Contributors: 24
Author Tokens Token Proportion Commits Commit Proportion
Tom Lendacky 4512 46.92% 37 27.61%
Joerg Roedel 2414 25.10% 30 22.39%
Brijesh Singh 1054 10.96% 15 11.19%
Ashish Kalra 510 5.30% 2 1.49%
Borislav Petkov 333 3.46% 13 9.70%
Michael Roth 318 3.31% 8 5.97%
Kirill A. Shutemov 171 1.78% 2 1.49%
Michael Sterritt 116 1.21% 1 0.75%
Nikunj A. Dadhania 38 0.40% 2 1.49%
Dionna Glaze 31 0.32% 2 1.49%
Alexey Kardashevskiy 18 0.19% 1 0.75%
Li RongQing 17 0.18% 1 0.75%
Ard Biesheuvel 14 0.15% 2 1.49%
Kevin Loughlin 13 0.14% 1 0.75%
Jason A. Donenfeld 13 0.14% 1 0.75%
Thomas Gleixner 11 0.11% 5 3.73%
Martin Radev 11 0.11% 1 0.75%
Ashwin Dayanand Kamat 7 0.07% 1 0.75%
Ingo Molnar 6 0.06% 4 2.99%
Linus Torvalds (pre-git) 2 0.02% 1 0.75%
Jack Steiner 2 0.02% 1 0.75%
Harvey Harrison 2 0.02% 1 0.75%
Andrew Morton 2 0.02% 1 0.75%
Peter Zijlstra 1 0.01% 1 0.75%
Total 9616 134

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669
// SPDX-License-Identifier: GPL-2.0-only
/*
 * AMD Memory Encryption Support
 *
 * Copyright (C) 2019 SUSE
 *
 * Author: Joerg Roedel <jroedel@suse.de>
 */

#define pr_fmt(fmt)	"SEV: " fmt

#include <linux/sched/debug.h>	/* For show_regs() */
#include <linux/percpu-defs.h>
#include <linux/cc_platform.h>
#include <linux/printk.h>
#include <linux/mm_types.h>
#include <linux/set_memory.h>
#include <linux/memblock.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/cpumask.h>
#include <linux/efi.h>
#include <linux/platform_device.h>
#include <linux/io.h>
#include <linux/psp-sev.h>
#include <linux/dmi.h>
#include <uapi/linux/sev-guest.h>

#include <asm/init.h>
#include <asm/cpu_entry_area.h>
#include <asm/stacktrace.h>
#include <asm/sev.h>
#include <asm/insn-eval.h>
#include <asm/fpu/xcr.h>
#include <asm/processor.h>
#include <asm/realmode.h>
#include <asm/setup.h>
#include <asm/traps.h>
#include <asm/svm.h>
#include <asm/smp.h>
#include <asm/cpu.h>
#include <asm/apic.h>
#include <asm/cpuid.h>
#include <asm/cmdline.h>

#define DR7_RESET_VALUE        0x400

/* AP INIT values as documented in the APM2  section "Processor Initialization State" */
#define AP_INIT_CS_LIMIT		0xffff
#define AP_INIT_DS_LIMIT		0xffff
#define AP_INIT_LDTR_LIMIT		0xffff
#define AP_INIT_GDTR_LIMIT		0xffff
#define AP_INIT_IDTR_LIMIT		0xffff
#define AP_INIT_TR_LIMIT		0xffff
#define AP_INIT_RFLAGS_DEFAULT		0x2
#define AP_INIT_DR6_DEFAULT		0xffff0ff0
#define AP_INIT_GPAT_DEFAULT		0x0007040600070406ULL
#define AP_INIT_XCR0_DEFAULT		0x1
#define AP_INIT_X87_FTW_DEFAULT		0x5555
#define AP_INIT_X87_FCW_DEFAULT		0x0040
#define AP_INIT_CR0_DEFAULT		0x60000010
#define AP_INIT_MXCSR_DEFAULT		0x1f80

static const char * const sev_status_feat_names[] = {
	[MSR_AMD64_SEV_ENABLED_BIT]		= "SEV",
	[MSR_AMD64_SEV_ES_ENABLED_BIT]		= "SEV-ES",
	[MSR_AMD64_SEV_SNP_ENABLED_BIT]		= "SEV-SNP",
	[MSR_AMD64_SNP_VTOM_BIT]		= "vTom",
	[MSR_AMD64_SNP_REFLECT_VC_BIT]		= "ReflectVC",
	[MSR_AMD64_SNP_RESTRICTED_INJ_BIT]	= "RI",
	[MSR_AMD64_SNP_ALT_INJ_BIT]		= "AI",
	[MSR_AMD64_SNP_DEBUG_SWAP_BIT]		= "DebugSwap",
	[MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT]	= "NoHostIBS",
	[MSR_AMD64_SNP_BTB_ISOLATION_BIT]	= "BTBIsol",
	[MSR_AMD64_SNP_VMPL_SSS_BIT]		= "VmplSSS",
	[MSR_AMD64_SNP_SECURE_TSC_BIT]		= "SecureTSC",
	[MSR_AMD64_SNP_VMGEXIT_PARAM_BIT]	= "VMGExitParam",
	[MSR_AMD64_SNP_IBS_VIRT_BIT]		= "IBSVirt",
	[MSR_AMD64_SNP_VMSA_REG_PROT_BIT]	= "VMSARegProt",
	[MSR_AMD64_SNP_SMT_PROT_BIT]		= "SMTProt",
};

/* For early boot hypervisor communication in SEV-ES enabled guests */
static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);

/*
 * Needs to be in the .data section because we need it NULL before bss is
 * cleared
 */
static struct ghcb *boot_ghcb __section(".data");

/* Bitmap of SEV features supported by the hypervisor */
static u64 sev_hv_features __ro_after_init;

/* Secrets page physical address from the CC blob */
static u64 secrets_pa __ro_after_init;

/* #VC handler runtime per-CPU data */
struct sev_es_runtime_data {
	struct ghcb ghcb_page;

	/*
	 * Reserve one page per CPU as backup storage for the unencrypted GHCB.
	 * It is needed when an NMI happens while the #VC handler uses the real
	 * GHCB, and the NMI handler itself is causing another #VC exception. In
	 * that case the GHCB content of the first handler needs to be backed up
	 * and restored.
	 */
	struct ghcb backup_ghcb;

	/*
	 * Mark the per-cpu GHCBs as in-use to detect nested #VC exceptions.
	 * There is no need for it to be atomic, because nothing is written to
	 * the GHCB between the read and the write of ghcb_active. So it is safe
	 * to use it when a nested #VC exception happens before the write.
	 *
	 * This is necessary for example in the #VC->NMI->#VC case when the NMI
	 * happens while the first #VC handler uses the GHCB. When the NMI code
	 * raises a second #VC handler it might overwrite the contents of the
	 * GHCB written by the first handler. To avoid this the content of the
	 * GHCB is saved and restored when the GHCB is detected to be in use
	 * already.
	 */
	bool ghcb_active;
	bool backup_ghcb_active;

	/*
	 * Cached DR7 value - write it on DR7 writes and return it on reads.
	 * That value will never make it to the real hardware DR7 as debugging
	 * is currently unsupported in SEV-ES guests.
	 */
	unsigned long dr7;
};

struct ghcb_state {
	struct ghcb *ghcb;
};

/* For early boot SVSM communication */
static struct svsm_ca boot_svsm_ca_page __aligned(PAGE_SIZE);

static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
static DEFINE_PER_CPU(struct svsm_ca *, svsm_caa);
static DEFINE_PER_CPU(u64, svsm_caa_pa);

static __always_inline bool on_vc_stack(struct pt_regs *regs)
{
	unsigned long sp = regs->sp;

	/* User-mode RSP is not trusted */
	if (user_mode(regs))
		return false;

	/* SYSCALL gap still has user-mode RSP */
	if (ip_within_syscall_gap(regs))
		return false;

	return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
}

/*
 * This function handles the case when an NMI is raised in the #VC
 * exception handler entry code, before the #VC handler has switched off
 * its IST stack. In this case, the IST entry for #VC must be adjusted,
 * so that any nested #VC exception will not overwrite the stack
 * contents of the interrupted #VC handler.
 *
 * The IST entry is adjusted unconditionally so that it can be also be
 * unconditionally adjusted back in __sev_es_ist_exit(). Otherwise a
 * nested sev_es_ist_exit() call may adjust back the IST entry too
 * early.
 *
 * The __sev_es_ist_enter() and __sev_es_ist_exit() functions always run
 * on the NMI IST stack, as they are only called from NMI handling code
 * right now.
 */
void noinstr __sev_es_ist_enter(struct pt_regs *regs)
{
	unsigned long old_ist, new_ist;

	/* Read old IST entry */
	new_ist = old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);

	/*
	 * If NMI happened while on the #VC IST stack, set the new IST
	 * value below regs->sp, so that the interrupted stack frame is
	 * not overwritten by subsequent #VC exceptions.
	 */
	if (on_vc_stack(regs))
		new_ist = regs->sp;

	/*
	 * Reserve additional 8 bytes and store old IST value so this
	 * adjustment can be unrolled in __sev_es_ist_exit().
	 */
	new_ist -= sizeof(old_ist);
	*(unsigned long *)new_ist = old_ist;

	/* Set new IST entry */
	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist);
}

void noinstr __sev_es_ist_exit(void)
{
	unsigned long ist;

	/* Read IST entry */
	ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);

	if (WARN_ON(ist == __this_cpu_ist_top_va(VC)))
		return;

	/* Read back old IST entry and write it to the TSS */
	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
}

/*
 * Nothing shall interrupt this code path while holding the per-CPU
 * GHCB. The backup GHCB is only for NMIs interrupting this path.
 *
 * Callers must disable local interrupts around it.
 */
static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
{
	struct sev_es_runtime_data *data;
	struct ghcb *ghcb;

	WARN_ON(!irqs_disabled());

	data = this_cpu_read(runtime_data);
	ghcb = &data->ghcb_page;

	if (unlikely(data->ghcb_active)) {
		/* GHCB is already in use - save its contents */

		if (unlikely(data->backup_ghcb_active)) {
			/*
			 * Backup-GHCB is also already in use. There is no way
			 * to continue here so just kill the machine. To make
			 * panic() work, mark GHCBs inactive so that messages
			 * can be printed out.
			 */
			data->ghcb_active        = false;
			data->backup_ghcb_active = false;

			instrumentation_begin();
			panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
			instrumentation_end();
		}

		/* Mark backup_ghcb active before writing to it */
		data->backup_ghcb_active = true;

		state->ghcb = &data->backup_ghcb;

		/* Backup GHCB content */
		*state->ghcb = *ghcb;
	} else {
		state->ghcb = NULL;
		data->ghcb_active = true;
	}

	return ghcb;
}

static inline u64 sev_es_rd_ghcb_msr(void)
{
	return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
}

static __always_inline void sev_es_wr_ghcb_msr(u64 val)
{
	u32 low, high;

	low  = (u32)(val);
	high = (u32)(val >> 32);

	native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high);
}

static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt,
				unsigned char *buffer)
{
	return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
}

static enum es_result __vc_decode_user_insn(struct es_em_ctxt *ctxt)
{
	char buffer[MAX_INSN_SIZE];
	int insn_bytes;

	insn_bytes = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
	if (insn_bytes == 0) {
		/* Nothing could be copied */
		ctxt->fi.vector     = X86_TRAP_PF;
		ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
		ctxt->fi.cr2        = ctxt->regs->ip;
		return ES_EXCEPTION;
	} else if (insn_bytes == -EINVAL) {
		/* Effective RIP could not be calculated */
		ctxt->fi.vector     = X86_TRAP_GP;
		ctxt->fi.error_code = 0;
		ctxt->fi.cr2        = 0;
		return ES_EXCEPTION;
	}

	if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, insn_bytes))
		return ES_DECODE_FAILED;

	if (ctxt->insn.immediate.got)
		return ES_OK;
	else
		return ES_DECODE_FAILED;
}

static enum es_result __vc_decode_kern_insn(struct es_em_ctxt *ctxt)
{
	char buffer[MAX_INSN_SIZE];
	int res, ret;

	res = vc_fetch_insn_kernel(ctxt, buffer);
	if (res) {
		ctxt->fi.vector     = X86_TRAP_PF;
		ctxt->fi.error_code = X86_PF_INSTR;
		ctxt->fi.cr2        = ctxt->regs->ip;
		return ES_EXCEPTION;
	}

	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
	if (ret < 0)
		return ES_DECODE_FAILED;
	else
		return ES_OK;
}

static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
{
	if (user_mode(ctxt->regs))
		return __vc_decode_user_insn(ctxt);
	else
		return __vc_decode_kern_insn(ctxt);
}

static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
				   char *dst, char *buf, size_t size)
{
	unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;

	/*
	 * This function uses __put_user() independent of whether kernel or user
	 * memory is accessed. This works fine because __put_user() does no
	 * sanity checks of the pointer being accessed. All that it does is
	 * to report when the access failed.
	 *
	 * Also, this function runs in atomic context, so __put_user() is not
	 * allowed to sleep. The page-fault handler detects that it is running
	 * in atomic context and will not try to take mmap_sem and handle the
	 * fault, so additional pagefault_enable()/disable() calls are not
	 * needed.
	 *
	 * The access can't be done via copy_to_user() here because
	 * vc_write_mem() must not use string instructions to access unsafe
	 * memory. The reason is that MOVS is emulated by the #VC handler by
	 * splitting the move up into a read and a write and taking a nested #VC
	 * exception on whatever of them is the MMIO access. Using string
	 * instructions here would cause infinite nesting.
	 */
	switch (size) {
	case 1: {
		u8 d1;
		u8 __user *target = (u8 __user *)dst;

		memcpy(&d1, buf, 1);
		if (__put_user(d1, target))
			goto fault;
		break;
	}
	case 2: {
		u16 d2;
		u16 __user *target = (u16 __user *)dst;

		memcpy(&d2, buf, 2);
		if (__put_user(d2, target))
			goto fault;
		break;
	}
	case 4: {
		u32 d4;
		u32 __user *target = (u32 __user *)dst;

		memcpy(&d4, buf, 4);
		if (__put_user(d4, target))
			goto fault;
		break;
	}
	case 8: {
		u64 d8;
		u64 __user *target = (u64 __user *)dst;

		memcpy(&d8, buf, 8);
		if (__put_user(d8, target))
			goto fault;
		break;
	}
	default:
		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
		return ES_UNSUPPORTED;
	}

	return ES_OK;

fault:
	if (user_mode(ctxt->regs))
		error_code |= X86_PF_USER;

	ctxt->fi.vector = X86_TRAP_PF;
	ctxt->fi.error_code = error_code;
	ctxt->fi.cr2 = (unsigned long)dst;

	return ES_EXCEPTION;
}

static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
				  char *src, char *buf, size_t size)
{
	unsigned long error_code = X86_PF_PROT;

	/*
	 * This function uses __get_user() independent of whether kernel or user
	 * memory is accessed. This works fine because __get_user() does no
	 * sanity checks of the pointer being accessed. All that it does is
	 * to report when the access failed.
	 *
	 * Also, this function runs in atomic context, so __get_user() is not
	 * allowed to sleep. The page-fault handler detects that it is running
	 * in atomic context and will not try to take mmap_sem and handle the
	 * fault, so additional pagefault_enable()/disable() calls are not
	 * needed.
	 *
	 * The access can't be done via copy_from_user() here because
	 * vc_read_mem() must not use string instructions to access unsafe
	 * memory. The reason is that MOVS is emulated by the #VC handler by
	 * splitting the move up into a read and a write and taking a nested #VC
	 * exception on whatever of them is the MMIO access. Using string
	 * instructions here would cause infinite nesting.
	 */
	switch (size) {
	case 1: {
		u8 d1;
		u8 __user *s = (u8 __user *)src;

		if (__get_user(d1, s))
			goto fault;
		memcpy(buf, &d1, 1);
		break;
	}
	case 2: {
		u16 d2;
		u16 __user *s = (u16 __user *)src;

		if (__get_user(d2, s))
			goto fault;
		memcpy(buf, &d2, 2);
		break;
	}
	case 4: {
		u32 d4;
		u32 __user *s = (u32 __user *)src;

		if (__get_user(d4, s))
			goto fault;
		memcpy(buf, &d4, 4);
		break;
	}
	case 8: {
		u64 d8;
		u64 __user *s = (u64 __user *)src;
		if (__get_user(d8, s))
			goto fault;
		memcpy(buf, &d8, 8);
		break;
	}
	default:
		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
		return ES_UNSUPPORTED;
	}

	return ES_OK;

fault:
	if (user_mode(ctxt->regs))
		error_code |= X86_PF_USER;

	ctxt->fi.vector = X86_TRAP_PF;
	ctxt->fi.error_code = error_code;
	ctxt->fi.cr2 = (unsigned long)src;

	return ES_EXCEPTION;
}

static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
					   unsigned long vaddr, phys_addr_t *paddr)
{
	unsigned long va = (unsigned long)vaddr;
	unsigned int level;
	phys_addr_t pa;
	pgd_t *pgd;
	pte_t *pte;

	pgd = __va(read_cr3_pa());
	pgd = &pgd[pgd_index(va)];
	pte = lookup_address_in_pgd(pgd, va, &level);
	if (!pte) {
		ctxt->fi.vector     = X86_TRAP_PF;
		ctxt->fi.cr2        = vaddr;
		ctxt->fi.error_code = 0;

		if (user_mode(ctxt->regs))
			ctxt->fi.error_code |= X86_PF_USER;

		return ES_EXCEPTION;
	}

	if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
		/* Emulated MMIO to/from encrypted memory not supported */
		return ES_UNSUPPORTED;

	pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
	pa |= va & ~page_level_mask(level);

	*paddr = pa;

	return ES_OK;
}

static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
{
	BUG_ON(size > 4);

	if (user_mode(ctxt->regs)) {
		struct thread_struct *t = &current->thread;
		struct io_bitmap *iobm = t->io_bitmap;
		size_t idx;

		if (!iobm)
			goto fault;

		for (idx = port; idx < port + size; ++idx) {
			if (test_bit(idx, iobm->bitmap))
				goto fault;
		}
	}

	return ES_OK;

fault:
	ctxt->fi.vector = X86_TRAP_GP;
	ctxt->fi.error_code = 0;

	return ES_EXCEPTION;
}

static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
{
	long error_code = ctxt->fi.error_code;
	int trapnr = ctxt->fi.vector;

	ctxt->regs->orig_ax = ctxt->fi.error_code;

	switch (trapnr) {
	case X86_TRAP_GP:
		exc_general_protection(ctxt->regs, error_code);
		break;
	case X86_TRAP_UD:
		exc_invalid_op(ctxt->regs);
		break;
	case X86_TRAP_PF:
		write_cr2(ctxt->fi.cr2);
		exc_page_fault(ctxt->regs, error_code);
		break;
	case X86_TRAP_AC:
		exc_alignment_check(ctxt->regs, error_code);
		break;
	default:
		pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
		BUG();
	}
}

/* Include code shared with pre-decompression boot stage */
#include "shared.c"

static inline struct svsm_ca *svsm_get_caa(void)
{
	/*
	 * Use rIP-relative references when called early in the boot. If
	 * ->use_cas is set, then it is late in the boot and no need
	 * to worry about rIP-relative references.
	 */
	if (RIP_REL_REF(sev_cfg).use_cas)
		return this_cpu_read(svsm_caa);
	else
		return RIP_REL_REF(boot_svsm_caa);
}

static u64 svsm_get_caa_pa(void)
{
	/*
	 * Use rIP-relative references when called early in the boot. If
	 * ->use_cas is set, then it is late in the boot and no need
	 * to worry about rIP-relative references.
	 */
	if (RIP_REL_REF(sev_cfg).use_cas)
		return this_cpu_read(svsm_caa_pa);
	else
		return RIP_REL_REF(boot_svsm_caa_pa);
}

static noinstr void __sev_put_ghcb(struct ghcb_state *state)
{
	struct sev_es_runtime_data *data;
	struct ghcb *ghcb;

	WARN_ON(!irqs_disabled());

	data = this_cpu_read(runtime_data);
	ghcb = &data->ghcb_page;

	if (state->ghcb) {
		/* Restore GHCB from Backup */
		*ghcb = *state->ghcb;
		data->backup_ghcb_active = false;
		state->ghcb = NULL;
	} else {
		/*
		 * Invalidate the GHCB so a VMGEXIT instruction issued
		 * from userspace won't appear to be valid.
		 */
		vc_ghcb_invalidate(ghcb);
		data->ghcb_active = false;
	}
}

static int svsm_perform_call_protocol(struct svsm_call *call)
{
	struct ghcb_state state;
	unsigned long flags;
	struct ghcb *ghcb;
	int ret;

	/*
	 * This can be called very early in the boot, use native functions in
	 * order to avoid paravirt issues.
	 */
	flags = native_local_irq_save();

	/*
	 * Use rip-relative references when called early in the boot. If
	 * ghcbs_initialized is set, then it is late in the boot and no need
	 * to worry about rip-relative references in called functions.
	 */
	if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
		ghcb = __sev_get_ghcb(&state);
	else if (RIP_REL_REF(boot_ghcb))
		ghcb = RIP_REL_REF(boot_ghcb);
	else
		ghcb = NULL;

	do {
		ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
			   : svsm_perform_msr_protocol(call);
	} while (ret == -EAGAIN);

	if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
		__sev_put_ghcb(&state);

	native_local_irq_restore(flags);

	return ret;
}

void noinstr __sev_es_nmi_complete(void)
{
	struct ghcb_state state;
	struct ghcb *ghcb;

	ghcb = __sev_get_ghcb(&state);

	vc_ghcb_invalidate(ghcb);
	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE);
	ghcb_set_sw_exit_info_1(ghcb, 0);
	ghcb_set_sw_exit_info_2(ghcb, 0);

	sev_es_wr_ghcb_msr(__pa_nodebug(ghcb));
	VMGEXIT();

	__sev_put_ghcb(&state);
}

static u64 __init get_snp_jump_table_addr(void)
{
	struct snp_secrets_page *secrets;
	void __iomem *mem;
	u64 addr;

	mem = ioremap_encrypted(secrets_pa, PAGE_SIZE);
	if (!mem) {
		pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n");
		return 0;
	}

	secrets = (__force struct snp_secrets_page *)mem;

	addr = secrets->os_area.ap_jump_table_pa;
	iounmap(mem);

	return addr;
}

static u64 __init get_jump_table_addr(void)
{
	struct ghcb_state state;
	unsigned long flags;
	struct ghcb *ghcb;
	u64 ret = 0;

	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		return get_snp_jump_table_addr();

	local_irq_save(flags);

	ghcb = __sev_get_ghcb(&state);

	vc_ghcb_invalidate(ghcb);
	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE);
	ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE);
	ghcb_set_sw_exit_info_2(ghcb, 0);

	sev_es_wr_ghcb_msr(__pa(ghcb));
	VMGEXIT();

	if (ghcb_sw_exit_info_1_is_valid(ghcb) &&
	    ghcb_sw_exit_info_2_is_valid(ghcb))
		ret = ghcb->save.sw_exit_info_2;

	__sev_put_ghcb(&state);

	local_irq_restore(flags);

	return ret;
}

static void __head
early_set_pages_state(unsigned long vaddr, unsigned long paddr,
		      unsigned long npages, enum psc_op op)
{
	unsigned long paddr_end;
	u64 val;

	vaddr = vaddr & PAGE_MASK;

	paddr = paddr & PAGE_MASK;
	paddr_end = paddr + (npages << PAGE_SHIFT);

	while (paddr < paddr_end) {
		/* Page validation must be rescinded before changing to shared */
		if (op == SNP_PAGE_STATE_SHARED)
			pvalidate_4k_page(vaddr, paddr, false);

		/*
		 * Use the MSR protocol because this function can be called before
		 * the GHCB is established.
		 */
		sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
		VMGEXIT();

		val = sev_es_rd_ghcb_msr();

		if (WARN(GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP,
			 "Wrong PSC response code: 0x%x\n",
			 (unsigned int)GHCB_RESP_CODE(val)))
			goto e_term;

		if (WARN(GHCB_MSR_PSC_RESP_VAL(val),
			 "Failed to change page state to '%s' paddr 0x%lx error 0x%llx\n",
			 op == SNP_PAGE_STATE_PRIVATE ? "private" : "shared",
			 paddr, GHCB_MSR_PSC_RESP_VAL(val)))
			goto e_term;

		/* Page validation must be performed after changing to private */
		if (op == SNP_PAGE_STATE_PRIVATE)
			pvalidate_4k_page(vaddr, paddr, true);

		vaddr += PAGE_SIZE;
		paddr += PAGE_SIZE;
	}

	return;

e_term:
	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
}

void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
					 unsigned long npages)
{
	/*
	 * This can be invoked in early boot while running identity mapped, so
	 * use an open coded check for SNP instead of using cc_platform_has().
	 * This eliminates worries about jump tables or checking boot_cpu_data
	 * in the cc_platform_has() function.
	 */
	if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED))
		return;

	 /*
	  * Ask the hypervisor to mark the memory pages as private in the RMP
	  * table.
	  */
	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_PRIVATE);
}

void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
					unsigned long npages)
{
	/*
	 * This can be invoked in early boot while running identity mapped, so
	 * use an open coded check for SNP instead of using cc_platform_has().
	 * This eliminates worries about jump tables or checking boot_cpu_data
	 * in the cc_platform_has() function.
	 */
	if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED))
		return;

	 /* Ask hypervisor to mark the memory pages shared in the RMP table. */
	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
}

static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
				       unsigned long vaddr_end, int op)
{
	struct ghcb_state state;
	bool use_large_entry;
	struct psc_hdr *hdr;
	struct psc_entry *e;
	unsigned long flags;
	unsigned long pfn;
	struct ghcb *ghcb;
	int i;

	hdr = &data->hdr;
	e = data->entries;

	memset(data, 0, sizeof(*data));
	i = 0;

	while (vaddr < vaddr_end && i < ARRAY_SIZE(data->entries)) {
		hdr->end_entry = i;

		if (is_vmalloc_addr((void *)vaddr)) {
			pfn = vmalloc_to_pfn((void *)vaddr);
			use_large_entry = false;
		} else {
			pfn = __pa(vaddr) >> PAGE_SHIFT;
			use_large_entry = true;
		}

		e->gfn = pfn;
		e->operation = op;

		if (use_large_entry && IS_ALIGNED(vaddr, PMD_SIZE) &&
		    (vaddr_end - vaddr) >= PMD_SIZE) {
			e->pagesize = RMP_PG_SIZE_2M;
			vaddr += PMD_SIZE;
		} else {
			e->pagesize = RMP_PG_SIZE_4K;
			vaddr += PAGE_SIZE;
		}

		e++;
		i++;
	}

	/* Page validation must be rescinded before changing to shared */
	if (op == SNP_PAGE_STATE_SHARED)
		pvalidate_pages(data);

	local_irq_save(flags);

	if (sev_cfg.ghcbs_initialized)
		ghcb = __sev_get_ghcb(&state);
	else
		ghcb = boot_ghcb;

	/* Invoke the hypervisor to perform the page state changes */
	if (!ghcb || vmgexit_psc(ghcb, data))
		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);

	if (sev_cfg.ghcbs_initialized)
		__sev_put_ghcb(&state);

	local_irq_restore(flags);

	/* Page validation must be performed after changing to private */
	if (op == SNP_PAGE_STATE_PRIVATE)
		pvalidate_pages(data);

	return vaddr;
}

static void set_pages_state(unsigned long vaddr, unsigned long npages, int op)
{
	struct snp_psc_desc desc;
	unsigned long vaddr_end;

	/* Use the MSR protocol when a GHCB is not available. */
	if (!boot_ghcb)
		return early_set_pages_state(vaddr, __pa(vaddr), npages, op);

	vaddr = vaddr & PAGE_MASK;
	vaddr_end = vaddr + (npages << PAGE_SHIFT);

	while (vaddr < vaddr_end)
		vaddr = __set_pages_state(&desc, vaddr, vaddr_end, op);
}

void snp_set_memory_shared(unsigned long vaddr, unsigned long npages)
{
	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		return;

	set_pages_state(vaddr, npages, SNP_PAGE_STATE_SHARED);
}

void snp_set_memory_private(unsigned long vaddr, unsigned long npages)
{
	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		return;

	set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
}

void snp_accept_memory(phys_addr_t start, phys_addr_t end)
{
	unsigned long vaddr, npages;

	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		return;

	vaddr = (unsigned long)__va(start);
	npages = (end - start) >> PAGE_SHIFT;

	set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
}

static void set_pte_enc(pte_t *kpte, int level, void *va)
{
	struct pte_enc_desc d = {
		.kpte	   = kpte,
		.pte_level = level,
		.va	   = va,
		.encrypt   = true
	};

	prepare_pte_enc(&d);
	set_pte_enc_mask(kpte, d.pfn, d.new_pgprot);
}

static void unshare_all_memory(void)
{
	unsigned long addr, end, size, ghcb;
	struct sev_es_runtime_data *data;
	unsigned int npages, level;
	bool skipped_addr;
	pte_t *pte;
	int cpu;

	/* Unshare the direct mapping. */
	addr = PAGE_OFFSET;
	end  = PAGE_OFFSET + get_max_mapped();

	while (addr < end) {
		pte = lookup_address(addr, &level);
		size = page_level_size(level);
		npages = size / PAGE_SIZE;
		skipped_addr = false;

		if (!pte || !pte_decrypted(*pte) || pte_none(*pte)) {
			addr += size;
			continue;
		}

		/*
		 * Ensure that all the per-CPU GHCBs are made private at the
		 * end of the unsharing loop so that the switch to the slower
		 * MSR protocol happens last.
		 */
		for_each_possible_cpu(cpu) {
			data = per_cpu(runtime_data, cpu);
			ghcb = (unsigned long)&data->ghcb_page;

			if (addr <= ghcb && ghcb <= addr + size) {
				skipped_addr = true;
				break;
			}
		}

		if (!skipped_addr) {
			set_pte_enc(pte, level, (void *)addr);
			snp_set_memory_private(addr, npages);
		}
		addr += size;
	}

	/* Unshare all bss decrypted memory. */
	addr = (unsigned long)__start_bss_decrypted;
	end  = (unsigned long)__start_bss_decrypted_unused;
	npages = (end - addr) >> PAGE_SHIFT;

	for (; addr < end; addr += PAGE_SIZE) {
		pte = lookup_address(addr, &level);
		if (!pte || !pte_decrypted(*pte) || pte_none(*pte))
			continue;

		set_pte_enc(pte, level, (void *)addr);
	}
	addr = (unsigned long)__start_bss_decrypted;
	snp_set_memory_private(addr, npages);

	__flush_tlb_all();
}

/* Stop new private<->shared conversions */
void snp_kexec_begin(void)
{
	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		return;

	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
		return;

	/*
	 * Crash kernel ends up here with interrupts disabled: can't wait for
	 * conversions to finish.
	 *
	 * If race happened, just report and proceed.
	 */
	if (!set_memory_enc_stop_conversion())
		pr_warn("Failed to stop shared<->private conversions\n");
}

void snp_kexec_finish(void)
{
	struct sev_es_runtime_data *data;
	unsigned int level, cpu;
	unsigned long size;
	struct ghcb *ghcb;
	pte_t *pte;

	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		return;

	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
		return;

	unshare_all_memory();

	/*
	 * Switch to using the MSR protocol to change per-CPU GHCBs to
	 * private. All the per-CPU GHCBs have been switched back to private,
	 * so can't do any more GHCB calls to the hypervisor beyond this point
	 * until the kexec'ed kernel starts running.
	 */
	boot_ghcb = NULL;
	sev_cfg.ghcbs_initialized = false;

	for_each_possible_cpu(cpu) {
		data = per_cpu(runtime_data, cpu);
		ghcb = &data->ghcb_page;
		pte = lookup_address((unsigned long)ghcb, &level);
		size = page_level_size(level);
		set_pte_enc(pte, level, (void *)ghcb);
		snp_set_memory_private((unsigned long)ghcb, (size / PAGE_SIZE));
	}
}

static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
{
	int ret;

	if (snp_vmpl) {
		struct svsm_call call = {};
		unsigned long flags;

		local_irq_save(flags);

		call.caa = this_cpu_read(svsm_caa);
		call.rcx = __pa(va);

		if (make_vmsa) {
			/* Protocol 0, Call ID 2 */
			call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
			call.rdx = __pa(caa);
			call.r8  = apic_id;
		} else {
			/* Protocol 0, Call ID 3 */
			call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
		}

		ret = svsm_perform_call_protocol(&call);

		local_irq_restore(flags);
	} else {
		/*
		 * If the kernel runs at VMPL0, it can change the VMSA
		 * bit for a page using the RMPADJUST instruction.
		 * However, for the instruction to succeed it must
		 * target the permissions of a lesser privileged (higher
		 * numbered) VMPL level, so use VMPL1.
		 */
		u64 attrs = 1;

		if (make_vmsa)
			attrs |= RMPADJUST_VMSA_PAGE_BIT;

		ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
	}

	return ret;
}

#define __ATTR_BASE		(SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK)
#define INIT_CS_ATTRIBS		(__ATTR_BASE | SVM_SELECTOR_READ_MASK | SVM_SELECTOR_CODE_MASK)
#define INIT_DS_ATTRIBS		(__ATTR_BASE | SVM_SELECTOR_WRITE_MASK)

#define INIT_LDTR_ATTRIBS	(SVM_SELECTOR_P_MASK | 2)
#define INIT_TR_ATTRIBS		(SVM_SELECTOR_P_MASK | 3)

static void *snp_alloc_vmsa_page(int cpu)
{
	struct page *p;

	/*
	 * Allocate VMSA page to work around the SNP erratum where the CPU will
	 * incorrectly signal an RMP violation #PF if a large page (2MB or 1GB)
	 * collides with the RMP entry of VMSA page. The recommended workaround
	 * is to not use a large page.
	 *
	 * Allocate an 8k page which is also 8k-aligned.
	 */
	p = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
	if (!p)
		return NULL;

	split_page(p, 1);

	/* Free the first 4k. This page may be 2M/1G aligned and cannot be used. */
	__free_page(p);

	return page_address(p + 1);
}

static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
{
	int err;

	err = snp_set_vmsa(vmsa, NULL, apic_id, false);
	if (err)
		pr_err("clear VMSA page failed (%u), leaking page\n", err);
	else
		free_page((unsigned long)vmsa);
}

static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
{
	struct sev_es_save_area *cur_vmsa, *vmsa;
	struct ghcb_state state;
	struct svsm_ca *caa;
	unsigned long flags;
	struct ghcb *ghcb;
	u8 sipi_vector;
	int cpu, ret;
	u64 cr4;

	/*
	 * The hypervisor SNP feature support check has happened earlier, just check
	 * the AP_CREATION one here.
	 */
	if (!(sev_hv_features & GHCB_HV_FT_SNP_AP_CREATION))
		return -EOPNOTSUPP;

	/*
	 * Verify the desired start IP against the known trampoline start IP
	 * to catch any future new trampolines that may be introduced that
	 * would require a new protected guest entry point.
	 */
	if (WARN_ONCE(start_ip != real_mode_header->trampoline_start,
		      "Unsupported SNP start_ip: %lx\n", start_ip))
		return -EINVAL;

	/* Override start_ip with known protected guest start IP */
	start_ip = real_mode_header->sev_es_trampoline_start;

	/* Find the logical CPU for the APIC ID */
	for_each_present_cpu(cpu) {
		if (arch_match_cpu_phys_id(cpu, apic_id))
			break;
	}
	if (cpu >= nr_cpu_ids)
		return -EINVAL;

	cur_vmsa = per_cpu(sev_vmsa, cpu);

	/*
	 * A new VMSA is created each time because there is no guarantee that
	 * the current VMSA is the kernels or that the vCPU is not running. If
	 * an attempt was done to use the current VMSA with a running vCPU, a
	 * #VMEXIT of that vCPU would wipe out all of the settings being done
	 * here.
	 */
	vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page(cpu);
	if (!vmsa)
		return -ENOMEM;

	/* If an SVSM is present, the SVSM per-CPU CAA will be !NULL */
	caa = per_cpu(svsm_caa, cpu);

	/* CR4 should maintain the MCE value */
	cr4 = native_read_cr4() & X86_CR4_MCE;

	/* Set the CS value based on the start_ip converted to a SIPI vector */
	sipi_vector		= (start_ip >> 12);
	vmsa->cs.base		= sipi_vector << 12;
	vmsa->cs.limit		= AP_INIT_CS_LIMIT;
	vmsa->cs.attrib		= INIT_CS_ATTRIBS;
	vmsa->cs.selector	= sipi_vector << 8;

	/* Set the RIP value based on start_ip */
	vmsa->rip		= start_ip & 0xfff;

	/* Set AP INIT defaults as documented in the APM */
	vmsa->ds.limit		= AP_INIT_DS_LIMIT;
	vmsa->ds.attrib		= INIT_DS_ATTRIBS;
	vmsa->es		= vmsa->ds;
	vmsa->fs		= vmsa->ds;
	vmsa->gs		= vmsa->ds;
	vmsa->ss		= vmsa->ds;

	vmsa->gdtr.limit	= AP_INIT_GDTR_LIMIT;
	vmsa->ldtr.limit	= AP_INIT_LDTR_LIMIT;
	vmsa->ldtr.attrib	= INIT_LDTR_ATTRIBS;
	vmsa->idtr.limit	= AP_INIT_IDTR_LIMIT;
	vmsa->tr.limit		= AP_INIT_TR_LIMIT;
	vmsa->tr.attrib		= INIT_TR_ATTRIBS;

	vmsa->cr4		= cr4;
	vmsa->cr0		= AP_INIT_CR0_DEFAULT;
	vmsa->dr7		= DR7_RESET_VALUE;
	vmsa->dr6		= AP_INIT_DR6_DEFAULT;
	vmsa->rflags		= AP_INIT_RFLAGS_DEFAULT;
	vmsa->g_pat		= AP_INIT_GPAT_DEFAULT;
	vmsa->xcr0		= AP_INIT_XCR0_DEFAULT;
	vmsa->mxcsr		= AP_INIT_MXCSR_DEFAULT;
	vmsa->x87_ftw		= AP_INIT_X87_FTW_DEFAULT;
	vmsa->x87_fcw		= AP_INIT_X87_FCW_DEFAULT;

	/* SVME must be set. */
	vmsa->efer		= EFER_SVME;

	/*
	 * Set the SNP-specific fields for this VMSA:
	 *   VMPL level
	 *   SEV_FEATURES (matches the SEV STATUS MSR right shifted 2 bits)
	 */
	vmsa->vmpl		= snp_vmpl;
	vmsa->sev_features	= sev_status >> 2;

	/* Switch the page over to a VMSA page now that it is initialized */
	ret = snp_set_vmsa(vmsa, caa, apic_id, true);
	if (ret) {
		pr_err("set VMSA page failed (%u)\n", ret);
		free_page((unsigned long)vmsa);

		return -EINVAL;
	}

	/* Issue VMGEXIT AP Creation NAE event */
	local_irq_save(flags);

	ghcb = __sev_get_ghcb(&state);

	vc_ghcb_invalidate(ghcb);
	ghcb_set_rax(ghcb, vmsa->sev_features);
	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
	ghcb_set_sw_exit_info_1(ghcb,
				((u64)apic_id << 32)	|
				((u64)snp_vmpl << 16)	|
				SVM_VMGEXIT_AP_CREATE);
	ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));

	sev_es_wr_ghcb_msr(__pa(ghcb));
	VMGEXIT();

	if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
	    lower_32_bits(ghcb->save.sw_exit_info_1)) {
		pr_err("SNP AP Creation error\n");
		ret = -EINVAL;
	}

	__sev_put_ghcb(&state);

	local_irq_restore(flags);

	/* Perform cleanup if there was an error */
	if (ret) {
		snp_cleanup_vmsa(vmsa, apic_id);
		vmsa = NULL;
	}

	/* Free up any previous VMSA page */
	if (cur_vmsa)
		snp_cleanup_vmsa(cur_vmsa, apic_id);

	/* Record the current VMSA page */
	per_cpu(sev_vmsa, cpu) = vmsa;

	return ret;
}

void __init snp_set_wakeup_secondary_cpu(void)
{
	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		return;

	/*
	 * Always set this override if SNP is enabled. This makes it the
	 * required method to start APs under SNP. If the hypervisor does
	 * not support AP creation, then no APs will be started.
	 */
	apic_update_callback(wakeup_secondary_cpu, wakeup_cpu_via_vmgexit);
}

int __init sev_es_setup_ap_jump_table(struct real_mode_header *rmh)
{
	u16 startup_cs, startup_ip;
	phys_addr_t jump_table_pa;
	u64 jump_table_addr;
	u16 __iomem *jump_table;

	jump_table_addr = get_jump_table_addr();

	/* On UP guests there is no jump table so this is not a failure */
	if (!jump_table_addr)
		return 0;

	/* Check if AP Jump Table is page-aligned */
	if (jump_table_addr & ~PAGE_MASK)
		return -EINVAL;

	jump_table_pa = jump_table_addr & PAGE_MASK;

	startup_cs = (u16)(rmh->trampoline_start >> 4);
	startup_ip = (u16)(rmh->sev_es_trampoline_start -
			   rmh->trampoline_start);

	jump_table = ioremap_encrypted(jump_table_pa, PAGE_SIZE);
	if (!jump_table)
		return -EIO;

	writew(startup_ip, &jump_table[0]);
	writew(startup_cs, &jump_table[1]);

	iounmap(jump_table);

	return 0;
}

/*
 * This is needed by the OVMF UEFI firmware which will use whatever it finds in
 * the GHCB MSR as its GHCB to talk to the hypervisor. So make sure the per-cpu
 * runtime GHCBs used by the kernel are also mapped in the EFI page-table.
 */
int __init sev_es_efi_map_ghcbs(pgd_t *pgd)
{
	struct sev_es_runtime_data *data;
	unsigned long address, pflags;
	int cpu;
	u64 pfn;

	if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
		return 0;

	pflags = _PAGE_NX | _PAGE_RW;

	for_each_possible_cpu(cpu) {
		data = per_cpu(runtime_data, cpu);

		address = __pa(&data->ghcb_page);
		pfn = address >> PAGE_SHIFT;

		if (kernel_map_pages_in_pgd(pgd, pfn, address, 1, pflags))
			return 1;
	}

	return 0;
}

/* Writes to the SVSM CAA MSR are ignored */
static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write)
{
	if (write)
		return ES_OK;

	regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa));
	regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa));

	return ES_OK;
}

static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
	struct pt_regs *regs = ctxt->regs;
	enum es_result ret;
	bool write;

	/* Is it a WRMSR? */
	write = ctxt->insn.opcode.bytes[1] == 0x30;

	if (regs->cx == MSR_SVSM_CAA)
		return __vc_handle_msr_caa(regs, write);

	ghcb_set_rcx(ghcb, regs->cx);
	if (write) {
		ghcb_set_rax(ghcb, regs->ax);
		ghcb_set_rdx(ghcb, regs->dx);
	}

	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, write, 0);

	if ((ret == ES_OK) && !write) {
		regs->ax = ghcb->save.rax;
		regs->dx = ghcb->save.rdx;
	}

	return ret;
}

static void snp_register_per_cpu_ghcb(void)
{
	struct sev_es_runtime_data *data;
	struct ghcb *ghcb;

	data = this_cpu_read(runtime_data);
	ghcb = &data->ghcb_page;

	snp_register_ghcb_early(__pa(ghcb));
}

void setup_ghcb(void)
{
	if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
		return;

	/*
	 * Check whether the runtime #VC exception handler is active. It uses
	 * the per-CPU GHCB page which is set up by sev_es_init_vc_handling().
	 *
	 * If SNP is active, register the per-CPU GHCB page so that the runtime
	 * exception handler can use it.
	 */
	if (initial_vc_handler == (unsigned long)kernel_exc_vmm_communication) {
		if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
			snp_register_per_cpu_ghcb();

		sev_cfg.ghcbs_initialized = true;

		return;
	}

	/*
	 * Make sure the hypervisor talks a supported protocol.
	 * This gets called only in the BSP boot phase.
	 */
	if (!sev_es_negotiate_protocol())
		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);

	/*
	 * Clear the boot_ghcb. The first exception comes in before the bss
	 * section is cleared.
	 */
	memset(&boot_ghcb_page, 0, PAGE_SIZE);

	/* Alright - Make the boot-ghcb public */
	boot_ghcb = &boot_ghcb_page;

	/* SNP guest requires that GHCB GPA must be registered. */
	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		snp_register_ghcb_early(__pa(&boot_ghcb_page));
}

#ifdef CONFIG_HOTPLUG_CPU
static void sev_es_ap_hlt_loop(void)
{
	struct ghcb_state state;
	struct ghcb *ghcb;

	ghcb = __sev_get_ghcb(&state);

	while (true) {
		vc_ghcb_invalidate(ghcb);
		ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_HLT_LOOP);
		ghcb_set_sw_exit_info_1(ghcb, 0);
		ghcb_set_sw_exit_info_2(ghcb, 0);

		sev_es_wr_ghcb_msr(__pa(ghcb));
		VMGEXIT();

		/* Wakeup signal? */
		if (ghcb_sw_exit_info_2_is_valid(ghcb) &&
		    ghcb->save.sw_exit_info_2)
			break;
	}

	__sev_put_ghcb(&state);
}

/*
 * Play_dead handler when running under SEV-ES. This is needed because
 * the hypervisor can't deliver an SIPI request to restart the AP.
 * Instead the kernel has to issue a VMGEXIT to halt the VCPU until the
 * hypervisor wakes it up again.
 */
static void sev_es_play_dead(void)
{
	play_dead_common();

	/* IRQs now disabled */

	sev_es_ap_hlt_loop();

	/*
	 * If we get here, the VCPU was woken up again. Jump to CPU
	 * startup code to get it back online.
	 */
	soft_restart_cpu();
}
#else  /* CONFIG_HOTPLUG_CPU */
#define sev_es_play_dead	native_play_dead
#endif /* CONFIG_HOTPLUG_CPU */

#ifdef CONFIG_SMP
static void __init sev_es_setup_play_dead(void)
{
	smp_ops.play_dead = sev_es_play_dead;
}
#else
static inline void sev_es_setup_play_dead(void) { }
#endif

static void __init alloc_runtime_data(int cpu)
{
	struct sev_es_runtime_data *data;

	data = memblock_alloc_node(sizeof(*data), PAGE_SIZE, cpu_to_node(cpu));
	if (!data)
		panic("Can't allocate SEV-ES runtime data");

	per_cpu(runtime_data, cpu) = data;

	if (snp_vmpl) {
		struct svsm_ca *caa;

		/* Allocate the SVSM CA page if an SVSM is present */
		caa = memblock_alloc(sizeof(*caa), PAGE_SIZE);
		if (!caa)
			panic("Can't allocate SVSM CA page\n");

		per_cpu(svsm_caa, cpu) = caa;
		per_cpu(svsm_caa_pa, cpu) = __pa(caa);
	}
}

static void __init init_ghcb(int cpu)
{
	struct sev_es_runtime_data *data;
	int err;

	data = per_cpu(runtime_data, cpu);

	err = early_set_memory_decrypted((unsigned long)&data->ghcb_page,
					 sizeof(data->ghcb_page));
	if (err)
		panic("Can't map GHCBs unencrypted");

	memset(&data->ghcb_page, 0, sizeof(data->ghcb_page));

	data->ghcb_active = false;
	data->backup_ghcb_active = false;
}

void __init sev_es_init_vc_handling(void)
{
	int cpu;

	BUILD_BUG_ON(offsetof(struct sev_es_runtime_data, ghcb_page) % PAGE_SIZE);

	if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
		return;

	if (!sev_es_check_cpu_features())
		panic("SEV-ES CPU Features missing");

	/*
	 * SNP is supported in v2 of the GHCB spec which mandates support for HV
	 * features.
	 */
	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) {
		sev_hv_features = get_hv_features();

		if (!(sev_hv_features & GHCB_HV_FT_SNP))
			sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
	}

	/* Initialize per-cpu GHCB pages */
	for_each_possible_cpu(cpu) {
		alloc_runtime_data(cpu);
		init_ghcb(cpu);
	}

	/* If running under an SVSM, switch to the per-cpu CA */
	if (snp_vmpl) {
		struct svsm_call call = {};
		unsigned long flags;
		int ret;

		local_irq_save(flags);

		/*
		 * SVSM_CORE_REMAP_CA call:
		 *   RAX = 0 (Protocol=0, CallID=0)
		 *   RCX = New CA GPA
		 */
		call.caa = svsm_get_caa();
		call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
		call.rcx = this_cpu_read(svsm_caa_pa);
		ret = svsm_perform_call_protocol(&call);
		if (ret)
			panic("Can't remap the SVSM CA, ret=%d, rax_out=0x%llx\n",
			      ret, call.rax_out);

		sev_cfg.use_cas = true;

		local_irq_restore(flags);
	}

	sev_es_setup_play_dead();

	/* Secondary CPUs use the runtime #VC handler */
	initial_vc_handler = (unsigned long)kernel_exc_vmm_communication;
}

static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt)
{
	int trapnr = ctxt->fi.vector;

	if (trapnr == X86_TRAP_PF)
		native_write_cr2(ctxt->fi.cr2);

	ctxt->regs->orig_ax = ctxt->fi.error_code;
	do_early_exception(ctxt->regs, trapnr);
}

static long *vc_insn_get_rm(struct es_em_ctxt *ctxt)
{
	long *reg_array;
	int offset;

	reg_array = (long *)ctxt->regs;
	offset    = insn_get_modrm_rm_off(&ctxt->insn, ctxt->regs);

	if (offset < 0)
		return NULL;

	offset /= sizeof(long);

	return reg_array + offset;
}
static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
				 unsigned int bytes, bool read)
{
	u64 exit_code, exit_info_1, exit_info_2;
	unsigned long ghcb_pa = __pa(ghcb);
	enum es_result res;
	phys_addr_t paddr;
	void __user *ref;

	ref = insn_get_addr_ref(&ctxt->insn, ctxt->regs);
	if (ref == (void __user *)-1L)
		return ES_UNSUPPORTED;

	exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;

	res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
	if (res != ES_OK) {
		if (res == ES_EXCEPTION && !read)
			ctxt->fi.error_code |= X86_PF_WRITE;

		return res;
	}

	exit_info_1 = paddr;
	/* Can never be greater than 8 */
	exit_info_2 = bytes;

	ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer));

	return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2);
}

/*
 * The MOVS instruction has two memory operands, which raises the
 * problem that it is not known whether the access to the source or the
 * destination caused the #VC exception (and hence whether an MMIO read
 * or write operation needs to be emulated).
 *
 * Instead of playing games with walking page-tables and trying to guess
 * whether the source or destination is an MMIO range, split the move
 * into two operations, a read and a write with only one memory operand.
 * This will cause a nested #VC exception on the MMIO address which can
 * then be handled.
 *
 * This implementation has the benefit that it also supports MOVS where
 * source _and_ destination are MMIO regions.
 *
 * It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a
 * rare operation. If it turns out to be a performance problem the split
 * operations can be moved to memcpy_fromio() and memcpy_toio().
 */
static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
					  unsigned int bytes)
{
	unsigned long ds_base, es_base;
	unsigned char *src, *dst;
	unsigned char buffer[8];
	enum es_result ret;
	bool rep;
	int off;

	ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS);
	es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);

	if (ds_base == -1L || es_base == -1L) {
		ctxt->fi.vector = X86_TRAP_GP;
		ctxt->fi.error_code = 0;
		return ES_EXCEPTION;
	}

	src = ds_base + (unsigned char *)ctxt->regs->si;
	dst = es_base + (unsigned char *)ctxt->regs->di;

	ret = vc_read_mem(ctxt, src, buffer, bytes);
	if (ret != ES_OK)
		return ret;

	ret = vc_write_mem(ctxt, dst, buffer, bytes);
	if (ret != ES_OK)
		return ret;

	if (ctxt->regs->flags & X86_EFLAGS_DF)
		off = -bytes;
	else
		off =  bytes;

	ctxt->regs->si += off;
	ctxt->regs->di += off;

	rep = insn_has_rep_prefix(&ctxt->insn);
	if (rep)
		ctxt->regs->cx -= 1;

	if (!rep || ctxt->regs->cx == 0)
		return ES_OK;
	else
		return ES_RETRY;
}

static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
	struct insn *insn = &ctxt->insn;
	enum insn_mmio_type mmio;
	unsigned int bytes = 0;
	enum es_result ret;
	u8 sign_byte;
	long *reg_data;

	mmio = insn_decode_mmio(insn, &bytes);
	if (mmio == INSN_MMIO_DECODE_FAILED)
		return ES_DECODE_FAILED;

	if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
		reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
		if (!reg_data)
			return ES_DECODE_FAILED;
	}

	if (user_mode(ctxt->regs))
		return ES_UNSUPPORTED;

	switch (mmio) {
	case INSN_MMIO_WRITE:
		memcpy(ghcb->shared_buffer, reg_data, bytes);
		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
		break;
	case INSN_MMIO_WRITE_IMM:
		memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
		break;
	case INSN_MMIO_READ:
		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
		if (ret)
			break;

		/* Zero-extend for 32-bit operation */
		if (bytes == 4)
			*reg_data = 0;

		memcpy(reg_data, ghcb->shared_buffer, bytes);
		break;
	case INSN_MMIO_READ_ZERO_EXTEND:
		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
		if (ret)
			break;

		/* Zero extend based on operand size */
		memset(reg_data, 0, insn->opnd_bytes);
		memcpy(reg_data, ghcb->shared_buffer, bytes);
		break;
	case INSN_MMIO_READ_SIGN_EXTEND:
		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
		if (ret)
			break;

		if (bytes == 1) {
			u8 *val = (u8 *)ghcb->shared_buffer;

			sign_byte = (*val & 0x80) ? 0xff : 0x00;
		} else {
			u16 *val = (u16 *)ghcb->shared_buffer;

			sign_byte = (*val & 0x8000) ? 0xff : 0x00;
		}

		/* Sign extend based on operand size */
		memset(reg_data, sign_byte, insn->opnd_bytes);
		memcpy(reg_data, ghcb->shared_buffer, bytes);
		break;
	case INSN_MMIO_MOVS:
		ret = vc_handle_mmio_movs(ctxt, bytes);
		break;
	default:
		ret = ES_UNSUPPORTED;
		break;
	}

	return ret;
}

static enum es_result vc_handle_dr7_write(struct ghcb *ghcb,
					  struct es_em_ctxt *ctxt)
{
	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
	long val, *reg = vc_insn_get_rm(ctxt);
	enum es_result ret;

	if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
		return ES_VMM_ERROR;

	if (!reg)
		return ES_DECODE_FAILED;

	val = *reg;

	/* Upper 32 bits must be written as zeroes */
	if (val >> 32) {
		ctxt->fi.vector = X86_TRAP_GP;
		ctxt->fi.error_code = 0;
		return ES_EXCEPTION;
	}

	/* Clear out other reserved bits and set bit 10 */
	val = (val & 0xffff23ffL) | BIT(10);

	/* Early non-zero writes to DR7 are not supported */
	if (!data && (val & ~DR7_RESET_VALUE))
		return ES_UNSUPPORTED;

	/* Using a value of 0 for ExitInfo1 means RAX holds the value */
	ghcb_set_rax(ghcb, val);
	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
	if (ret != ES_OK)
		return ret;

	if (data)
		data->dr7 = val;

	return ES_OK;
}

static enum es_result vc_handle_dr7_read(struct ghcb *ghcb,
					 struct es_em_ctxt *ctxt)
{
	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
	long *reg = vc_insn_get_rm(ctxt);

	if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
		return ES_VMM_ERROR;

	if (!reg)
		return ES_DECODE_FAILED;

	if (data)
		*reg = data->dr7;
	else
		*reg = DR7_RESET_VALUE;

	return ES_OK;
}

static enum es_result vc_handle_wbinvd(struct ghcb *ghcb,
				       struct es_em_ctxt *ctxt)
{
	return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0);
}

static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
	enum es_result ret;

	ghcb_set_rcx(ghcb, ctxt->regs->cx);

	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0);
	if (ret != ES_OK)
		return ret;

	if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb)))
		return ES_VMM_ERROR;

	ctxt->regs->ax = ghcb->save.rax;
	ctxt->regs->dx = ghcb->save.rdx;

	return ES_OK;
}

static enum es_result vc_handle_monitor(struct ghcb *ghcb,
					struct es_em_ctxt *ctxt)
{
	/*
	 * Treat it as a NOP and do not leak a physical address to the
	 * hypervisor.
	 */
	return ES_OK;
}

static enum es_result vc_handle_mwait(struct ghcb *ghcb,
				      struct es_em_ctxt *ctxt)
{
	/* Treat the same as MONITOR/MONITORX */
	return ES_OK;
}

static enum es_result vc_handle_vmmcall(struct ghcb *ghcb,
					struct es_em_ctxt *ctxt)
{
	enum es_result ret;

	ghcb_set_rax(ghcb, ctxt->regs->ax);
	ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0);

	if (x86_platform.hyper.sev_es_hcall_prepare)
		x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs);

	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0);
	if (ret != ES_OK)
		return ret;

	if (!ghcb_rax_is_valid(ghcb))
		return ES_VMM_ERROR;

	ctxt->regs->ax = ghcb->save.rax;

	/*
	 * Call sev_es_hcall_finish() after regs->ax is already set.
	 * This allows the hypervisor handler to overwrite it again if
	 * necessary.
	 */
	if (x86_platform.hyper.sev_es_hcall_finish &&
	    !x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs))
		return ES_VMM_ERROR;

	return ES_OK;
}

static enum es_result vc_handle_trap_ac(struct ghcb *ghcb,
					struct es_em_ctxt *ctxt)
{
	/*
	 * Calling ecx_alignment_check() directly does not work, because it
	 * enables IRQs and the GHCB is active. Forward the exception and call
	 * it later from vc_forward_exception().
	 */
	ctxt->fi.vector = X86_TRAP_AC;
	ctxt->fi.error_code = 0;
	return ES_EXCEPTION;
}

static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
					 struct ghcb *ghcb,
					 unsigned long exit_code)
{
	enum es_result result = vc_check_opcode_bytes(ctxt, exit_code);

	if (result != ES_OK)
		return result;

	switch (exit_code) {
	case SVM_EXIT_READ_DR7:
		result = vc_handle_dr7_read(ghcb, ctxt);
		break;
	case SVM_EXIT_WRITE_DR7:
		result = vc_handle_dr7_write(ghcb, ctxt);
		break;
	case SVM_EXIT_EXCP_BASE + X86_TRAP_AC:
		result = vc_handle_trap_ac(ghcb, ctxt);
		break;
	case SVM_EXIT_RDTSC:
	case SVM_EXIT_RDTSCP:
		result = vc_handle_rdtsc(ghcb, ctxt, exit_code);
		break;
	case SVM_EXIT_RDPMC:
		result = vc_handle_rdpmc(ghcb, ctxt);
		break;
	case SVM_EXIT_INVD:
		pr_err_ratelimited("#VC exception for INVD??? Seriously???\n");
		result = ES_UNSUPPORTED;
		break;
	case SVM_EXIT_CPUID:
		result = vc_handle_cpuid(ghcb, ctxt);
		break;
	case SVM_EXIT_IOIO:
		result = vc_handle_ioio(ghcb, ctxt);
		break;
	case SVM_EXIT_MSR:
		result = vc_handle_msr(ghcb, ctxt);
		break;
	case SVM_EXIT_VMMCALL:
		result = vc_handle_vmmcall(ghcb, ctxt);
		break;
	case SVM_EXIT_WBINVD:
		result = vc_handle_wbinvd(ghcb, ctxt);
		break;
	case SVM_EXIT_MONITOR:
		result = vc_handle_monitor(ghcb, ctxt);
		break;
	case SVM_EXIT_MWAIT:
		result = vc_handle_mwait(ghcb, ctxt);
		break;
	case SVM_EXIT_NPF:
		result = vc_handle_mmio(ghcb, ctxt);
		break;
	default:
		/*
		 * Unexpected #VC exception
		 */
		result = ES_UNSUPPORTED;
	}

	return result;
}

static __always_inline bool is_vc2_stack(unsigned long sp)
{
	return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
}

static __always_inline bool vc_from_invalid_context(struct pt_regs *regs)
{
	unsigned long sp, prev_sp;

	sp      = (unsigned long)regs;
	prev_sp = regs->sp;

	/*
	 * If the code was already executing on the VC2 stack when the #VC
	 * happened, let it proceed to the normal handling routine. This way the
	 * code executing on the VC2 stack can cause #VC exceptions to get handled.
	 */
	return is_vc2_stack(sp) && !is_vc2_stack(prev_sp);
}

static bool vc_raw_handle_exception(struct pt_regs *regs, unsigned long error_code)
{
	struct ghcb_state state;
	struct es_em_ctxt ctxt;
	enum es_result result;
	struct ghcb *ghcb;
	bool ret = true;

	ghcb = __sev_get_ghcb(&state);

	vc_ghcb_invalidate(ghcb);
	result = vc_init_em_ctxt(&ctxt, regs, error_code);

	if (result == ES_OK)
		result = vc_handle_exitcode(&ctxt, ghcb, error_code);

	__sev_put_ghcb(&state);

	/* Done - now check the result */
	switch (result) {
	case ES_OK:
		vc_finish_insn(&ctxt);
		break;
	case ES_UNSUPPORTED:
		pr_err_ratelimited("Unsupported exit-code 0x%02lx in #VC exception (IP: 0x%lx)\n",
				   error_code, regs->ip);
		ret = false;
		break;
	case ES_VMM_ERROR:
		pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
				   error_code, regs->ip);
		ret = false;
		break;
	case ES_DECODE_FAILED:
		pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
				   error_code, regs->ip);
		ret = false;
		break;
	case ES_EXCEPTION:
		vc_forward_exception(&ctxt);
		break;
	case ES_RETRY:
		/* Nothing to do */
		break;
	default:
		pr_emerg("Unknown result in %s():%d\n", __func__, result);
		/*
		 * Emulating the instruction which caused the #VC exception
		 * failed - can't continue so print debug information
		 */
		BUG();
	}

	return ret;
}

static __always_inline bool vc_is_db(unsigned long error_code)
{
	return error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB;
}

/*
 * Runtime #VC exception handler when raised from kernel mode. Runs in NMI mode
 * and will panic when an error happens.
 */
DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
{
	irqentry_state_t irq_state;

	/*
	 * With the current implementation it is always possible to switch to a
	 * safe stack because #VC exceptions only happen at known places, like
	 * intercepted instructions or accesses to MMIO areas/IO ports. They can
	 * also happen with code instrumentation when the hypervisor intercepts
	 * #DB, but the critical paths are forbidden to be instrumented, so #DB
	 * exceptions currently also only happen in safe places.
	 *
	 * But keep this here in case the noinstr annotations are violated due
	 * to bug elsewhere.
	 */
	if (unlikely(vc_from_invalid_context(regs))) {
		instrumentation_begin();
		panic("Can't handle #VC exception from unsupported context\n");
		instrumentation_end();
	}

	/*
	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
	 */
	if (vc_is_db(error_code)) {
		exc_debug(regs);
		return;
	}

	irq_state = irqentry_nmi_enter(regs);

	instrumentation_begin();

	if (!vc_raw_handle_exception(regs, error_code)) {
		/* Show some debug info */
		show_regs(regs);

		/* Ask hypervisor to sev_es_terminate */
		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);

		/* If that fails and we get here - just panic */
		panic("Returned from Terminate-Request to Hypervisor\n");
	}

	instrumentation_end();
	irqentry_nmi_exit(regs, irq_state);
}

/*
 * Runtime #VC exception handler when raised from user mode. Runs in IRQ mode
 * and will kill the current task with SIGBUS when an error happens.
 */
DEFINE_IDTENTRY_VC_USER(exc_vmm_communication)
{
	/*
	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
	 */
	if (vc_is_db(error_code)) {
		noist_exc_debug(regs);
		return;
	}

	irqentry_enter_from_user_mode(regs);
	instrumentation_begin();

	if (!vc_raw_handle_exception(regs, error_code)) {
		/*
		 * Do not kill the machine if user-space triggered the
		 * exception. Send SIGBUS instead and let user-space deal with
		 * it.
		 */
		force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0);
	}

	instrumentation_end();
	irqentry_exit_to_user_mode(regs);
}

bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
{
	unsigned long exit_code = regs->orig_ax;
	struct es_em_ctxt ctxt;
	enum es_result result;

	vc_ghcb_invalidate(boot_ghcb);

	result = vc_init_em_ctxt(&ctxt, regs, exit_code);
	if (result == ES_OK)
		result = vc_handle_exitcode(&ctxt, boot_ghcb, exit_code);

	/* Done - now check the result */
	switch (result) {
	case ES_OK:
		vc_finish_insn(&ctxt);
		break;
	case ES_UNSUPPORTED:
		early_printk("PANIC: Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n",
				exit_code, regs->ip);
		goto fail;
	case ES_VMM_ERROR:
		early_printk("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
				exit_code, regs->ip);
		goto fail;
	case ES_DECODE_FAILED:
		early_printk("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
				exit_code, regs->ip);
		goto fail;
	case ES_EXCEPTION:
		vc_early_forward_exception(&ctxt);
		break;
	case ES_RETRY:
		/* Nothing to do */
		break;
	default:
		BUG();
	}

	return true;

fail:
	show_regs(regs);

	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
}

/*
 * Initial set up of SNP relies on information provided by the
 * Confidential Computing blob, which can be passed to the kernel
 * in the following ways, depending on how it is booted:
 *
 * - when booted via the boot/decompress kernel:
 *   - via boot_params
 *
 * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH):
 *   - via a setup_data entry, as defined by the Linux Boot Protocol
 *
 * Scan for the blob in that order.
 */
static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
{
	struct cc_blob_sev_info *cc_info;

	/* Boot kernel would have passed the CC blob via boot_params. */
	if (bp->cc_blob_address) {
		cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address;
		goto found_cc_info;
	}

	/*
	 * If kernel was booted directly, without the use of the
	 * boot/decompression kernel, the CC blob may have been passed via
	 * setup_data instead.
	 */
	cc_info = find_cc_blob_setup_data(bp);
	if (!cc_info)
		return NULL;

found_cc_info:
	if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
		snp_abort();

	return cc_info;
}

static __head void svsm_setup(struct cc_blob_sev_info *cc_info)
{
	struct svsm_call call = {};
	int ret;
	u64 pa;

	/*
	 * Record the SVSM Calling Area address (CAA) if the guest is not
	 * running at VMPL0. The CA will be used to communicate with the
	 * SVSM to perform the SVSM services.
	 */
	if (!svsm_setup_ca(cc_info))
		return;

	/*
	 * It is very early in the boot and the kernel is running identity
	 * mapped but without having adjusted the pagetables to where the
	 * kernel was loaded (physbase), so the get the CA address using
	 * RIP-relative addressing.
	 */
	pa = (u64)&RIP_REL_REF(boot_svsm_ca_page);

	/*
	 * Switch over to the boot SVSM CA while the current CA is still
	 * addressable. There is no GHCB at this point so use the MSR protocol.
	 *
	 * SVSM_CORE_REMAP_CA call:
	 *   RAX = 0 (Protocol=0, CallID=0)
	 *   RCX = New CA GPA
	 */
	call.caa = svsm_get_caa();
	call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
	call.rcx = pa;
	ret = svsm_perform_call_protocol(&call);
	if (ret)
		panic("Can't remap the SVSM CA, ret=%d, rax_out=0x%llx\n", ret, call.rax_out);

	RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)pa;
	RIP_REL_REF(boot_svsm_caa_pa) = pa;
}

bool __head snp_init(struct boot_params *bp)
{
	struct cc_blob_sev_info *cc_info;

	if (!bp)
		return false;

	cc_info = find_cc_blob(bp);
	if (!cc_info)
		return false;

	if (cc_info->secrets_phys && cc_info->secrets_len == PAGE_SIZE)
		secrets_pa = cc_info->secrets_phys;
	else
		return false;

	setup_cpuid_table(cc_info);

	svsm_setup(cc_info);

	/*
	 * The CC blob will be used later to access the secrets page. Cache
	 * it here like the boot kernel does.
	 */
	bp->cc_blob_address = (u32)(unsigned long)cc_info;

	return true;
}

void __head __noreturn snp_abort(void)
{
	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
}

/*
 * SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are
 * enabled, as the alternative (fallback) logic for DMI probing in the legacy
 * ROM region can cause a crash since this region is not pre-validated.
 */
void __init snp_dmi_setup(void)
{
	if (efi_enabled(EFI_CONFIG_TABLES))
		dmi_setup();
}

static void dump_cpuid_table(void)
{
	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
	int i = 0;

	pr_info("count=%d reserved=0x%x reserved2=0x%llx\n",
		cpuid_table->count, cpuid_table->__reserved1, cpuid_table->__reserved2);

	for (i = 0; i < SNP_CPUID_COUNT_MAX; i++) {
		const struct snp_cpuid_fn *fn = &cpuid_table->fn[i];

		pr_info("index=%3d fn=0x%08x subfn=0x%08x: eax=0x%08x ebx=0x%08x ecx=0x%08x edx=0x%08x xcr0_in=0x%016llx xss_in=0x%016llx reserved=0x%016llx\n",
			i, fn->eax_in, fn->ecx_in, fn->eax, fn->ebx, fn->ecx,
			fn->edx, fn->xcr0_in, fn->xss_in, fn->__reserved);
	}
}

/*
 * It is useful from an auditing/testing perspective to provide an easy way
 * for the guest owner to know that the CPUID table has been initialized as
 * expected, but that initialization happens too early in boot to print any
 * sort of indicator, and there's not really any other good place to do it,
 * so do it here.
 *
 * If running as an SNP guest, report the current VM privilege level (VMPL).
 */
static int __init report_snp_info(void)
{
	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();

	if (cpuid_table->count) {
		pr_info("Using SNP CPUID table, %d entries present.\n",
			cpuid_table->count);

		if (sev_cfg.debug)
			dump_cpuid_table();
	}

	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		pr_info("SNP running at VMPL%u.\n", snp_vmpl);

	return 0;
}
arch_initcall(report_snp_info);

static void update_attest_input(struct svsm_call *call, struct svsm_attest_call *input)
{
	/* If (new) lengths have been returned, propagate them up */
	if (call->rcx_out != call->rcx)
		input->manifest_buf.len = call->rcx_out;

	if (call->rdx_out != call->rdx)
		input->certificates_buf.len = call->rdx_out;

	if (call->r8_out != call->r8)
		input->report_buf.len = call->r8_out;
}

int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call,
			      struct svsm_attest_call *input)
{
	struct svsm_attest_call *ac;
	unsigned long flags;
	u64 attest_call_pa;
	int ret;

	if (!snp_vmpl)
		return -EINVAL;

	local_irq_save(flags);

	call->caa = svsm_get_caa();

	ac = (struct svsm_attest_call *)call->caa->svsm_buffer;
	attest_call_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);

	*ac = *input;

	/*
	 * Set input registers for the request and set RDX and R8 to known
	 * values in order to detect length values being returned in them.
	 */
	call->rax = call_id;
	call->rcx = attest_call_pa;
	call->rdx = -1;
	call->r8 = -1;
	ret = svsm_perform_call_protocol(call);
	update_attest_input(call, input);

	local_irq_restore(flags);

	return ret;
}
EXPORT_SYMBOL_GPL(snp_issue_svsm_attest_req);

int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input,
			    struct snp_guest_request_ioctl *rio)
{
	struct ghcb_state state;
	struct es_em_ctxt ctxt;
	unsigned long flags;
	struct ghcb *ghcb;
	int ret;

	rio->exitinfo2 = SEV_RET_NO_FW_CALL;

	/*
	 * __sev_get_ghcb() needs to run with IRQs disabled because it is using
	 * a per-CPU GHCB.
	 */
	local_irq_save(flags);

	ghcb = __sev_get_ghcb(&state);
	if (!ghcb) {
		ret = -EIO;
		goto e_restore_irq;
	}

	vc_ghcb_invalidate(ghcb);

	if (req->exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) {
		ghcb_set_rax(ghcb, input->data_gpa);
		ghcb_set_rbx(ghcb, input->data_npages);
	}

	ret = sev_es_ghcb_hv_call(ghcb, &ctxt, req->exit_code, input->req_gpa, input->resp_gpa);
	if (ret)
		goto e_put;

	rio->exitinfo2 = ghcb->save.sw_exit_info_2;
	switch (rio->exitinfo2) {
	case 0:
		break;

	case SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_BUSY):
		ret = -EAGAIN;
		break;

	case SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN):
		/* Number of expected pages are returned in RBX */
		if (req->exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) {
			input->data_npages = ghcb_get_rbx(ghcb);
			ret = -ENOSPC;
			break;
		}
		fallthrough;
	default:
		ret = -EIO;
		break;
	}

e_put:
	__sev_put_ghcb(&state);
e_restore_irq:
	local_irq_restore(flags);

	return ret;
}
EXPORT_SYMBOL_GPL(snp_issue_guest_request);

static struct platform_device sev_guest_device = {
	.name		= "sev-guest",
	.id		= -1,
};

static int __init snp_init_platform_device(void)
{
	struct sev_guest_platform_data data;

	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		return -ENODEV;

	data.secrets_gpa = secrets_pa;
	if (platform_device_add_data(&sev_guest_device, &data, sizeof(data)))
		return -ENODEV;

	if (platform_device_register(&sev_guest_device))
		return -ENODEV;

	pr_info("SNP guest platform device initialized.\n");
	return 0;
}
device_initcall(snp_init_platform_device);

void sev_show_status(void)
{
	int i;

	pr_info("Status: ");
	for (i = 0; i < MSR_AMD64_SNP_RESV_BIT; i++) {
		if (sev_status & BIT_ULL(i)) {
			if (!sev_status_feat_names[i])
				continue;

			pr_cont("%s ", sev_status_feat_names[i]);
		}
	}
	pr_cont("\n");
}

void __init snp_update_svsm_ca(void)
{
	if (!snp_vmpl)
		return;

	/* Update the CAA to a proper kernel address */
	boot_svsm_caa = &boot_svsm_ca_page;
}

#ifdef CONFIG_SYSFS
static ssize_t vmpl_show(struct kobject *kobj,
			 struct kobj_attribute *attr, char *buf)
{
	return sysfs_emit(buf, "%d\n", snp_vmpl);
}

static struct kobj_attribute vmpl_attr = __ATTR_RO(vmpl);

static struct attribute *vmpl_attrs[] = {
	&vmpl_attr.attr,
	NULL
};

static struct attribute_group sev_attr_group = {
	.attrs = vmpl_attrs,
};

static int __init sev_sysfs_init(void)
{
	struct kobject *sev_kobj;
	struct device *dev_root;
	int ret;

	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
		return -ENODEV;

	dev_root = bus_get_dev_root(&cpu_subsys);
	if (!dev_root)
		return -ENODEV;

	sev_kobj = kobject_create_and_add("sev", &dev_root->kobj);
	put_device(dev_root);

	if (!sev_kobj)
		return -ENOMEM;

	ret = sysfs_create_group(sev_kobj, &sev_attr_group);
	if (ret)
		kobject_put(sev_kobj);

	return ret;
}
arch_initcall(sev_sysfs_init);
#endif // CONFIG_SYSFS