Support TDX guests on Hyper-V (the x86/tdx part)
Subsystems (5)
Dexuan Cui
maintainerv9 cover Support TDX guests on Hyper-V (the x86/tdx part)
The two patches are based on today's tip.git's master branch.
Note: the two patches don't apply to the current x86/tdx branch, which doesn't have commit 75d090fd167a ("x86/tdx: Add unaccepted memory support").
As Dave suggested, I moved some local variables of tdx_map_gpa() to inside the loop. I added Sathyanarayanan's Reviewed-by.
Please review.
FWIW, the old versons are here:
v8: https://lwn.net/ml/linux-kernel/[email protected]/
v7: https://lwn.net/ml/linux-kernel/20230616044701.15888-1-decui%40microsoft.com/
v6: https://lwn.net/ml/linux-kernel/[email protected]/
Dexuan Cui (2):
x86/tdx: Retry TDVMCALL_MAP_GPA() when needed x86/tdx: Support vmalloc() for tdx_enc_status_changed()
arch/x86/coco/tdx/tdx.c | 87 ++++++++++++++++++++++++++----- arch/x86/include/asm/shared/tdx.h | 2 + 2 files changed, 77 insertions(+), 12 deletions(-)
Signature · 1 line
2.25.1
Dexuan Cui
maintainerPATCH v9 1/2 x86/tdx: Retry TDVMCALL_MAP_GPA() when needed
GHCI spec for TDX 1.0 says that the MapGPA call may fail with the R10 error code = TDG.VP.VMCALL_RETRY (1), and the guest must retry this operation for the pages in the region starting at the GPA specified in R11.
When a fully enlightened TDX guest runs on Hyper-V, Hyper-V can return the retry error when set_memory_decrypted() is called to decrypt up to 1GB of swiotlb bounce buffers.
--- arch/x86/coco/tdx/tdx.c | 64 +++++++++++++++++++++++++------ arch/x86/include/asm/shared/tdx.h | 2 + 2 files changed, 54 insertions(+), 12 deletions(-)
Changes in v2:
Used __tdx_hypercall() directly in tdx_map_gpa(). Added a max_retry_cnt of 1000.
Renamed a few variables, e.g., r11 -> map_fail_paddr.
Changes in v3:
Changed max_retry_cnt from 1000 to 3.
Changes in v4:
__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT) -> __tdx_hypercall_ret() Added Kirill's Acked-by.
Changes in v5:
Added Michael's Reviewed-by.
Changes in v6: None.
Changes in v7:
Addressed Dave's comments:
see https://lwn.net/ml/linux-kernel/SA1PR21MB1335736123C2BCBBFD7460C3BF46A@SA1PR21MB1335.namprd21.prod.outlook.com
Changes in v8:
Rebased to tip.git's master branch.
Changes in v9:
Added a comment before 'max_retries_per_page'. Moved 'args', 'map_fail_paddr' and 'ret' into the loop. Added Kuppuswamy Sathyanarayanan's Reviewed-by.
arch/x86/coco/tdx/tdx.c +52 -12
@@ -703,14 +703,15 @@ static bool tdx_cache_flush_required(void) }/* -* Inform the VMM of the guest's intent for this physical page: shared with -* the VMM or private to the guest. The VMM is expected to change its mapping -* of the page in response. +* Notify the VMM about page mapping conversion. More info about ABI +* can be found in TDX Guest-Host-Communication Interface (GHCI), +* section "TDG.VP.VMCALL<MapGPA>". */ -static bool tdx_enc_status_changed (unsigned long vaddr,int numpages,bool enc) +static bool tdx_map_gpa (phys_addr_t start,phys_addr_t end,bool enc) { -phys_addr_t start =__pa (vaddr); -phys_addr_t end =__pa (vaddr + numpages *PAGE_SIZE ); +/* Retrying the hypercall a second time should succeed; use 3 just in case */ +const int max_retries_per_page =3 ; +int retry_count =0 ;if (!enc) {/* Set the shared (decrypted) bits: */
@@ -718,12 +719,51 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc) end |=cc_mkdec (0 ); } -/* -* Notify the VMM about page mapping conversion. More info about ABI -* can be found in TDX Guest-Host-Communication Interface (GHCI), -* section "TDG.VP.VMCALL<MapGPA>" -*/ -if (_tdx_hypercall (TDVMCALL_MAP_GPA , start, end - start,0 ,0 )) +while (retry_count < max_retries_per_page) { +struct tdx_hypercall_args args = { + .r10 =TDX_HYPERCALL_STANDARD , + .r11 =TDVMCALL_MAP_GPA , + .r12 = start, + .r13 = end - start }; + +u64 map_fail_paddr; +u64 ret =__tdx_hypercall_ret (&args); + +if (ret !=TDVMCALL_STATUS_RETRY ) +return !ret; +/* +* The guest must retry the operation for the pages in the +* region starting at the GPA specified in R11. R11 comes +* from the untrusted VMM. Sanity check it. +*/ + map_fail_paddr = args.r11; +if (map_fail_paddr < start || map_fail_paddr >= end) +return false; + +/* "Consume" a retry without forward progress */ +if (map_fail_paddr == start) { + retry_count++; +continue ; + } + + start = map_fail_paddr; + retry_count =0 ; + } + +return false; +} + +/* +* Inform the VMM of the guest's intent for this physical page: shared with +* the VMM or private to the guest. The VMM is expected to change its mapping +* of the page in response. +*/ +static bool tdx_enc_status_changed (unsigned long vaddr,int numpages,bool enc) +{ +phys_addr_t start =__pa (vaddr); +phys_addr_t end =__pa (vaddr + numpages *PAGE_SIZE ); + +if (!tdx_map_gpa (start, end, enc))return false;/* shared->private conversion requires memory to be accepted before use */
arch/x86/include/asm/shared/tdx.h +2 -0
@@ -24,6 +24,8 @@#define TDVMCALL_MAP_GPA 0x10001#define TDVMCALL_REPORT_FATAL_ERROR 0x10003 +#define TDVMCALL_STATUS_RETRY 1 +#ifndef __ASSEMBLY__/*
Signature · 1 line
2.25.1
Dexuan Cui
maintainerPATCH v9 2/2 x86/tdx: Support vmalloc() for tdx_enc_status_changed()
In reply to Dexuan CuiWhen a TDX guest runs on Hyper-V, the hv_netvsc driver's netvsc_init_buf() allocates buffers using vzalloc(), and needs to share the buffers with the host OS by calling set_memory_decrypted(), which is not working for vmalloc() yet. Add the support by handling the pages one by one.
--- arch/x86/coco/tdx/tdx.c | 35 +++++++++++++++++++++++++++++------ 1 file changed, 29 insertions(+), 6 deletions(-)
Changes in v2:
Changed tdx_enc_status_changed() in place.
Changes in v3:
No change since v2.
Changes in v4:
Added Kirill's Co-developed-by since Kirill helped to improve the
code by adding tdx_enc_status_changed_phys().
Thanks Kirill for the clarification on load_unaligned_zeropad()!
Changes in v5:
Added Kirill's Signed-off-by.
Added Michael's Reviewed-by.
Changes in v6: None.
Changes in v7: None.
Note: there was a race between set_memory_encrypted() and load_unaligned_zeropad(), which has been fixed by the 3 patches of Kirill in the x86/tdx branch of the tip tree.
Changes in v8:
Rebased to tip.git's master branch.
Changes in v9:
Added Kuppuswamy Sathyanarayanan's Reviewed-by.
arch/x86/coco/tdx/tdx.c +29 -6
@@ -7,6 +7,7 @@#include <linux/cpufeature.h> #include <linux/export.h> #include <linux/io.h> +#include <linux/mm.h> #include <asm/coco.h> #include <asm/tdx.h> #include <asm/vmx.h>
@@ -753,6 +754,19 @@ static bool tdx_map_gpa(phys_addr_t start, phys_addr_t end, bool enc)return false; } +static bool tdx_enc_status_changed_phys (phys_addr_t start,phys_addr_t end, +bool enc) +{ +if (!tdx_map_gpa (start, end, enc)) +return false; + +/* shared->private conversion requires memory to be accepted before use */ +if (enc) +return tdx_accept_memory (start, end); + +return true; +} +/* * Inform the VMM of the guest's intent for this physical page: shared with * the VMM or private to the guest. The VMM is expected to change its mapping
@@ -760,15 +774,24 @@ static bool tdx_map_gpa(phys_addr_t start, phys_addr_t end, bool enc)*/ static bool tdx_enc_status_changed (unsigned long vaddr,int numpages,bool enc) { -phys_addr_t start =__pa (vaddr); -phys_addr_t end =__pa (vaddr + numpages *PAGE_SIZE ); +unsigned long start = vaddr; +unsigned long end = start + numpages *PAGE_SIZE ; -if (!tdx_map_gpa (start, end, enc)) +if (offset_in_page (start) !=0 )return false; -/* shared->private conversion requires memory to be accepted before use */ -if (enc) -return tdx_accept_memory (start, end); +if (!is_vmalloc_addr ((void *)start)) +return tdx_enc_status_changed_phys (__pa (start),__pa (end), enc); + +while (start < end) { +phys_addr_t start_pa =slow_virt_to_phys ((void *)start); +phys_addr_t end_pa = start_pa +PAGE_SIZE ; + +if (!tdx_enc_status_changed_phys (start_pa, end_pa, enc)) +return false; + + start +=PAGE_SIZE ; + }return true; }
Signature · 1 line
2.25.1
Wei Liu
maintainerQuoted 15 lines · Dexuan Cui
The two patches are based on today's tip.git's master branch.
Note: the two patches don't apply to the current x86/tdx branch, which doesn't have commit
75d090fd167a("x86/tdx: Add unaccepted memory support").As Dave suggested, I moved some local variables of
tdx_map_gpa()to inside the loop. I added Sathyanarayanan's Reviewed-by.Please review.
FWIW, the old versons are here:
v8: https://lwn.net/ml/linux-kernel/[email protected]/
v7: https://lwn.net/ml/linux-kernel/20230616044701.15888-1-decui%40microsoft.com/
v6: https://lwn.net/ml/linux-kernel/[email protected]/
Quoted 7 lines
Dexuan Cui (2):
x86/tdx: RetryTDVMCALL_MAP_GPA()when needed x86/tdx: Supportvmalloc()fortdx_enc_status_changed()arch/x86/coco/tdx/tdx.c | 87 ++++++++++++++++++++++++++----- arch/x86/include/asm/shared/tdx.h | 2 + 2 files changed, 77 insertions(+), 12 deletions(-)
Dexuan, do you expect these to go through the Hyper-V tree?
Thanks,
Wei.
Quoted 4 lines
Signature · 2 lines
-- 2.25.1
Dexuan Cui
maintainerQuoted 23 lines
From: Wei Liu <[email protected]>
Sent: Wednesday, June 28, 2023 11:06 AM
To: Dexuan Cui <[email protected]>
Subject: Re: [PATCH v9 0/2] Support TDX guests on Hyper-V (the x86/tdx part)Quoted 4 lines · Dexuan Cui
The two patches are based on today's tip.git's master branch.
Note: the two patches don't apply to the current x86/tdx branch, which doesn't have commit
75d090fd167a("x86/tdx: Add unaccepted memorysupport").
Quoted 11 lines
As Dave suggested, I moved some local variables of
tdx_map_gpa()to inside the loop. I added Sathyanarayanan's Reviewed-by.Please review.
...
Dexuan Cui (2):
x86/tdx: RetryTDVMCALL_MAP_GPA()when needed x86/tdx: Supportvmalloc()fortdx_enc_status_changed()arch/x86/coco/tdx/tdx.c | 87
Quoted 8 lines
++++++++++++++++++++++++++-----
Quoted 2 lines
arch/x86/include/asm/shared/tdx.h | 2 + 2 files changed, 77 insertions(+), 12 deletions(-)Dexuan, do you expect these to go through the Hyper-V tree?
Thanks,
Wei.
I suppose Dave and/or other x86 folks would like the 2 patches to go through the tip tree if the patches look good.
Hi Dave, any comments on the patches?
Thanks,
Dexuan
Dexuan Cui
maintainerQuoted 28 lines
From: Dexuan Cui <[email protected]>
Sent: Wednesday, June 28, 2023 11:45 AM
To: Wei Liu <[email protected]>
...Quoted 24 lines
From: Wei Liu <[email protected]>
Sent: Wednesday, June 28, 2023 11:06 AM
To: Dexuan Cui <[email protected]>
Subject: Re: [PATCH v9 0/2] Support TDX guests on Hyper-V (the x86/tdx part)Quoted 4 lines · Dexuan Cui
The two patches are based on today's tip.git's master branch.
Note: the two patches don't apply to the current x86/tdx branch, which doesn't have commit
75d090fd167a("x86/tdx: Add unaccepted memorysupport").
Quoted 9 lines
As Dave suggested, I moved some local variables of
tdx_map_gpa()to inside the loop. I added Sathyanarayanan's Reviewed-by.Please review.
...
Dexuan Cui (2):
x86/tdx: RetryTDVMCALL_MAP_GPA()when needed x86/tdx: Supportvmalloc()fortdx_enc_status_changed()...
Dexuan, do you expect these to go through the Hyper-V tree?
Quoted 7 lines
Quoted 2 lines
Thanks,
Wei.I suppose Dave and/or other x86 folks would like the 2 patches to go through the tip tree if the patches look good.
Hi Dave, any comments on the patches?
Hi Dave, would you please take a look at the 2 patches?
The patches have got Reviewed-by/Acked-by from Kirill, Sathyanarayanan and Michael.
The patches can still apply cleanly on today's tip tree's master branch.
Thanks,
Dexuan
Re: [PATCH v9 1/2] x86/tdx: Retry TDVMCALL_MAP_GPA() when needed
In reply to Dexuan CuiQuoted 8 lines · Dexuan Cui
GHCI spec for TDX 1.0 says that the MapGPA call may fail with the R10 error code = TDG.VP.VMCALL_RETRY (1), and the guest must retry this operation for the pages in the region starting at the GPA specified in R11.
When a fully enlightened TDX guest runs on Hyper-V, Hyper-V can return the retry error when
set_memory_decrypted()is called to decrypt up to 1GB of swiotlb bounce buffers.
just out of curiosity, what size does Hyper-v handle at most in one call?
Dexuan Cui
maintainerRE: [PATCH v9 1/2] x86/tdx: Retry TDVMCALL_MAP_GPA() when needed
Quoted 9 lines
From: Xiaoyao Li <[email protected]>
Sent: Tuesday, July 18, 2023 7:31 PM
...Quoted 5 lines · Dexuan Cui
GHCI spec for TDX 1.0 says that the MapGPA call may fail with the R10 error code = TDG.VP.VMCALL_RETRY (1), and the guest must retry this operation for the pages in the region starting at the GPA specified in R11.
Quoted 5 lines
Quoted 3 lines
When a fully enlightened TDX guest runs on Hyper-V, Hyper-V can return the retry error when
set_memory_decrypted()is called to decrypt up to 1GB of swiotlb bounce buffers.just out of curiosity, what size does Hyper-v handle at most in one call?
In my test, Hyper-V can process 1 to 9 pages in one call. Most of the time, Hyper-V only processes 2 pages or 1 page, in one call.
Thanks,
Dexuan
Dexuan Cui
maintainerQuoted 53 lines
From: Dexuan Cui
Sent: Monday, July 10, 2023 10:21 AM
To: Dexuan Cui <[email protected]>; Wei Liu <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]
Cc: [email protected]; [email protected]; [email protected]; [email protected]; Haiyang Zhang <[email protected]>; [email protected]; [email protected]; KY Srinivasan <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Michael Kelley (LINUX) <[email protected]>; [email protected]; Tianyu Lan <[email protected]>; [email protected]
Subject: RE: [PATCH v9 0/2] Support TDX guests on Hyper-V (the x86/tdx part)Quoted 15 lines
From: Dexuan Cui <[email protected]>
Sent: Wednesday, June 28, 2023 11:45 AM
To: Wei Liu <[email protected]>
...Quoted 11 lines
From: Wei Liu <[email protected]>
Sent: Wednesday, June 28, 2023 11:06 AM
To: Dexuan Cui <[email protected]>
Subject: Re: [PATCH v9 0/2] Support TDX guests on Hyper-V (the x86/tdx part)Quoted 4 lines · Dexuan Cui
The two patches are based on today's tip.git's master branch.
Note: the two patches don't apply to the current x86/tdx branch, which doesn't have commit
75d090fd167a("x86/tdx: Add unacceptedmemory
Quoted 13 lines
Quoted 13 lines
support").
Quoted 9 lines
As Dave suggested, I moved some local variables of
tdx_map_gpa()to inside the loop. I added Sathyanarayanan's Reviewed-by.Please review.
...
Dexuan Cui (2):
x86/tdx: RetryTDVMCALL_MAP_GPA()when needed x86/tdx: Supportvmalloc()fortdx_enc_status_changed()...
Dexuan, do you expect these to go through the Hyper-V tree?Quoted 7 lines
Quoted 2 lines
Thanks,
Wei.I suppose Dave and/or other x86 folks would like the 2 patches to go through the tip tree if the patches look good.
Hi Dave, any comments on the patches?
Quoted 8 lines
Hi Dave, would you please take a look at the 2 patches?
The patches have got Reviewed-by/Acked-by from Kirill, Sathyanarayanan and Michael.
The patches can still apply cleanly on today's tip tree's master branch.Thanks,
Dexuan
Hi Dave, kindly ping.