From 60b8f711143de7cd9c0f55be0fe7eb94b19eb5c7 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 13 Feb 2025 13:41:32 -0500 Subject: [PATCH 01/16] tracing: Have the error of __tracing_resize_ring_buffer() passed to user Currently if __tracing_resize_ring_buffer() returns an error, the tracing_resize_ringbuffer() returns -ENOMEM. But it may not be a memory issue that caused the function to fail. If the ring buffer is memory mapped, then the resizing of the ring buffer will be disabled. But if the user tries to resize the buffer, it will get an -ENOMEM returned, which is confusing because there is plenty of memory. The actual error returned was -EBUSY, which would make much more sense to the user. Cc: stable@vger.kernel.org Cc: Mathieu Desnoyers Cc: Vincent Donnefort Link: https://lore.kernel.org/20250213134132.7e4505d7@gandalf.local.home Fixes: 117c39200d9d7 ("ring-buffer: Introducing ring-buffer mapping functions") Signed-off-by: Steven Rostedt (Google) Reviewed-by: Masami Hiramatsu (Google) --- kernel/trace/trace.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1496a5ac33ae..25ff37aab00f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5977,8 +5977,6 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, ssize_t tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu_id) { - int ret; - guard(mutex)(&trace_types_lock); if (cpu_id != RING_BUFFER_ALL_CPUS) { @@ -5987,11 +5985,7 @@ ssize_t tracing_resize_ring_buffer(struct trace_array *tr, return -EINVAL; } - ret = __tracing_resize_ring_buffer(tr, size, cpu_id); - if (ret < 0) - ret = -ENOMEM; - - return ret; + return __tracing_resize_ring_buffer(tr, size, cpu_id); } static void update_last_data(struct trace_array *tr) -- 2.50.1 From f5b95f1fa2ef3a03f49eeec658ba97e721412b32 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 14 Feb 2025 10:28:20 -0500 Subject: [PATCH 02/16] ring-buffer: Validate the persistent meta data subbuf array The meta data for a mapped ring buffer contains an array of indexes of all the subbuffers. The first entry is the reader page, and the rest of the entries lay out the order of the subbuffers in how the ring buffer link list is to be created. The validator currently makes sure that all the entries are within the range of 0 and nr_subbufs. But it does not check if there are any duplicates. While working on the ring buffer, I corrupted this array, where I added duplicates. The validator did not catch it and created the ring buffer link list on top of it. Luckily, the corruption was only that the reader page was also in the writer path and only presented corrupted data but did not crash the kernel. But if there were duplicates in the writer side, then it could corrupt the ring buffer link list and cause a crash. Create a bitmask array with the size of the number of subbuffers. Then clear it. When walking through the subbuf array checking to see if the entries are within the range, test if its bit is already set in the subbuf_mask. If it is, then there is duplicates and fail the validation. If not, set the corresponding bit and continue. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Vincent Donnefort Link: https://lore.kernel.org/20250214102820.7509ddea@gandalf.local.home Fixes: c76883f18e59b ("ring-buffer: Add test if range of boot buffer is valid") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 07b421115692..0419d41a2060 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1672,7 +1672,8 @@ static void *rb_range_buffer(struct ring_buffer_per_cpu *cpu_buffer, int idx) * must be the same. */ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, - struct trace_buffer *buffer, int nr_pages) + struct trace_buffer *buffer, int nr_pages, + unsigned long *subbuf_mask) { int subbuf_size = PAGE_SIZE; struct buffer_data_page *subbuf; @@ -1680,6 +1681,9 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, unsigned long buffers_end; int i; + if (!subbuf_mask) + return false; + /* Check the meta magic and meta struct size */ if (meta->magic != RING_BUFFER_META_MAGIC || meta->struct_size != sizeof(*meta)) { @@ -1712,6 +1716,8 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, subbuf = rb_subbufs_from_meta(meta); + bitmap_clear(subbuf_mask, 0, meta->nr_subbufs); + /* Is the meta buffers and the subbufs themselves have correct data? */ for (i = 0; i < meta->nr_subbufs; i++) { if (meta->buffers[i] < 0 || @@ -1725,6 +1731,12 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, return false; } + if (test_bit(meta->buffers[i], subbuf_mask)) { + pr_info("Ring buffer boot meta [%d] array has duplicates\n", cpu); + return false; + } + + set_bit(meta->buffers[i], subbuf_mask); subbuf = (void *)subbuf + subbuf_size; } @@ -1889,17 +1901,22 @@ static void rb_meta_init_text_addr(struct ring_buffer_meta *meta) static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages) { struct ring_buffer_meta *meta; + unsigned long *subbuf_mask; unsigned long delta; void *subbuf; int cpu; int i; + /* Create a mask to test the subbuf array */ + subbuf_mask = bitmap_alloc(nr_pages + 1, GFP_KERNEL); + /* If subbuf_mask fails to allocate, then rb_meta_valid() will return false */ + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { void *next_meta; meta = rb_range_meta(buffer, nr_pages, cpu); - if (rb_meta_valid(meta, cpu, buffer, nr_pages)) { + if (rb_meta_valid(meta, cpu, buffer, nr_pages, subbuf_mask)) { /* Make the mappings match the current address */ subbuf = rb_subbufs_from_meta(meta); delta = (unsigned long)subbuf - meta->first_buffer; @@ -1943,6 +1960,7 @@ static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages) subbuf += meta->subbuf_size; } } + bitmap_free(subbuf_mask); } static void *rbm_start(struct seq_file *m, loff_t *pos) -- 2.50.1 From 77b823fa619f97d16409ca37ad4f7936e28c5f83 Mon Sep 17 00:00:00 2001 From: Ivan Kokshaysky Date: Tue, 4 Feb 2025 23:35:22 +0100 Subject: [PATCH 03/16] alpha: replace hardcoded stack offsets with autogenerated ones This allows the assembly in entry.S to automatically keep in sync with changes in the stack layout (struct pt_regs and struct switch_stack). Cc: stable@vger.kernel.org Tested-by: Maciej W. Rozycki Tested-by: Matt Turner Reviewed-by: Maciej W. Rozycki Signed-off-by: Ivan Kokshaysky Signed-off-by: Matt Turner --- arch/alpha/kernel/asm-offsets.c | 4 ++++ arch/alpha/kernel/entry.S | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/alpha/kernel/asm-offsets.c b/arch/alpha/kernel/asm-offsets.c index 4cfeae42c79a..e9dad60b147f 100644 --- a/arch/alpha/kernel/asm-offsets.c +++ b/arch/alpha/kernel/asm-offsets.c @@ -19,9 +19,13 @@ static void __used foo(void) DEFINE(TI_STATUS, offsetof(struct thread_info, status)); BLANK(); + DEFINE(SP_OFF, offsetof(struct pt_regs, ps)); DEFINE(SIZEOF_PT_REGS, sizeof(struct pt_regs)); BLANK(); + DEFINE(SWITCH_STACK_SIZE, sizeof(struct switch_stack)); + BLANK(); + DEFINE(HAE_CACHE, offsetof(struct alpha_machine_vector, hae_cache)); DEFINE(HAE_REG, offsetof(struct alpha_machine_vector, hae_register)); } diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index dd26062d75b3..6fb38365539d 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -15,10 +15,6 @@ .set noat .cfi_sections .debug_frame -/* Stack offsets. */ -#define SP_OFF 184 -#define SWITCH_STACK_SIZE 64 - .macro CFI_START_OSF_FRAME func .align 4 .globl \func -- 2.50.1 From 0a0f7362b0367634a2d5cb7c96226afc116f19c9 Mon Sep 17 00:00:00 2001 From: Ivan Kokshaysky Date: Tue, 4 Feb 2025 23:35:23 +0100 Subject: [PATCH 04/16] alpha: make stack 16-byte aligned (most cases) The problem is that GCC expects 16-byte alignment of the incoming stack since early 2004, as Maciej found out [1]: Having actually dug speculatively I can see that the psABI was changed in GCC 3.5 with commit e5e10fb4a350 ("re PR target/14539 (128-bit long double improperly aligned)") back in Mar 2004, when the stack pointer alignment was increased from 8 bytes to 16 bytes, and arch/alpha/kernel/entry.S has various suspicious stack pointer adjustments, starting with SP_OFF which is not a whole multiple of 16. Also, as Magnus noted, "ALPHA Calling Standard" [2] required the same: D.3.1 Stack Alignment This standard requires that stacks be octaword aligned at the time a new procedure is invoked. However: - the "normal" kernel stack is always misaligned by 8 bytes, thanks to the odd number of 64-bit words in 'struct pt_regs', which is the very first thing pushed onto the kernel thread stack; - syscall, fault, interrupt etc. handlers may, or may not, receive aligned stack depending on numerous factors. Somehow we got away with it until recently, when we ended up with a stack corruption in kernel/smp.c:smp_call_function_single() due to its use of 32-byte aligned local data and the compiler doing clever things allocating it on the stack. This adds padding between the PAL-saved and kernel-saved registers so that 'struct pt_regs' have an even number of 64-bit words. This makes the stack properly aligned for most of the kernel code, except two handlers which need special threatment. Note: struct pt_regs doesn't belong in uapi/asm; this should be fixed, but let's put this off until later. Link: https://lore.kernel.org/rcu/alpine.DEB.2.21.2501130248010.18889@angie.orcam.me.uk/ [1] Link: https://bitsavers.org/pdf/dec/alpha/Alpha_Calling_Standard_Rev_2.0_19900427.pdf [2] Cc: stable@vger.kernel.org Tested-by: Maciej W. Rozycki Tested-by: Magnus Lindholm Tested-by: Matt Turner Reviewed-by: Maciej W. Rozycki Signed-off-by: Ivan Kokshaysky Signed-off-by: Matt Turner --- arch/alpha/include/uapi/asm/ptrace.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/alpha/include/uapi/asm/ptrace.h b/arch/alpha/include/uapi/asm/ptrace.h index 5ca45934fcbb..72ed913a910f 100644 --- a/arch/alpha/include/uapi/asm/ptrace.h +++ b/arch/alpha/include/uapi/asm/ptrace.h @@ -42,6 +42,8 @@ struct pt_regs { unsigned long trap_a0; unsigned long trap_a1; unsigned long trap_a2; +/* This makes the stack 16-byte aligned as GCC expects */ + unsigned long __pad0; /* These are saved by PAL-code: */ unsigned long ps; unsigned long pc; -- 2.50.1 From 3b35a171060f846b08b48646b38c30b5d57d17ff Mon Sep 17 00:00:00 2001 From: Ivan Kokshaysky Date: Tue, 4 Feb 2025 23:35:24 +0100 Subject: [PATCH 05/16] alpha: align stack for page fault and user unaligned trap handlers do_page_fault() and do_entUna() are special because they use non-standard stack frame layout. Fix them manually. Cc: stable@vger.kernel.org Tested-by: Maciej W. Rozycki Tested-by: Magnus Lindholm Tested-by: Matt Turner Reviewed-by: Maciej W. Rozycki Suggested-by: Maciej W. Rozycki Signed-off-by: Ivan Kokshaysky Signed-off-by: Matt Turner --- arch/alpha/kernel/entry.S | 20 ++++++++++---------- arch/alpha/kernel/traps.c | 2 +- arch/alpha/mm/fault.c | 4 ++-- 3 files changed, 13 insertions(+), 13 deletions(-) diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index 6fb38365539d..f4d41b4538c2 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -194,8 +194,8 @@ CFI_END_OSF_FRAME entArith CFI_START_OSF_FRAME entMM SAVE_ALL /* save $9 - $15 so the inline exception code can manipulate them. */ - subq $sp, 56, $sp - .cfi_adjust_cfa_offset 56 + subq $sp, 64, $sp + .cfi_adjust_cfa_offset 64 stq $9, 0($sp) stq $10, 8($sp) stq $11, 16($sp) @@ -210,7 +210,7 @@ CFI_START_OSF_FRAME entMM .cfi_rel_offset $13, 32 .cfi_rel_offset $14, 40 .cfi_rel_offset $15, 48 - addq $sp, 56, $19 + addq $sp, 64, $19 /* handle the fault */ lda $8, 0x3fff bic $sp, $8, $8 @@ -223,7 +223,7 @@ CFI_START_OSF_FRAME entMM ldq $13, 32($sp) ldq $14, 40($sp) ldq $15, 48($sp) - addq $sp, 56, $sp + addq $sp, 64, $sp .cfi_restore $9 .cfi_restore $10 .cfi_restore $11 @@ -231,7 +231,7 @@ CFI_START_OSF_FRAME entMM .cfi_restore $13 .cfi_restore $14 .cfi_restore $15 - .cfi_adjust_cfa_offset -56 + .cfi_adjust_cfa_offset -64 /* finish up the syscall as normal. */ br ret_from_sys_call CFI_END_OSF_FRAME entMM @@ -378,8 +378,8 @@ entUnaUser: .cfi_restore $0 .cfi_adjust_cfa_offset -256 SAVE_ALL /* setup normal kernel stack */ - lda $sp, -56($sp) - .cfi_adjust_cfa_offset 56 + lda $sp, -64($sp) + .cfi_adjust_cfa_offset 64 stq $9, 0($sp) stq $10, 8($sp) stq $11, 16($sp) @@ -395,7 +395,7 @@ entUnaUser: .cfi_rel_offset $14, 40 .cfi_rel_offset $15, 48 lda $8, 0x3fff - addq $sp, 56, $19 + addq $sp, 64, $19 bic $sp, $8, $8 jsr $26, do_entUnaUser ldq $9, 0($sp) @@ -405,7 +405,7 @@ entUnaUser: ldq $13, 32($sp) ldq $14, 40($sp) ldq $15, 48($sp) - lda $sp, 56($sp) + lda $sp, 64($sp) .cfi_restore $9 .cfi_restore $10 .cfi_restore $11 @@ -413,7 +413,7 @@ entUnaUser: .cfi_restore $13 .cfi_restore $14 .cfi_restore $15 - .cfi_adjust_cfa_offset -56 + .cfi_adjust_cfa_offset -64 br ret_from_sys_call CFI_END_OSF_FRAME entUna diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index a9a38c80c4a7..7004397937cf 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -649,7 +649,7 @@ s_reg_to_mem (unsigned long s_reg) static int unauser_reg_offsets[32] = { R(r0), R(r1), R(r2), R(r3), R(r4), R(r5), R(r6), R(r7), R(r8), /* r9 ... r15 are stored in front of regs. */ - -56, -48, -40, -32, -24, -16, -8, + -64, -56, -48, -40, -32, -24, -16, /* padding at -8 */ R(r16), R(r17), R(r18), R(r19), R(r20), R(r21), R(r22), R(r23), R(r24), R(r25), R(r26), R(r27), R(r28), R(gp), diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 8c9850437e67..a9816bbc9f34 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -78,8 +78,8 @@ __load_new_mm_context(struct mm_struct *next_mm) /* Macro for exception fixup code to access integer registers. */ #define dpf_reg(r) \ - (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \ - (r) <= 18 ? (r)+10 : (r)-10]) + (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-17 : \ + (r) <= 18 ? (r)+11 : (r)-10]) asmlinkage void do_page_fault(unsigned long address, unsigned long mmcsr, -- 2.50.1 From 757f051a506198186d796dff4ba696adb7bda54c Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Tue, 7 Jan 2025 11:43:42 +0100 Subject: [PATCH 06/16] alpha: Replace one-element array with flexible array member Replace the deprecated one-element array with a modern flexible array member in the struct crb_struct. Reviewed-by: Kees Cook Signed-off-by: Thorsten Blum Signed-off-by: Matt Turner --- arch/alpha/include/asm/hwrpb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/include/asm/hwrpb.h b/arch/alpha/include/asm/hwrpb.h index fc76f36265ad..db831cf8de10 100644 --- a/arch/alpha/include/asm/hwrpb.h +++ b/arch/alpha/include/asm/hwrpb.h @@ -135,7 +135,7 @@ struct crb_struct { /* virtual->physical map */ unsigned long map_entries; unsigned long map_pages; - struct vf_map_struct map[1]; + struct vf_map_struct map[]; }; struct memclust_struct { -- 2.50.1 From 1523226edda566057bdd3264ceb56631ddf5f6f7 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Wed, 12 Feb 2025 12:14:47 +0100 Subject: [PATCH 07/16] alpha: Use str_yes_no() helper in pci_dac_dma_supported() Remove hard-coded strings by using the str_yes_no() helper function. Reviewed-by: Geert Uytterhoeven Signed-off-by: Thorsten Blum Signed-off-by: Matt Turner --- arch/alpha/kernel/pci_iommu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 681f56089d9c..dc91de50f906 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -212,7 +213,7 @@ static int pci_dac_dma_supported(struct pci_dev *dev, u64 mask) /* If both conditions above are met, we are fine. */ DBGA("pci_dac_dma_supported %s from %ps\n", - ok ? "yes" : "no", __builtin_return_address(0)); + str_yes_no(ok), __builtin_return_address(0)); return ok; } -- 2.50.1 From 435b344a7042e91fb4719d589f18310e8919e39f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 10 Feb 2025 22:53:47 +0000 Subject: [PATCH 08/16] crypto: ccp: Add external API interface for PSP module initialization KVM is dependent on the PSP SEV driver and PSP SEV driver needs to be loaded before KVM module. In case of module loading any dependent modules are automatically loaded but in case of built-in modules there is no inherent mechanism available to specify dependencies between modules and ensure that any dependent modules are loaded implicitly. Add a new external API interface for PSP module initialization which allows PSP SEV driver to be loaded explicitly if KVM is built-in. Signed-off-by: Sean Christopherson Co-developed-by: Ashish Kalra Signed-off-by: Ashish Kalra Reviewed-by: Tom Lendacky Message-ID: <15279ca0cad56a07cf12834ec544310f85ff5edc.1739226950.git.ashish.kalra@amd.com> Signed-off-by: Paolo Bonzini --- drivers/crypto/ccp/sp-dev.c | 14 ++++++++++++++ include/linux/psp-sev.h | 9 +++++++++ 2 files changed, 23 insertions(+) diff --git a/drivers/crypto/ccp/sp-dev.c b/drivers/crypto/ccp/sp-dev.c index 7eb3e4668286..3467f6db4f50 100644 --- a/drivers/crypto/ccp/sp-dev.c +++ b/drivers/crypto/ccp/sp-dev.c @@ -19,6 +19,7 @@ #include #include +#include "sev-dev.h" #include "ccp-dev.h" #include "sp-dev.h" @@ -253,8 +254,12 @@ unlock: static int __init sp_mod_init(void) { #ifdef CONFIG_X86 + static bool initialized; int ret; + if (initialized) + return 0; + ret = sp_pci_init(); if (ret) return ret; @@ -263,6 +268,8 @@ static int __init sp_mod_init(void) psp_pci_init(); #endif + initialized = true; + return 0; #endif @@ -279,6 +286,13 @@ static int __init sp_mod_init(void) return -ENODEV; } +#if IS_BUILTIN(CONFIG_KVM_AMD) && IS_ENABLED(CONFIG_KVM_AMD_SEV) +int __init sev_module_init(void) +{ + return sp_mod_init(); +} +#endif + static void __exit sp_mod_exit(void) { #ifdef CONFIG_X86 diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 903ddfea8585..f3cad182d4ef 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -814,6 +814,15 @@ struct sev_data_snp_commit { #ifdef CONFIG_CRYPTO_DEV_SP_PSP +/** + * sev_module_init - perform PSP SEV module initialization + * + * Returns: + * 0 if the PSP module is successfully initialized + * negative value if the PSP module initialization fails + */ +int sev_module_init(void); + /** * sev_platform_init - perform SEV INIT command * -- 2.50.1 From 44e70718df4fc2fadf1665eb9374df71aeda1f03 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 10 Feb 2025 22:54:02 +0000 Subject: [PATCH 09/16] KVM: SVM: Ensure PSP module is initialized if KVM module is built-in The kernel's initcall infrastructure lacks the ability to express dependencies between initcalls, whereas the modules infrastructure automatically handles dependencies via symbol loading. Ensure the PSP SEV driver is initialized before proceeding in sev_hardware_setup() if KVM is built-in as the dependency isn't handled by the initcall infrastructure. Signed-off-by: Sean Christopherson Reviewed-by: Tom Lendacky Signed-off-by: Ashish Kalra Message-ID: Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index a2a794c32050..0dbb25442ec1 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2972,6 +2972,16 @@ void __init sev_hardware_setup(void) WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID))) goto out; + /* + * The kernel's initcall infrastructure lacks the ability to express + * dependencies between initcalls, whereas the modules infrastructure + * automatically handles dependencies via symbol loading. Ensure the + * PSP SEV driver is initialized before proceeding if KVM is built-in, + * as the dependency isn't handled by the initcall infrastructure. + */ + if (IS_BUILTIN(CONFIG_KVM_AMD) && sev_module_init()) + goto out; + /* Retrieve SEV CPUID information */ cpuid(0x8000001f, &eax, &ebx, &ecx, &edx); -- 2.50.1 From 409f45387c937145adeeeebc6d6032c2ec232b35 Mon Sep 17 00:00:00 2001 From: Ashish Kalra Date: Mon, 10 Feb 2025 22:54:18 +0000 Subject: [PATCH 10/16] x86/sev: Fix broken SNP support with KVM module built-in Fix issues with enabling SNP host support and effectively SNP support which is broken with respect to the KVM module being built-in. SNP host support is enabled in snp_rmptable_init() which is invoked as device_initcall(). SNP check on IOMMU is done during IOMMU PCI init (IOMMU_PCI_INIT stage). And for that reason snp_rmptable_init() is currently invoked via device_initcall() and cannot be invoked via subsys_initcall() as core IOMMU subsystem gets initialized via subsys_initcall(). Now, if kvm_amd module is built-in, it gets initialized before SNP host support is enabled in snp_rmptable_init() : [ 10.131811] kvm_amd: TSC scaling supported [ 10.136384] kvm_amd: Nested Virtualization enabled [ 10.141734] kvm_amd: Nested Paging enabled [ 10.146304] kvm_amd: LBR virtualization supported [ 10.151557] kvm_amd: SEV enabled (ASIDs 100 - 509) [ 10.156905] kvm_amd: SEV-ES enabled (ASIDs 1 - 99) [ 10.162256] kvm_amd: SEV-SNP enabled (ASIDs 1 - 99) [ 10.171508] kvm_amd: Virtual VMLOAD VMSAVE supported [ 10.177052] kvm_amd: Virtual GIF supported ... ... [ 10.201648] kvm_amd: in svm_enable_virtualization_cpu And then svm_x86_ops->enable_virtualization_cpu() (svm_enable_virtualization_cpu) programs MSR_VM_HSAVE_PA as following: wrmsrl(MSR_VM_HSAVE_PA, sd->save_area_pa); So VM_HSAVE_PA is non-zero before SNP support is enabled on all CPUs. snp_rmptable_init() gets invoked after svm_enable_virtualization_cpu() as following : ... [ 11.256138] kvm_amd: in svm_enable_virtualization_cpu ... [ 11.264918] SEV-SNP: in snp_rmptable_init This triggers a #GP exception in snp_rmptable_init() when snp_enable() is invoked to set SNP_EN in SYSCFG MSR: [ 11.294289] unchecked MSR access error: WRMSR to 0xc0010010 (tried to write 0x0000000003fc0000) at rIP: 0xffffffffaf5d5c28 (native_write_msr+0x8/0x30) ... [ 11.294404] Call Trace: [ 11.294482] [ 11.294513] ? show_stack_regs+0x26/0x30 [ 11.294522] ? ex_handler_msr+0x10f/0x180 [ 11.294529] ? search_extable+0x2b/0x40 [ 11.294538] ? fixup_exception+0x2dd/0x340 [ 11.294542] ? exc_general_protection+0x14f/0x440 [ 11.294550] ? asm_exc_general_protection+0x2b/0x30 [ 11.294557] ? __pfx_snp_enable+0x10/0x10 [ 11.294567] ? native_write_msr+0x8/0x30 [ 11.294570] ? __snp_enable+0x5d/0x70 [ 11.294575] snp_enable+0x19/0x20 [ 11.294578] __flush_smp_call_function_queue+0x9c/0x3a0 [ 11.294586] generic_smp_call_function_single_interrupt+0x17/0x20 [ 11.294589] __sysvec_call_function+0x20/0x90 [ 11.294596] sysvec_call_function+0x80/0xb0 [ 11.294601] [ 11.294603] [ 11.294605] asm_sysvec_call_function+0x1f/0x30 ... [ 11.294631] arch_cpu_idle+0xd/0x20 [ 11.294633] default_idle_call+0x34/0xd0 [ 11.294636] do_idle+0x1f1/0x230 [ 11.294643] ? complete+0x71/0x80 [ 11.294649] cpu_startup_entry+0x30/0x40 [ 11.294652] start_secondary+0x12d/0x160 [ 11.294655] common_startup_64+0x13e/0x141 [ 11.294662] This #GP exception is getting triggered due to the following errata for AMD family 19h Models 10h-1Fh Processors: Processor may generate spurious #GP(0) Exception on WRMSR instruction: Description: The Processor will generate a spurious #GP(0) Exception on a WRMSR instruction if the following conditions are all met: - the target of the WRMSR is a SYSCFG register. - the write changes the value of SYSCFG.SNPEn from 0 to 1. - One of the threads that share the physical core has a non-zero value in the VM_HSAVE_PA MSR. The document being referred to above: https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/revision-guides/57095-PUB_1_01.pdf To summarize, with kvm_amd module being built-in, KVM/SVM initialization happens before host SNP is enabled and this SVM initialization sets VM_HSAVE_PA to non-zero, which then triggers a #GP when SYSCFG.SNPEn is being set and this will subsequently cause SNP_INIT(_EX) to fail with INVALID_CONFIG error as SYSCFG[SnpEn] is not set on all CPUs. Essentially SNP host enabling code should be invoked before KVM initialization, which is currently not the case when KVM is built-in. Add fix to call snp_rmptable_init() early from iommu_snp_enable() directly and not invoked via device_initcall() which enables SNP host support before KVM initialization with kvm_amd module built-in. Add additional handling for `iommu=off` or `amd_iommu=off` options. Note that IOMMUs need to be enabled for SNP initialization, therefore, if host SNP support is enabled but late IOMMU initialization fails then that will cause PSP driver's SNP_INIT to fail as IOMMU SNP sanity checks in SNP firmware will fail with invalid configuration error as below: [ 9.723114] ccp 0000:23:00.1: sev enabled [ 9.727602] ccp 0000:23:00.1: psp enabled [ 9.732527] ccp 0000:a2:00.1: enabling device (0000 -> 0002) [ 9.739098] ccp 0000:a2:00.1: no command queues available [ 9.745167] ccp 0000:a2:00.1: psp enabled [ 9.805337] ccp 0000:23:00.1: SEV-SNP: failed to INIT rc -5, error 0x3 [ 9.866426] ccp 0000:23:00.1: SEV API:1.53 build:5 Fixes: c3b86e61b756 ("x86/cpufeatures: Enable/unmask SEV-SNP CPU feature") Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Co-developed-by: Vasant Hegde Signed-off-by: Vasant Hegde Cc: Signed-off-by: Ashish Kalra Acked-by: Joerg Roedel Message-ID: <138b520fb83964782303b43ade4369cd181fdd9c.1739226950.git.ashish.kalra@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/sev.h | 2 ++ arch/x86/virt/svm/sev.c | 23 +++++++---------------- drivers/iommu/amd/init.c | 34 ++++++++++++++++++++++++++++++---- 3 files changed, 39 insertions(+), 20 deletions(-) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 5d9685f92e5c..1581246491b5 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -531,6 +531,7 @@ static inline void __init snp_secure_tsc_init(void) { } #ifdef CONFIG_KVM_AMD_SEV bool snp_probe_rmptable_info(void); +int snp_rmptable_init(void); int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level); void snp_dump_hva_rmpentry(unsigned long address); int psmash(u64 pfn); @@ -541,6 +542,7 @@ void kdump_sev_callback(void); void snp_fixup_e820_tables(void); #else static inline bool snp_probe_rmptable_info(void) { return false; } +static inline int snp_rmptable_init(void) { return -ENOSYS; } static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } static inline void snp_dump_hva_rmpentry(unsigned long address) {} static inline int psmash(u64 pfn) { return -ENODEV; } diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index 1dcc027ec77e..42e74a5a7d78 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -505,19 +505,19 @@ static bool __init setup_rmptable(void) * described in the SNP_INIT_EX firmware command description in the SNP * firmware ABI spec. */ -static int __init snp_rmptable_init(void) +int __init snp_rmptable_init(void) { unsigned int i; u64 val; - if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) - return 0; + if (WARN_ON_ONCE(!cc_platform_has(CC_ATTR_HOST_SEV_SNP))) + return -ENOSYS; - if (!amd_iommu_snp_en) - goto nosnp; + if (WARN_ON_ONCE(!amd_iommu_snp_en)) + return -ENOSYS; if (!setup_rmptable()) - goto nosnp; + return -ENOSYS; /* * Check if SEV-SNP is already enabled, this can happen in case of @@ -530,7 +530,7 @@ static int __init snp_rmptable_init(void) /* Zero out the RMP bookkeeping area */ if (!clear_rmptable_bookkeeping()) { free_rmp_segment_table(); - goto nosnp; + return -ENOSYS; } /* Zero out the RMP entries */ @@ -562,17 +562,8 @@ skip_enable: crash_kexec_post_notifiers = true; return 0; - -nosnp: - cc_platform_clear(CC_ATTR_HOST_SEV_SNP); - return -ENOSYS; } -/* - * This must be called after the IOMMU has been initialized. - */ -device_initcall(snp_rmptable_init); - static void set_rmp_segment_info(unsigned int segment_shift) { rmp_segment_shift = segment_shift; diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index c5cd92edada0..2fecfed75e54 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3194,7 +3194,7 @@ out: return true; } -static void iommu_snp_enable(void) +static __init void iommu_snp_enable(void) { #ifdef CONFIG_KVM_AMD_SEV if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) @@ -3219,6 +3219,14 @@ static void iommu_snp_enable(void) goto disable_snp; } + /* + * Enable host SNP support once SNP support is checked on IOMMU. + */ + if (snp_rmptable_init()) { + pr_warn("SNP: RMP initialization failed, SNP cannot be supported.\n"); + goto disable_snp; + } + pr_info("IOMMU SNP support enabled.\n"); return; @@ -3318,6 +3326,19 @@ static int __init iommu_go_to_state(enum iommu_init_state state) ret = state_next(); } + /* + * SNP platform initilazation requires IOMMUs to be fully configured. + * If the SNP support on IOMMUs has NOT been checked, simply mark SNP + * as unsupported. If the SNP support on IOMMUs has been checked and + * host SNP support enabled but RMP enforcement has not been enabled + * in IOMMUs, then the system is in a half-baked state, but can limp + * along as all memory should be Hypervisor-Owned in the RMP. WARN, + * but leave SNP as "supported" to avoid confusing the kernel. + */ + if (ret && cc_platform_has(CC_ATTR_HOST_SEV_SNP) && + !WARN_ON_ONCE(amd_iommu_snp_en)) + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); + return ret; } @@ -3426,18 +3447,23 @@ void __init amd_iommu_detect(void) int ret; if (no_iommu || (iommu_detected && !gart_iommu_aperture)) - return; + goto disable_snp; if (!amd_iommu_sme_check()) - return; + goto disable_snp; ret = iommu_go_to_state(IOMMU_IVRS_DETECTED); if (ret) - return; + goto disable_snp; amd_iommu_detected = true; iommu_detected = 1; x86_init.iommu.iommu_init = amd_iommu_init; + return; + +disable_snp: + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); } /**************************************************************************** -- 2.50.1 From d440148418f4816b4973ec6723bf63821793a0a7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 15 Feb 2025 09:28:55 -0800 Subject: [PATCH 11/16] tegra210-adma: fix 32-bit x86 build The Tegra210 Audio DMA controller driver did a plain divide: page_no = (res_page->start - res_base->start) / cdata->ch_base_offset; which causes problems on 32-bit x86 configurations that have 64-bit resource sizes: x86_64-linux-ld: drivers/dma/tegra210-adma.o: in function `tegra_adma_probe': tegra210-adma.c:(.text+0x1322): undefined reference to `__udivdi3' because gcc doesn't generate the trivial code for a 64-by-32 divide, turning it into a function call to do a full 64-by-64 divide. And the kernel intentionally doesn't provide that helper function, because 99% of the time all you want is the narrower version. Of course, tegra210 is a 64-bit architecture and the 32-bit x86 build is purely for build testing, so this really is just about build coverage failure. But build coverage is good. Side note: div_u64() would be suboptimal if you actually have a 32-bit resource_t, so our "helper" for divides are admittedly making it harder than it should be to generate good code for all the possible cases. At some point, I'll consider 32-bit x86 so entirely legacy that I can't find it in myself to care any more, and we'll just add the __udivdi3 library function. But for now, the right thing to do is to use "div_u64()" to show that you know that you are doing the simpler divide with a 32-bit number. And the build error enforces that. While fixing the build issue, also check for division-by-zero, and for overflow. Which hopefully cannot happen on real production hardware, but the value of 'ch_base_offset' can definitely be zero in other places. Reported-by: Guenter Roeck Signed-off-by: Linus Torvalds --- drivers/dma/tegra210-adma.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index 6896da8ac7ef..5c6a5b358987 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -887,7 +887,7 @@ static int tegra_adma_probe(struct platform_device *pdev) const struct tegra_adma_chip_data *cdata; struct tegra_adma *tdma; struct resource *res_page, *res_base; - int ret, i, page_no; + int ret, i; cdata = of_device_get_match_data(&pdev->dev); if (!cdata) { @@ -914,9 +914,20 @@ static int tegra_adma_probe(struct platform_device *pdev) res_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "global"); if (res_base) { - page_no = (res_page->start - res_base->start) / cdata->ch_base_offset; - if (page_no <= 0) + resource_size_t page_offset, page_no; + unsigned int ch_base_offset; + + if (res_page->start < res_base->start) + return -EINVAL; + page_offset = res_page->start - res_base->start; + ch_base_offset = cdata->ch_base_offset; + if (!ch_base_offset) return -EINVAL; + + page_no = div_u64(page_offset, ch_base_offset); + if (!page_no || page_no > INT_MAX) + return -EINVAL; + tdma->ch_page_no = page_no - 1; tdma->base_addr = devm_ioremap_resource(&pdev->dev, res_base); if (IS_ERR(tdma->base_addr)) -- 2.50.1 From 129fe718819cc5e24ea2f489db9ccd4371f0c6f6 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 14 Feb 2025 11:55:47 -0500 Subject: [PATCH 12/16] tracing: Do not allow mmap() of persistent ring buffer When trying to mmap a trace instance buffer that is attached to reserve_mem, it would crash: BUG: unable to handle page fault for address: ffffe97bd00025c8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 2862f3067 P4D 2862f3067 PUD 0 Oops: Oops: 0000 [#1] PREEMPT_RT SMP PTI CPU: 4 UID: 0 PID: 981 Comm: mmap-rb Not tainted 6.14.0-rc2-test-00003-g7f1a5e3fbf9e-dirty #233 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 RIP: 0010:validate_page_before_insert+0x5/0xb0 Code: e2 01 89 d0 c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 <48> 8b 46 08 a8 01 75 67 66 90 48 89 f0 8b 50 34 85 d2 74 76 48 89 RSP: 0018:ffffb148c2f3f968 EFLAGS: 00010246 RAX: ffff9fa5d3322000 RBX: ffff9fa5ccff9c08 RCX: 00000000b879ed29 RDX: ffffe97bd00025c0 RSI: ffffe97bd00025c0 RDI: ffff9fa5ccff9c08 RBP: ffffb148c2f3f9f0 R08: 0000000000000004 R09: 0000000000000004 R10: 0000000000000000 R11: 0000000000000200 R12: 0000000000000000 R13: 00007f16a18d5000 R14: ffff9fa5c48db6a8 R15: 0000000000000000 FS: 00007f16a1b54740(0000) GS:ffff9fa73df00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffe97bd00025c8 CR3: 00000001048c6006 CR4: 0000000000172ef0 Call Trace: ? __die_body.cold+0x19/0x1f ? __die+0x2e/0x40 ? page_fault_oops+0x157/0x2b0 ? search_module_extables+0x53/0x80 ? validate_page_before_insert+0x5/0xb0 ? kernelmode_fixup_or_oops.isra.0+0x5f/0x70 ? __bad_area_nosemaphore+0x16e/0x1b0 ? bad_area_nosemaphore+0x16/0x20 ? do_kern_addr_fault+0x77/0x90 ? exc_page_fault+0x22b/0x230 ? asm_exc_page_fault+0x2b/0x30 ? validate_page_before_insert+0x5/0xb0 ? vm_insert_pages+0x151/0x400 __rb_map_vma+0x21f/0x3f0 ring_buffer_map+0x21b/0x2f0 tracing_buffers_mmap+0x70/0xd0 __mmap_region+0x6f0/0xbd0 mmap_region+0x7f/0x130 do_mmap+0x475/0x610 vm_mmap_pgoff+0xf2/0x1d0 ksys_mmap_pgoff+0x166/0x200 __x64_sys_mmap+0x37/0x50 x64_sys_call+0x1670/0x1d70 do_syscall_64+0xbb/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f The reason was that the code that maps the ring buffer pages to user space has: page = virt_to_page((void *)cpu_buffer->subbuf_ids[s]); And uses that in: vm_insert_pages(vma, vma->vm_start, pages, &nr_pages); But virt_to_page() does not work with vmap()'d memory which is what the persistent ring buffer has. It is rather trivial to allow this, but for now just disable mmap() of instances that have their ring buffer from the reserve_mem option. If an mmap() is performed on a persistent buffer it will return -ENODEV just like it would if the .mmap field wasn't defined in the file_operations structure. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Vincent Donnefort Link: https://lore.kernel.org/20250214115547.0d7287d3@gandalf.local.home Fixes: 9b7bdf6f6ece6 ("tracing: Have trace_printk not use binary prints if boot buffer") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 25ff37aab00f..0e6d517e74e0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8279,6 +8279,10 @@ static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) struct trace_iterator *iter = &info->iter; int ret = 0; + /* Currently the boot mapped buffer is not supported for mmap */ + if (iter->tr->flags & TRACE_ARRAY_FL_BOOT) + return -ENODEV; + ret = get_snapshot_map(iter->tr); if (ret) return ret; -- 2.50.1 From 97937834ae876f29565415ab15f1284666dc6be3 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 14 Feb 2025 12:35:12 -0500 Subject: [PATCH 13/16] ring-buffer: Update pages_touched to reflect persistent buffer content The pages_touched field represents the number of subbuffers in the ring buffer that have content that can be read. This is used in accounting of "dirty_pages" and "buffer_percent" to allow the user to wait for the buffer to be filled to a certain amount before it reads the buffer in blocking mode. The persistent buffer never updated this value so it was set to zero, and this accounting would take it as it had no content. This would cause user space to wait for content even though there's enough content in the ring buffer that satisfies the buffer_percent. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Vincent Donnefort Link: https://lore.kernel.org/20250214123512.0631436e@gandalf.local.home Fixes: 5f3b6e839f3ce ("ring-buffer: Validate boot range memory events") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 0419d41a2060..bb6089c2951e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1850,6 +1850,11 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->cpu); goto invalid; } + + /* If the buffer has content, update pages_touched */ + if (ret) + local_inc(&cpu_buffer->pages_touched); + entries += ret; entry_bytes += local_read(&head_page->page->commit); local_set(&cpu_buffer->head_page->entries, ret); -- 2.50.1 From 7103f0589ac220eac3d2b1e8411494b31b883d06 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Thu, 23 Jan 2025 13:14:34 +0100 Subject: [PATCH 14/16] x86/microcode/AMD: Remove ugly linebreak in __verify_patch_section() signature No functional changes. Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20250211163648.30531-2-bp@kernel.org --- arch/x86/kernel/cpu/microcode/amd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index a5dac7f3c0a0..4a62625c311a 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -246,8 +246,7 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size) * On success, @sh_psize returns the patch size according to the section header, * to the caller. */ -static bool -__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize) +static bool __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize) { u32 p_type, p_size; const u32 *hdr; -- 2.50.1 From 3ef0740d10b005a45e8ae5b4b7b5d37bfddf63c0 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Thu, 23 Jan 2025 12:23:47 +0100 Subject: [PATCH 15/16] x86/microcode/AMD: Remove unused save_microcode_in_initrd_amd() declarations Commit a7939f016720 ("x86/microcode/amd: Cache builtin/initrd microcode early") renamed it to save_microcode_in_initrd() and made it static. Zap the forgotten declarations. No functional changes. Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20250211163648.30531-3-bp@kernel.org --- arch/x86/kernel/cpu/microcode/amd.c | 2 +- arch/x86/kernel/cpu/microcode/internal.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 4a62625c311a..f831c0602994 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -517,7 +517,7 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize) * patch container file in initrd, traverse equivalent cpu table, look for a * matching microcode patch, and update, all in initrd memory in place. * When vmalloc() is available for use later -- on 64-bit during first AP load, - * and on 32-bit during save_microcode_in_initrd_amd() -- we can call + * and on 32-bit during save_microcode_in_initrd() -- we can call * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. * diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h index 21776c529fa9..5df621752fef 100644 --- a/arch/x86/kernel/cpu/microcode/internal.h +++ b/arch/x86/kernel/cpu/microcode/internal.h @@ -100,14 +100,12 @@ extern bool force_minrev; #ifdef CONFIG_CPU_SUP_AMD void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family); void load_ucode_amd_ap(unsigned int family); -int save_microcode_in_initrd_amd(unsigned int family); void reload_ucode_amd(unsigned int cpu); struct microcode_ops *init_amd_microcode(void); void exit_amd_microcode(void); #else /* CONFIG_CPU_SUP_AMD */ static inline void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family) { } static inline void load_ucode_amd_ap(unsigned int family) { } -static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } static inline void reload_ucode_amd(unsigned int cpu) { } static inline struct microcode_ops *init_amd_microcode(void) { return NULL; } static inline void exit_amd_microcode(void) { } -- 2.50.1 From dc15675074dcfd79a2f10a6e39f96b0244961a01 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Thu, 23 Jan 2025 12:46:45 +0100 Subject: [PATCH 16/16] x86/microcode/AMD: Merge early_apply_microcode() into its single callsite No functional changes. Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20250211163648.30531-4-bp@kernel.org --- arch/x86/kernel/cpu/microcode/amd.c | 60 +++++++++++++---------------- 1 file changed, 26 insertions(+), 34 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index f831c0602994..90f93b3ca9db 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -512,39 +512,6 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize) return true; } -/* - * Early load occurs before we can vmalloc(). So we look for the microcode - * patch container file in initrd, traverse equivalent cpu table, look for a - * matching microcode patch, and update, all in initrd memory in place. - * When vmalloc() is available for use later -- on 64-bit during first AP load, - * and on 32-bit during save_microcode_in_initrd() -- we can call - * load_microcode_amd() to save equivalent cpu table and microcode patches in - * kernel heap memory. - * - * Returns true if container found (sets @desc), false otherwise. - */ -static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size) -{ - struct cont_desc desc = { 0 }; - struct microcode_amd *mc; - - scan_containers(ucode, size, &desc); - - mc = desc.mc; - if (!mc) - return false; - - /* - * Allow application of the same revision to pick up SMT-specific - * changes even if the revision of the other SMT thread is already - * up-to-date. - */ - if (old_rev > mc->hdr.patch_id) - return false; - - return __apply_microcode_amd(mc, desc.psize); -} - static bool get_builtin_microcode(struct cpio_data *cp) { char fw_name[36] = "amd-ucode/microcode_amd.bin"; @@ -582,8 +549,19 @@ static bool __init find_blobs_in_containers(struct cpio_data *ret) return found; } +/* + * Early load occurs before we can vmalloc(). So we look for the microcode + * patch container file in initrd, traverse equivalent cpu table, look for a + * matching microcode patch, and update, all in initrd memory in place. + * When vmalloc() is available for use later -- on 64-bit during first AP load, + * and on 32-bit during save_microcode_in_initrd() -- we can call + * load_microcode_amd() to save equivalent cpu table and microcode patches in + * kernel heap memory. + */ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax) { + struct cont_desc desc = { }; + struct microcode_amd *mc; struct cpio_data cp = { }; u32 dummy; @@ -597,7 +575,21 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_ if (!find_blobs_in_containers(&cp)) return; - if (early_apply_microcode(ed->old_rev, cp.data, cp.size)) + scan_containers(cp.data, cp.size, &desc); + + mc = desc.mc; + if (!mc) + return; + + /* + * Allow application of the same revision to pick up SMT-specific + * changes even if the revision of the other SMT thread is already + * up-to-date. + */ + if (ed->old_rev > mc->hdr.patch_id) + return; + + if (__apply_microcode_amd(mc, desc.psize)) native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy); } -- 2.50.1