From: Ard Biesheuvel ardb@kernel.org
Communicating with the hypervisor using the shared GHCB page requires clearing the C bit in the mapping of that page. When executing in the context of the EFI boot services, the page tables are owned by the firmware, and this manipulation is not possible.
So switch to a different API for accepting memory in SEV-SNP guests, one which is actually supported at the point during boot where the EFI stub may need to accept memory, but the SEV-SNP init code has not executed yet.
For simplicity, also switch the memory acceptance carried out by the decompressor when not booting via EFI - this only involves the allocation for the decompressed kernel, and is generally only called after kexec, as normal boot will jump straight into the kernel from the EFI stub.
Cc: Tom Lendacky thomas.lendacky@amd.com Cc: "Kirill A. Shutemov" kirill.shutemov@linux.intel.com Cc: Borislav Petkov bp@alien8.de Cc: Dionna Amalie Glaze dionnaglaze@google.com Cc: Kevin Loughlin kevinloughlin@google.com Cc: stable@vger.kernel.org Fixes: 6c3211796326 ("x86/sev: Add SNP-specific unaccepted memory support") Co-developed-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Ard Biesheuvel ardb@kernel.org --- Changes since v3 [0]: - work around the fact that sev_snp_enabled() does not work yet when the EFI stub accepts misaligned chunks of memory while populating the E820 table
Changes since v2 [1]: - avoid two separate acceptance APIs; instead, use MSR based page-by-page acceptance for the decompressor as well
[0] https://lore.kernel.org/all/20250410132850.3708703-2-ardb+git@google.com/T/#... [1] https://lore.kernel.org/all/20250404082921.2767593-8-ardb+git@google.com/T/#...
arch/x86/boot/compressed/mem.c | 5 +- arch/x86/boot/compressed/sev.c | 67 +++++--------------- arch/x86/boot/compressed/sev.h | 2 + 3 files changed, 21 insertions(+), 53 deletions(-)
diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c index dbba332e4a12..f676156d9f3d 100644 --- a/arch/x86/boot/compressed/mem.c +++ b/arch/x86/boot/compressed/mem.c @@ -34,11 +34,14 @@ static bool early_is_tdx_guest(void)
void arch_accept_memory(phys_addr_t start, phys_addr_t end) { + static bool sevsnp; + /* Platform-specific memory-acceptance call goes here */ if (early_is_tdx_guest()) { if (!tdx_accept_memory(start, end)) panic("TDX: Failed to accept memory\n"); - } else if (sev_snp_enabled()) { + } else if (sevsnp || (sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED)) { + sevsnp = true; snp_accept_memory(start, end); } else { error("Cannot accept memory: unknown platform\n"); diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 6eadd790f4e5..478eca4f7180 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -169,10 +169,7 @@ bool sev_snp_enabled(void)
static void __page_state_change(unsigned long paddr, enum psc_op op) { - u64 val; - - if (!sev_snp_enabled()) - return; + u64 val, msr;
/* * If private -> shared then invalidate the page before requesting the @@ -181,6 +178,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op) if (op == SNP_PAGE_STATE_SHARED) pvalidate_4k_page(paddr, paddr, false);
+ /* Save the current GHCB MSR value */ + msr = sev_es_rd_ghcb_msr(); + /* Issue VMGEXIT to change the page state in RMP table. */ sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); VMGEXIT(); @@ -190,6 +190,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op) if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val)) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+ /* Restore the GHCB MSR value */ + sev_es_wr_ghcb_msr(msr); + /* * Now that page state is changed in the RMP table, validate it so that it is * consistent with the RMP entry. @@ -200,11 +203,17 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
void snp_set_page_private(unsigned long paddr) { + if (!sev_snp_enabled()) + return; + __page_state_change(paddr, SNP_PAGE_STATE_PRIVATE); }
void snp_set_page_shared(unsigned long paddr) { + if (!sev_snp_enabled()) + return; + __page_state_change(paddr, SNP_PAGE_STATE_SHARED); }
@@ -228,56 +237,10 @@ static bool early_setup_ghcb(void) return true; }
-static phys_addr_t __snp_accept_memory(struct snp_psc_desc *desc, - phys_addr_t pa, phys_addr_t pa_end) -{ - struct psc_hdr *hdr; - struct psc_entry *e; - unsigned int i; - - hdr = &desc->hdr; - memset(hdr, 0, sizeof(*hdr)); - - e = desc->entries; - - i = 0; - while (pa < pa_end && i < VMGEXIT_PSC_MAX_ENTRY) { - hdr->end_entry = i; - - e->gfn = pa >> PAGE_SHIFT; - e->operation = SNP_PAGE_STATE_PRIVATE; - if (IS_ALIGNED(pa, PMD_SIZE) && (pa_end - pa) >= PMD_SIZE) { - e->pagesize = RMP_PG_SIZE_2M; - pa += PMD_SIZE; - } else { - e->pagesize = RMP_PG_SIZE_4K; - pa += PAGE_SIZE; - } - - e++; - i++; - } - - if (vmgexit_psc(boot_ghcb, desc)) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); - - pvalidate_pages(desc); - - return pa; -} - void snp_accept_memory(phys_addr_t start, phys_addr_t end) { - struct snp_psc_desc desc = {}; - unsigned int i; - phys_addr_t pa; - - if (!boot_ghcb && !early_setup_ghcb()) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); - - pa = start; - while (pa < end) - pa = __snp_accept_memory(&desc, pa, end); + for (phys_addr_t pa = start; pa < end; pa += PAGE_SIZE) + __page_state_change(pa, SNP_PAGE_STATE_PRIVATE); }
void sev_es_shutdown_ghcb(void) diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h index fc725a981b09..4e463f33186d 100644 --- a/arch/x86/boot/compressed/sev.h +++ b/arch/x86/boot/compressed/sev.h @@ -12,11 +12,13 @@
bool sev_snp_enabled(void); void snp_accept_memory(phys_addr_t start, phys_addr_t end); +u64 sev_get_status(void);
#else
static inline bool sev_snp_enabled(void) { return false; } static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } +static inline u64 sev_get_status(void) { return 0; }
#endif