Register Image */ build_append_int_noprefix(table_data,
amdvi_extended_feature_register(s),hw/i386/amd_iommu.c +4
-0@@ -83,6 +83,9 @@ uint64_t amdvi_extended_feature_register(AMDVIState *s)if (s->xtsup) { feature |=AMDVI_FEATURE_XT ; } +if (!s->dma_translation) { + feature |=AMDVI_HATS_MODE_RESERVED ; + }return feature; }@@ -1665,6 +1668,7 @@ static void amdvi_sysbus_realize(DeviceState *dev, Error **errp) }static Property amdvi_properties[] = { +DEFINE_PROP_BOOL ("dma-translation" , AMDVIState, dma_translation, true),DEFINE_PROP_BOOL ("xtsup" , AMDVIState, xtsup, false),DEFINE_PROP_END_OF_LIST (),};
hw/i386/amd_iommu.h +1
-0@@ -169,6 +169,7 @@/* AMDVI paging mode */ #define AMDVI_GATS_MODE (2ULL << 12)#define AMDVI_HATS_MODE (2ULL << 10) +#define AMDVI_HATS_MODE_RESERVED (2ULL << 11)/* IOTLB */ #define AMDVI_IOTLB_MAX_SIZE 1024
hw/i386/amd_iommu.h struct AMDVIState { · line 378
Quoted 7 lines
hw/i386/amd_iommu.h +1
-0@@ -371,6 +372,7 @@ struct AMDVIState {/* Interrupt remapping */ bool ga_enabled;bool xtsup; +bool dma_translation; };uint64_t amdvi_extended_feature_register (AMDVIState *s);
Thank you for QEMU patch, i also had similar patch ready, i was waiting for kernel patch to be submitted.
- Ankit
Vasant Hegde
maintainerRe: [PATCH 1/2] iommu/amd: Add HATDis feature support
Hi Ankit,
Quoted 40 lines · Ankit Soni
Hi,
Quoted 25 lines · Joao Martins
Quoted 9 lines · Ankit Soni
Quoted 8 lines · Joao Martins
Quoted 5 lines
With intel patch you mentioned above, it seems that it is mostly handling "second stage translation support" disable, which will eventually disable dma translation. And in AMD case, HATDis bit indicates host(v1) translation is not available, then attempt to use guest(v2) translation, and if both page table modes are not available then disable dma tranlation.
OK, I guess it makes sense if HATDis is v1 only.
Quoted 9 lines
Quoted 4 lines
My other call out was that when we disable dma-translation all together (aka both modes), then we shouldn't advertise the IOMMU groups (internally and to userspace) by not calling iommu_device_register()/iommu_device_sysfs_add().
Sorry for the late reply. I had cross-checked it; if the probe fails, then IOMMU groups will not be populated, and eventually, it will not have significance for calling iommu_device_register()/iommu_device_sysfs_add().
It would nonetheless populate a ivhd entry in sysfs needlessly but with an empty devices list (qemu diff at the tail end for how I checked it; it's only missing the
ILLEGAL_DEVICE_TABLE_ENTRYevent being generated, but enough to check the first patch with sw iommu) e.g. as far as I checked:Quoted 11 lines
$ find /sys | grep ivhd /sys/class/iommu/ivhd0 /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0 /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/uevent /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu/cap /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu/features /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/devices /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/device /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/subsystem
Quoted 3 lines
I was assuming, since iommu is still active for interrupt remapping, user may need info for cap and feature using /sys fs. @vasant: can you please suggest on this?
I don't have strong preference. But it looks like intel skips populating sysfs properties. May be we can match the behaviour and skip populating ivdh entries.
-Vasant
Re: [PATCH 1/2] iommu/amd: Add HATDis feature support
Quoted 44 lines · Vasant Hegde
Hi Ankit,
Quoted 40 lines · Ankit Soni
Hi,
Quoted 36 lines · Joao Martins
Quoted 9 lines · Ankit Soni
Quoted 8 lines · Joao Martins
Quoted 5 lines
With intel patch you mentioned above, it seems that it is mostly handling "second stage translation support" disable, which will eventually disable dma translation. And in AMD case, HATDis bit indicates host(v1) translation is not available, then attempt to use guest(v2) translation, and if both page table modes are not available then disable dma tranlation.
OK, I guess it makes sense if HATDis is v1 only.
Quoted 9 lines
Quoted 4 lines
My other call out was that when we disable dma-translation all together (aka both modes), then we shouldn't advertise the IOMMU groups (internally and to userspace) by not calling iommu_device_register()/iommu_device_sysfs_add().
Sorry for the late reply. I had cross-checked it; if the probe fails, then IOMMU groups will not be populated, and eventually, it will not have significance for calling iommu_device_register()/iommu_device_sysfs_add().
It would nonetheless populate a ivhd entry in sysfs needlessly but with an empty devices list (qemu diff at the tail end for how I checked it; it's only missing the
ILLEGAL_DEVICE_TABLE_ENTRYevent being generated, but enough to check the first patch with sw iommu) e.g. as far as I checked:$ find /sys | grep ivhd /sys/class/iommu/ivhd0 /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0 /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/uevent /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu/cap /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/amd-iommu/features /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/devices /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/device /sys/devices/pci0000:00/0000:00:05.0/iommu/ivhd0/subsystem
Quoted 10 lines
Quoted 3 lines
I was assuming, since iommu is still active for interrupt remapping, user may need info for cap and feature using /sys fs. @vasant: can you please suggest on this?
I don't have strong preference. But it looks like intel skips populating sysfs properties. May be we can match the behaviour and skip populating ivdh entries.
-Vasant
Sure vasant, thanks for confirming. I'll post v3 soon with this change. Thanks,
-Ankit
Vasant Hegde
maintainerRe: [PATCH 1/2] iommu/amd: Add HATDis feature support
In reply to Joao MartinsHi Joao,
[+Baolu to get clarification on intel driver behaviour.]
Quoted 14 lines · Joao Martins
Quoted 3 lines · Ankit Soni
Current AMD IOMMU assumes Host Address Translation (HAT) is always supported, and Linux kernel enables this capability by default. However, in case of emulated and virtualized IOMMU, this might not be the case.
+Alejandro as he is filling that gap
Quoted 7 lines
For example,current QEMU-emulated AMD vIOMMU does not support host translation for VFIO pass-through device, but the interrupt remapping support is required for x2APIC (i.e. kvm-msi-ext-dest-id is also not supported by the guest OS). This would require the guest kernel to boot with guest kernel option iommu=pt to by-pass the initialization of host (v1) table.
Quoted 20 lines
Quoted 1 line
The AMD I/O Virtualization Technology (IOMMU) Specification Rev 3.10 [1]>
introduces a new flag 'HATDis' in the IVHD 11h IOMMU attributes to indicate
Quoted 18 lines
that HAT is not supported on a particular IOMMU instance.
Therefore, modifies the AMD IOMMU driver to detect the new HATDis attributes, and disable host translation and switch to use guest translation if it is available. Otherwise, the driver will disable DMA translation.
[1] https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/specifications/48882_IOMMU.pdf
Reviewed-by Suravee Suthikulpanit <[email protected]>Signed-off-by Ankit Soni <[email protected]>--- drivers/iommu/amd/amd_iommu.h | 1 + drivers/iommu/amd/amd_iommu_types.h | 6 +++++- drivers/iommu/amd/init.c | 23 +++++++++++++++++++++-- drivers/iommu/amd/iommu.c | 13 +++++++++++++ 4 files changed, 40 insertions(+), 3 deletions(-)
.../...
Quoted 30 lines
Quoted 30 lines
drivers/iommu/amd/iommu.c +10
-0@@ -2393,6 +2393,13 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev) pci_max_pasids(to_pci_dev(dev))); } +if (amd_iommu_pgtable ==PD_MODE_NONE ) { +pr_warn_once ("%s: DMA translation not supported by iommu.\n" , + __func__); + iommu_dev =ERR_PTR (-ENODEV ); + goto out_err; + } + out_err:iommu_completion_wait (iommu);@@ -2480,6 +2487,9 @@ static int pdom_setup_pgtable(struct protection_domain *domain,case PD_MODE_V2 : fmt =AMD_IOMMU_V2 ;break ; +case PD_MODE_NONE : +WARN_ON_ONCE (1 ); +return -EPERM ; } domain->iop.pgtbl.cfg.amd.nid =dev_to_node (dev);@@ -2501,6 +2511,9 @@ static inline u64 dma_max_address(enum protection_domain_mode pgtable)
Quoted 11 lines
drivers/iommu/amd/iommu.c static inline u64 dma_max_address(enum protection_domain_mode pgtable) · line 2519
Quoted 8 lines
drivers/iommu/amd/iommu.c +3
-0static bool amd_iommu_hd_support (struct amd_iommu *iommu) { +if (amd_iommu_hatdis) +return false; +return iommu && (iommu->features &FEATURE_HDSUP ); }It's strange we seem to somehow have host translation disabled, while it advertises other translation-related features like the normal case.
I think even if qemu advertises those features we shouldn't hit this code path as probe() will fail and core shouldn't try to allocate domain, etc.
I was extra cautious and suggested to add this check!
Quoted 10 lines
In any case we should probably follow Intel's example (which does similar thing to HATSDis) where we only call invoke IOMMU groups iommu_device_register()/iommu_device_sysfs_add() with DMA translation enabled? That should simplify most of the patch as those codepaths are not reachable via kernel/userspace? Unless I am missing something ofc
See also commit
c40aaaac10("iommu/vt-d: Gracefully handle DMAR units with no supported address widths"). I am not sure what else is the closest example here besides intel-iommu equivalent.
@Baolu,
Looking into intel driver, my understanding is if DMA is not supported, intel
driver will set drhd->ignored to 1 (alloc_iommu()). So iommu_is_dummy() check will return true and hence intel_iommu_probe_device() will fail. But it will continue to support interrupt remapping. Is that the correct understanding?
-Vasant
Vasant Hegde
maintainerRe: [PATCH 1/2] iommu/amd: Add HATDis feature support
In reply to Ankit SoniHi,
Quoted 8 lines · Ankit Soni
Current AMD IOMMU assumes Host Address Translation (HAT) is always supported, and Linux kernel enables this capability by default. However, in case of emulated and virtualized IOMMU, this might not be the case. For example,current QEMU-emulated AMD vIOMMU does not support host translation for VFIO pass-through device, but the interrupt remapping support is required for x2APIC (i.e. kvm-msi-ext-dest-id is also not supported by the guest OS). This would require the guest kernel to boot with guest kernel option iommu=pt to by-pass the initialization of> host (v1)
table.
Quoted 62 lines
The AMD I/O Virtualization Technology (IOMMU) Specification Rev 3.10 [1] introduces a new flag 'HATDis' in the IVHD 11h IOMMU attributes to indicate that HAT is not supported on a particular IOMMU instance.
Therefore, modifies the AMD IOMMU driver to detect the new HATDis attributes, and disable host translation and switch to use guest translation if it is available. Otherwise, the driver will disable DMA translation.
[1] https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/specifications/48882_IOMMU.pdf
Reviewed-by Suravee Suthikulpanit <[email protected]>Signed-off-by Ankit Soni <[email protected]>--- drivers/iommu/amd/amd_iommu.h | 1 + drivers/iommu/amd/amd_iommu_types.h | 6 +++++- drivers/iommu/amd/init.c | 23 +++++++++++++++++++++-- drivers/iommu/amd/iommu.c | 13 +++++++++++++ 4 files changed, 40 insertions(+), 3 deletions(-)drivers/iommu/amd/amd_iommu.h +1
-0@@ -43,6 +43,7 @@ extern int amd_iommu_guest_ir;extern enum protection_domain_mode amd_iommu_pgtable;extern int amd_iommu_gpt_level;extern unsigned long amd_iommu_pgsize_bitmap; +extern bool amd_iommu_hatdis;/* Protection domain ops */ void amd_iommu_init_identity_domain (void );drivers/iommu/amd/amd_iommu_types.h +5
-1@@ -460,6 +460,9 @@/* IOMMU Feature Reporting Field (for IVHD type 10h */ #define IOMMU_FEAT_GASUP_SHIFT 6 +/* IOMMU HATDIS for IVHD type 11h and 40h */ +#define IOMMU_IVHD_ATTR_HATDIS_SHIFT 0 +/* IOMMU Extended Feature Register (EFR) */ #define IOMMU_EFR_XTSUP_SHIFT 2#define IOMMU_EFR_GASUP_SHIFT 7@@ -558,7 +561,8 @@ struct amd_io_pgtable { };enum protection_domain_mode { -PD_MODE_V1 =1 , +PD_MODE_NONE , +PD_MODE_V1 ,PD_MODE_V2 , };drivers/iommu/amd/init.c +0
-0
drivers/iommu/amd/init.c struct ivmd_header { · line 154
Quoted 5 lines
drivers/iommu/amd/init.c +1
-1@@ -151,7 +151,7 @@ struct ivmd_header {bool amd_iommu_dump;bool amd_iommu_irq_remap__read_mostly ; -enum protection_domain_mode amd_iommu_pgtable =PD_MODE_V1 ; +enum protection_domain_mode amd_iommu_pgtable =PD_MODE_NONE ;
Why not keep it as PD_MODE_V1 (as its our default page table) so that we can remove explict PD_MODE_V1 assignment in below hunk?
drivers/iommu/amd/init.c static int amd_iommu_target_ivhd_type; · line 171
Quoted 8 lines
drivers/iommu/amd/init.c +1
-0/* Guest page table level */ int amd_iommu_gpt_level =PAGE_MODE_4_LEVEL ;@@ -168,6 +168,9 @@ static int amd_iommu_target_ivhd_type;u64 amd_iommu_efr;u64 amd_iommu_efr2; +/* dma translation not supported*/
Host (v2) page table is not supported.
Quoted 27 lines
drivers/iommu/amd/init.c +8
-1+bool amd_iommu_hatdis; +/* SNP is enabled on the system? */ bool amd_iommu_snp_en;EXPORT_SYMBOL (amd_iommu_snp_en);@@ -1798,6 +1801,11 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h,if (h->efr_reg &BIT (IOMMU_EFR_XTSUP_SHIFT )) amd_iommu_xt_mode =IRQ_REMAP_X2APIC_MODE ; +if (h->efr_attr &BIT (IOMMU_IVHD_ATTR_HATDIS_SHIFT )) { +pr_warn_once ("Host Address Translation is not supported.\n" ); + amd_iommu_hatdis = true; + } +early_iommu_features_init (iommu, h);break ;@@ -2582,7 +2590,7 @@ static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg)u32 devid;struct dev_table_entry *dev_table = pci_seg->dev_table; -if (dev_table ==NULL ) +if (!dev_table || amd_iommu_pgtable ==PD_MODE_NONE )return ;for (devid =0 ; devid <= pci_seg->last_bdf; ++devid) {
drivers/iommu/amd/init.c static int __init early_amd_iommu_init(void) · line 3106
Quoted 4 lines
drivers/iommu/amd/init.c +1
-0@@ -3095,6 +3103,17 @@ static int __init early_amd_iommu_init(void) } } +if (amd_iommu_hatdis) {
I missed it in the internal review. This introduces ordering dependency (v2 page table check should be done before this). IMO its worth to add an explicit comment so that its clear.
-Vasant
Re: [PATCH 1/2] iommu/amd: Add HATDis feature support
Hi,
Quoted 9 lines · Vasant Hegde
Hi,
Quoted 6 lines · Ankit Soni
drivers/iommu/amd/init.c +0
-0@@ -151,7 +151,7 @@ struct ivmd_header {bool amd_iommu_dump;bool amd_iommu_irq_remap__read_mostly ;
Quoted 7 lines
drivers/iommu/amd/init.c struct ivmd_header { · line 154
Quoted 2 lines
drivers/iommu/amd/init.c +1
-1-enum protection_domain_mode amd_iommu_pgtable =PD_MODE_V1 ; +enum protection_domain_mode amd_iommu_pgtable =PD_MODE_NONE ;Why not keep it as
PD_MODE_V1(as its our default page table) so that we can remove explictPD_MODE_V1assignment in below hunk?
Yes it will remove PD_MODE_V1 assignment hunk. But, Intension to keep PD_MODE_NONE is more clean code, where by default page table mode is NONE, and with proper checks and default/command line input, driver changes it.
Quoted 11 lines
drivers/iommu/amd/init.c static int amd_iommu_target_ivhd_type; · line 171
Quoted 8 lines
drivers/iommu/amd/init.c +1
-0/* Guest page table level */ int amd_iommu_gpt_level =PAGE_MODE_4_LEVEL ;@@ -168,6 +168,9 @@ static int amd_iommu_target_ivhd_type;u64 amd_iommu_efr;u64 amd_iommu_efr2; +/* dma translation not supported*/ Host (v2) page table is not supported.
I'll rephrase this.
Quoted 30 lines
Quoted 30 lines
drivers/iommu/amd/init.c +8
-1+bool amd_iommu_hatdis; +/* SNP is enabled on the system? */ bool amd_iommu_snp_en;EXPORT_SYMBOL (amd_iommu_snp_en);@@ -1798,6 +1801,11 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h,if (h->efr_reg &BIT (IOMMU_EFR_XTSUP_SHIFT )) amd_iommu_xt_mode =IRQ_REMAP_X2APIC_MODE ; +if (h->efr_attr &BIT (IOMMU_IVHD_ATTR_HATDIS_SHIFT )) { +pr_warn_once ("Host Address Translation is not supported.\n" ); + amd_iommu_hatdis = true; + } +early_iommu_features_init (iommu, h);break ;@@ -2582,7 +2590,7 @@ static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg)u32 devid;struct dev_table_entry *dev_table = pci_seg->dev_table; -if (dev_table ==NULL ) +if (!dev_table || amd_iommu_pgtable ==PD_MODE_NONE )return ;for (devid =0 ; devid <= pci_seg->last_bdf; ++devid) {@@ -3095,6 +3103,17 @@ static int __init early_amd_iommu_init(void) } }
Quoted 8 lines
drivers/iommu/amd/init.c static int __init early_amd_iommu_init(void) · line 3106
Quoted 1 line
drivers/iommu/amd/init.c +1
-0+if (amd_iommu_hatdis) {I missed it in the internal review. This introduces ordering dependency (v2 page table check should be done before this). IMO its worth to add an explicit comment so that its clear.
-Vasant
Sure, i'll move this below v2 page table check.
-Ankit
PATCH 2/2 iommu/amd: Add efr[HATS] max v1 page table level
In reply to Ankit SoniThe EFR[HATS] bits indicate maximum host translation level supported by IOMMU. Adding support to set the maximum host page table level as indicated by EFR[HATS]. If the HATS=11b (reserved), the driver will attempt to use guest page table for DMA API.
--- drivers/iommu/amd/amd_iommu.h | 1 + drivers/iommu/amd/amd_iommu_types.h | 1 + drivers/iommu/amd/init.c | 16 ++++++++++++++++ drivers/iommu/amd/io_pgtable.c | 4 ++-- drivers/iommu/amd/iommu.c | 2 +- 5 files changed, 21 insertions(+), 3 deletions(-)
drivers/iommu/amd/amd_iommu.h +1 -0
@@ -42,6 +42,7 @@ int amd_iommu_enable_faulting(unsigned int cpu);extern int amd_iommu_guest_ir;extern enum protection_domain_mode amd_iommu_pgtable;extern int amd_iommu_gpt_level; +extern u8 amd_iommu_hpt_level;extern unsigned long amd_iommu_pgsize_bitmap;extern bool amd_iommu_hatdis;
drivers/iommu/amd/amd_iommu_types.h +1 -0
@@ -96,6 +96,7 @@#define FEATURE_GA BIT_ULL(7)#define FEATURE_HE BIT_ULL(8)#define FEATURE_PC BIT_ULL(9) +#define FEATURE_HATS GENMASK_ULL(11, 10)#define FEATURE_GATS GENMASK_ULL(13, 12)#define FEATURE_GLX GENMASK_ULL(15, 14)#define FEATURE_GAM_VAPIC BIT_ULL(21)
drivers/iommu/amd/init.c +16 -0
@@ -152,6 +152,8 @@ bool amd_iommu_dump;bool amd_iommu_irq_remap__read_mostly ;enum protection_domain_mode amd_iommu_pgtable =PD_MODE_NONE ; +/* Host page table level */ +u8 amd_iommu_hpt_level;/* Guest page table level */ int amd_iommu_gpt_level =PAGE_MODE_4_LEVEL ;
@@ -3052,6 +3054,7 @@ static int __init early_amd_iommu_init(void)struct acpi_table_header *ivrs_base;int ret;acpi_status status; +u8 efr_hats;if (!amd_iommu_detected)return -ENODEV ;
@@ -3096,6 +3099,19 @@ static int __init early_amd_iommu_init(void) FIELD_GET(FEATURE_GATS, amd_iommu_efr) == GUEST_PGTABLE_5_LEVEL) amd_iommu_gpt_level =PAGE_MODE_5_LEVEL ; + efr_hats =FIELD_GET (FEATURE_HATS , amd_iommu_efr); +if (efr_hats !=0x3 ) { +/* +* efr[HATS] bits specify the maximum host translation level +* supported, with LEVEL 4 being initial max level. +*/ + amd_iommu_hpt_level = efr_hats +PAGE_MODE_4_LEVEL ; + }else { +pr_warn_once ("Disable host address translation due to invalid max level (%#x).\n" , + efr_hats); + amd_iommu_hatdis = true; + } +if (amd_iommu_pgtable ==PD_MODE_V2 ) {if (!amd_iommu_v2_pgtbl_supported ()) {pr_warn ("Cannot enable v2 page table for DMA-API. Fallback to v1.\n" );
drivers/iommu/amd/io_pgtable.c +2 -2
@@ -132,7 +132,7 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable, goto out; ret = false; -if (WARN_ON_ONCE (pgtable->mode ==PAGE_MODE_6_LEVEL )) +if (WARN_ON_ONCE (pgtable->mode == amd_iommu_hpt_level)) goto out; *pte =PM_LEVEL_PDE (pgtable->mode,iommu_virt_to_phys (pgtable->root));
@@ -531,7 +531,7 @@ static void v1_free_pgtable(struct io_pgtable *iop)/* Page-table is not visible to IOMMU anymore, so free it */ BUG_ON (pgtable->mode <PAGE_MODE_NONE || - pgtable->mode >PAGE_MODE_6_LEVEL ); + pgtable->mode > amd_iommu_hpt_level);free_sub_pt (pgtable->root, pgtable->mode, &freelist);iommu_put_pages_list (&freelist);
drivers/iommu/amd/iommu.c +1 -1
@@ -2503,7 +2503,7 @@ static int pdom_setup_pgtable(struct protection_domain *domain,static inline u64 dma_max_address (enum protection_domain_mode pgtable) {if (pgtable ==PD_MODE_V1 ) -return ~0ULL ; +return PM_LEVEL_SIZE (amd_iommu_hpt_level);/* V2 with 4/5 level page table */ return ((1ULL <<PM_LEVEL_SHIFT (amd_iommu_gpt_level)) -1 );
Signature · 1 line
2.43.0
Re: [PATCH 2/2] iommu/amd: Add efr[HATS] max v1 page table level
Quoted 7 lines · Ankit Soni
The EFR[HATS] bits indicate maximum host translation level supported by IOMMU. Adding support to set the maximum host page table level as indicated by EFR[HATS]. If the HATS=11b (reserved), the driver will attempt to use guest page table for DMA API.
Reviewed-by Suravee Suthikulpanit <[email protected]>Signed-off-by Ankit Soni <[email protected]>
Minor nit.
Quoted 56 lines
--- drivers/iommu/amd/amd_iommu.h | 1 + drivers/iommu/amd/amd_iommu_types.h | 1 + drivers/iommu/amd/init.c | 16 ++++++++++++++++ drivers/iommu/amd/io_pgtable.c | 4 ++-- drivers/iommu/amd/iommu.c | 2 +- 5 files changed, 21 insertions(+), 3 deletions(-)drivers/iommu/amd/amd_iommu.h +1
-0@@ -42,6 +42,7 @@ int amd_iommu_enable_faulting(unsigned int cpu);extern int amd_iommu_guest_ir;extern enum protection_domain_mode amd_iommu_pgtable;extern int amd_iommu_gpt_level; +extern u8 amd_iommu_hpt_level;extern unsigned long amd_iommu_pgsize_bitmap;extern bool amd_iommu_hatdis;drivers/iommu/amd/amd_iommu_types.h +1
-0@@ -96,6 +96,7 @@#define FEATURE_GA BIT_ULL(7)#define FEATURE_HE BIT_ULL(8)#define FEATURE_PC BIT_ULL(9) +#define FEATURE_HATS GENMASK_ULL(11, 10)#define FEATURE_GATS GENMASK_ULL(13, 12)#define FEATURE_GLX GENMASK_ULL(15, 14)#define FEATURE_GAM_VAPIC BIT_ULL(21)drivers/iommu/amd/init.c +3
-0@@ -152,6 +152,8 @@ bool amd_iommu_dump;bool amd_iommu_irq_remap__read_mostly ;enum protection_domain_mode amd_iommu_pgtable =PD_MODE_NONE ; +/* Host page table level */ +u8 amd_iommu_hpt_level;/* Guest page table level */ int amd_iommu_gpt_level =PAGE_MODE_4_LEVEL ;@@ -3052,6 +3054,7 @@ static int __init early_amd_iommu_init(void)struct acpi_table_header *ivrs_base;int ret;acpi_status status; +u8 efr_hats;if (!amd_iommu_detected)return -ENODEV ;@@ -3096,6 +3099,19 @@ static int __init early_amd_iommu_init(void) FIELD_GET(FEATURE_GATS, amd_iommu_efr) == GUEST_PGTABLE_5_LEVEL) amd_iommu_gpt_level =PAGE_MODE_5_LEVEL ;
drivers/iommu/amd/init.c static int __init early_amd_iommu_init(void) · line 3110
Quoted 10 lines
drivers/iommu/amd/init.c +9
-0+ efr_hats =FIELD_GET (FEATURE_HATS , amd_iommu_efr); +if (efr_hats !=0x3 ) { +/* +* efr[HATS] bits specify the maximum host translation level +* supported, with LEVEL 4 being initial max level. +*/ + amd_iommu_hpt_level = efr_hats +PAGE_MODE_4_LEVEL ; + }else { + pr_warn_once("Disable host address translation due to invalid max level (%#x).\n",
s/invalid max level/invalid translation level/
-Vasant
Re: [PATCH 2/2] iommu/amd: Add efr[HATS] max v1 page table level
Quoted 11 lines · Vasant Hegde
drivers/iommu/amd/init.c static int __init early_amd_iommu_init(void) · line 3110
Quoted 9 lines
drivers/iommu/amd/init.c +9
-0+ efr_hats =FIELD_GET (FEATURE_HATS , amd_iommu_efr); +if (efr_hats !=0x3 ) { +/* +* efr[HATS] bits specify the maximum host translation level +* supported, with LEVEL 4 being initial max level. +*/ + amd_iommu_hpt_level = efr_hats +PAGE_MODE_4_LEVEL ; + }else { + pr_warn_once("Disable host address translation due to invalid max level (%#x).\n",s/invalid max level/invalid translation level/
This should have a FW_BUG annotation too?
Jason
Vasant Hegde
maintainerRe: [PATCH 2/2] iommu/amd: Add efr[HATS] max v1 page table level
Quoted 13 lines · Jason Gunthorpe
Quoted 11 lines · Vasant Hegde
drivers/iommu/amd/init.c static int __init early_amd_iommu_init(void) · line 3110
Quoted 9 lines
drivers/iommu/amd/init.c +9
-0+ efr_hats =FIELD_GET (FEATURE_HATS , amd_iommu_efr); +if (efr_hats !=0x3 ) { +/* +* efr[HATS] bits specify the maximum host translation level +* supported, with LEVEL 4 being initial max level. +*/ + amd_iommu_hpt_level = efr_hats +PAGE_MODE_4_LEVEL ; + }else { + pr_warn_once("Disable host address translation due to invalid max level (%#x).\n",s/invalid max level/invalid translation level/
Quoted 1 line
This should have a
FW_BUGannotation too?
Ack. We can add FW_BUG.
-Vasant