[PATCH v3 0/7] Remove 32-bit Xen PV guest support

[PATCH v3 0/7] Remove 32-bit Xen PV guest support

[Juergen Gross]

The long term plan has been to replace Xen PV guests by PVH. The first
victim of that plan are now 32-bit PV guests, as those are used only
rather seldom these days. Xen on x86 requires 64-bit support and with
Grub2 now supporting PVH officially since version 2.04 there is no
need to keep 32-bit PV guest support alive in the Linux kernel.
Additionally Meltdown mitigation is not available in the kernel running
as 32-bit PV guest, so dropping this mode makes sense from security
point of view, too.

Changes in V3:
- addressed comments to V2
- split patch 1 into 2 patches
- new patches 3 and 7

Changes in V2:
- rebase to 5.8 kernel
- addressed comments to V1
- new patches 3 and 4

Juergen Gross (7):
  x86/xen: remove 32-bit Xen PV guest support
  x86/xen: eliminate xen-asm_64.S
  x86/xen: drop tests for highmem in pv code
  x86/paravirt: remove 32-bit support from PARAVIRT_XXL
  x86/paravirt: cleanup paravirt macros
  x86/paravirt: use CONFIG_PARAVIRT_XXL instead of CONFIG_PARAVIRT
  x86/entry/32: revert "Fix XEN_PV build dependency"

 arch/x86/entry/entry_32.S                   | 109 +----
 arch/x86/entry/entry_64.S                   |   4 +-
 arch/x86/entry/vdso/vdso32/note.S           |  30 --
 arch/x86/entry/vdso/vdso32/vclock_gettime.c |   1 +
 arch/x86/include/asm/fixmap.h               |   2 +-
 arch/x86/include/asm/idtentry.h             |   4 +-
 arch/x86/include/asm/paravirt.h             | 107 +----
 arch/x86/include/asm/paravirt_types.h       |  21 -
 arch/x86/include/asm/pgtable-3level_types.h |   5 -
 arch/x86/include/asm/proto.h                |   2 +-
 arch/x86/include/asm/required-features.h    |   2 +-
 arch/x86/include/asm/segment.h              |   6 +-
 arch/x86/kernel/cpu/common.c                |   8 -
 arch/x86/kernel/head_32.S                   |  31 --
 arch/x86/kernel/kprobes/core.c              |   1 -
 arch/x86/kernel/kprobes/opt.c               |   1 -
 arch/x86/kernel/paravirt.c                  |  18 -
 arch/x86/kernel/paravirt_patch.c            |  17 -
 arch/x86/xen/Kconfig                        |   3 +-
 arch/x86/xen/Makefile                       |   3 +-
 arch/x86/xen/apic.c                         |  17 -
 arch/x86/xen/enlighten_pv.c                 |  78 +---
 arch/x86/xen/mmu_pv.c                       | 488 ++++----------------
 arch/x86/xen/p2m.c                          |   6 +-
 arch/x86/xen/setup.c                        |  36 +-
 arch/x86/xen/smp_pv.c                       |  18 -
 arch/x86/xen/vdso.h                         |   6 -
 arch/x86/xen/xen-asm.S                      | 193 +++++++-
 arch/x86/xen/xen-asm_32.S                   | 185 --------
 arch/x86/xen/xen-asm_64.S                   | 192 --------
 arch/x86/xen/xen-head.S                     |   6 -
 drivers/xen/Kconfig                         |   4 +-
 32 files changed, 305 insertions(+), 1299 deletions(-)
 delete mode 100644 arch/x86/xen/vdso.h
 delete mode 100644 arch/x86/xen/xen-asm_32.S
 delete mode 100644 arch/x86/xen/xen-asm_64.S

-- 
2.26.2

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

[PATCH v3 4/7] x86/paravirt: remove 32-bit support from PARAVIRT_XXL

[Juergen Gross]

The last 32-bit user of stuff under CONFIG_PARAVIRT_XXL is gone.

Remove 32-bit specific parts.

Signed-off-by: Juergen Gross <jgross@suse.com>
---
 arch/x86/entry/vdso/vdso32/vclock_gettime.c |  1 +
 arch/x86/include/asm/paravirt.h             | 92 +++------------------
 arch/x86/include/asm/paravirt_types.h       | 21 -----
 arch/x86/include/asm/pgtable-3level_types.h |  5 --
 arch/x86/include/asm/segment.h              |  4 -
 arch/x86/kernel/cpu/common.c                |  8 --
 arch/x86/kernel/kprobes/core.c              |  1 -
 arch/x86/kernel/kprobes/opt.c               |  1 -
 arch/x86/kernel/paravirt.c                  | 18 ----
 arch/x86/kernel/paravirt_patch.c            | 17 ----
 arch/x86/xen/enlighten_pv.c                 |  6 --
 11 files changed, 13 insertions(+), 161 deletions(-)

diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
index 84a4a73f77f7..283ed9d00426 100644
--- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
@@ -14,6 +14,7 @@
 #undef CONFIG_ILLEGAL_POINTER_VALUE
 #undef CONFIG_SPARSEMEM_VMEMMAP
 #undef CONFIG_NR_CPUS
+#undef CONFIG_PARAVIRT_XXL
 
 #define CONFIG_X86_32 1
 #define CONFIG_PGTABLE_LEVELS 2
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 3d2afecde50c..dedc89a07826 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -160,8 +160,6 @@ static inline void wbinvd(void)
 	PVOP_VCALL0(cpu.wbinvd);
 }
 
-#define get_kernel_rpl()  (pv_info.kernel_rpl)
-
 static inline u64 paravirt_read_msr(unsigned msr)
 {
 	return PVOP_CALL1(u64, cpu.read_msr, msr);
@@ -277,12 +275,10 @@ static inline void load_TLS(struct thread_struct *t, unsigned cpu)
 	PVOP_VCALL2(cpu.load_tls, t, cpu);
 }
 
-#ifdef CONFIG_X86_64
 static inline void load_gs_index(unsigned int gs)
 {
 	PVOP_VCALL1(cpu.load_gs_index, gs);
 }
-#endif
 
 static inline void write_ldt_entry(struct desc_struct *dt, int entry,
 				   const void *desc)
@@ -377,10 +373,7 @@ static inline pte_t __pte(pteval_t val)
 {
 	pteval_t ret;
 
-	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALLEE2(pteval_t, mmu.make_pte, val, (u64)val >> 32);
-	else
-		ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
+	ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
 
 	return (pte_t) { .pte = ret };
 }
@@ -389,11 +382,7 @@ static inline pteval_t pte_val(pte_t pte)
 {
 	pteval_t ret;
 
-	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALLEE2(pteval_t, mmu.pte_val,
-				   pte.pte, (u64)pte.pte >> 32);
-	else
-		ret = PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte);
+	ret = PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte);
 
 	return ret;
 }
@@ -402,10 +391,7 @@ static inline pgd_t __pgd(pgdval_t val)
 {
 	pgdval_t ret;
 
-	if (sizeof(pgdval_t) > sizeof(long))
-		ret = PVOP_CALLEE2(pgdval_t, mmu.make_pgd, val, (u64)val >> 32);
-	else
-		ret = PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val);
+	ret = PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val);
 
 	return (pgd_t) { ret };
 }
@@ -414,11 +400,7 @@ static inline pgdval_t pgd_val(pgd_t pgd)
 {
 	pgdval_t ret;
 
-	if (sizeof(pgdval_t) > sizeof(long))
-		ret =  PVOP_CALLEE2(pgdval_t, mmu.pgd_val,
-				    pgd.pgd, (u64)pgd.pgd >> 32);
-	else
-		ret =  PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd);
+	ret =  PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd);
 
 	return ret;
 }
@@ -438,51 +420,32 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned
 					   pte_t *ptep, pte_t old_pte, pte_t pte)
 {
 
-	if (sizeof(pteval_t) > sizeof(long))
-		/* 5 arg words */
-		pv_ops.mmu.ptep_modify_prot_commit(vma, addr, ptep, pte);
-	else
-		PVOP_VCALL4(mmu.ptep_modify_prot_commit,
-			    vma, addr, ptep, pte.pte);
+	PVOP_VCALL4(mmu.ptep_modify_prot_commit, vma, addr, ptep, pte.pte);
 }
 
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
-	if (sizeof(pteval_t) > sizeof(long))
-		PVOP_VCALL3(mmu.set_pte, ptep, pte.pte, (u64)pte.pte >> 32);
-	else
-		PVOP_VCALL2(mmu.set_pte, ptep, pte.pte);
+	PVOP_VCALL2(mmu.set_pte, ptep, pte.pte);
 }
 
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
-	if (sizeof(pteval_t) > sizeof(long))
-		/* 5 arg words */
-		pv_ops.mmu.set_pte_at(mm, addr, ptep, pte);
-	else
-		PVOP_VCALL4(mmu.set_pte_at, mm, addr, ptep, pte.pte);
+	PVOP_VCALL4(mmu.set_pte_at, mm, addr, ptep, pte.pte);
 }
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	pmdval_t val = native_pmd_val(pmd);
 
-	if (sizeof(pmdval_t) > sizeof(long))
-		PVOP_VCALL3(mmu.set_pmd, pmdp, val, (u64)val >> 32);
-	else
-		PVOP_VCALL2(mmu.set_pmd, pmdp, val);
+	PVOP_VCALL2(mmu.set_pmd, pmdp, val);
 }
 
-#if CONFIG_PGTABLE_LEVELS >= 3
 static inline pmd_t __pmd(pmdval_t val)
 {
 	pmdval_t ret;
 
-	if (sizeof(pmdval_t) > sizeof(long))
-		ret = PVOP_CALLEE2(pmdval_t, mmu.make_pmd, val, (u64)val >> 32);
-	else
-		ret = PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val);
+	ret = PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val);
 
 	return (pmd_t) { ret };
 }
@@ -491,11 +454,7 @@ static inline pmdval_t pmd_val(pmd_t pmd)
 {
 	pmdval_t ret;
 
-	if (sizeof(pmdval_t) > sizeof(long))
-		ret =  PVOP_CALLEE2(pmdval_t, mmu.pmd_val,
-				    pmd.pmd, (u64)pmd.pmd >> 32);
-	else
-		ret =  PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd);
+	ret =  PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd);
 
 	return ret;
 }
@@ -504,12 +463,9 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
 {
 	pudval_t val = native_pud_val(pud);
 
-	if (sizeof(pudval_t) > sizeof(long))
-		PVOP_VCALL3(mmu.set_pud, pudp, val, (u64)val >> 32);
-	else
-		PVOP_VCALL2(mmu.set_pud, pudp, val);
+	PVOP_VCALL2(mmu.set_pud, pudp, val);
 }
-#if CONFIG_PGTABLE_LEVELS >= 4
+
 static inline pud_t __pud(pudval_t val)
 {
 	pudval_t ret;
@@ -574,29 +530,6 @@ static inline void p4d_clear(p4d_t *p4dp)
 	set_p4d(p4dp, __p4d(0));
 }
 
-#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
-
-#endif	/* CONFIG_PGTABLE_LEVELS >= 3 */
-
-#ifdef CONFIG_X86_PAE
-/* Special-case pte-setting operations for PAE, which can't update a
-   64-bit pte atomically */
-static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	PVOP_VCALL3(mmu.set_pte_atomic, ptep, pte.pte, pte.pte >> 32);
-}
-
-static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
-			     pte_t *ptep)
-{
-	PVOP_VCALL3(mmu.pte_clear, mm, addr, ptep);
-}
-
-static inline void pmd_clear(pmd_t *pmdp)
-{
-	PVOP_VCALL1(mmu.pmd_clear, pmdp);
-}
-#else  /* !CONFIG_X86_PAE */
 static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
 {
 	set_pte(ptep, pte);
@@ -612,7 +545,6 @@ static inline void pmd_clear(pmd_t *pmdp)
 {
 	set_pmd(pmdp, __pmd(0));
 }
-#endif	/* CONFIG_X86_PAE */
 
 #define  __HAVE_ARCH_START_CONTEXT_SWITCH
 static inline void arch_start_context_switch(struct task_struct *prev)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 8dfcb2508e6d..f27c3febaa6e 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -68,12 +68,7 @@ struct paravirt_callee_save {
 /* general info */
 struct pv_info {
 #ifdef CONFIG_PARAVIRT_XXL
-	unsigned int kernel_rpl;
-	int shared_kernel_pmd;
-
-#ifdef CONFIG_X86_64
 	u16 extra_user_64bit_cs;  /* __USER_CS if none */
-#endif
 #endif
 
 	const char *name;
@@ -126,9 +121,7 @@ struct pv_cpu_ops {
 	void (*set_ldt)(const void *desc, unsigned entries);
 	unsigned long (*store_tr)(void);
 	void (*load_tls)(struct thread_struct *t, unsigned int cpu);
-#ifdef CONFIG_X86_64
 	void (*load_gs_index)(unsigned int idx);
-#endif
 	void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum,
 				const void *desc);
 	void (*write_gdt_entry)(struct desc_struct *,
@@ -264,21 +257,11 @@ struct pv_mmu_ops {
 	struct paravirt_callee_save pgd_val;
 	struct paravirt_callee_save make_pgd;
 
-#if CONFIG_PGTABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-	void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
-	void (*pte_clear)(struct mm_struct *mm, unsigned long addr,
-			  pte_t *ptep);
-	void (*pmd_clear)(pmd_t *pmdp);
-
-#endif	/* CONFIG_X86_PAE */
-
 	void (*set_pud)(pud_t *pudp, pud_t pudval);
 
 	struct paravirt_callee_save pmd_val;
 	struct paravirt_callee_save make_pmd;
 
-#if CONFIG_PGTABLE_LEVELS >= 4
 	struct paravirt_callee_save pud_val;
 	struct paravirt_callee_save make_pud;
 
@@ -291,10 +274,6 @@ struct pv_mmu_ops {
 	void (*set_pgd)(pgd_t *pgdp, pgd_t pgdval);
 #endif	/* CONFIG_PGTABLE_LEVELS >= 5 */
 
-#endif	/* CONFIG_PGTABLE_LEVELS >= 4 */
-
-#endif	/* CONFIG_PGTABLE_LEVELS >= 3 */
-
 	struct pv_lazy_ops lazy_mode;
 
 	/* dom0 ops */
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 80fbb4a9ed87..56baf43befb4 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -20,12 +20,7 @@ typedef union {
 } pte_t;
 #endif	/* !__ASSEMBLY__ */
 
-#ifdef CONFIG_PARAVIRT_XXL
-#define SHARED_KERNEL_PMD	((!static_cpu_has(X86_FEATURE_PTI) &&	\
-				 (pv_info.shared_kernel_pmd)))
-#else
 #define SHARED_KERNEL_PMD	(!static_cpu_has(X86_FEATURE_PTI))
-#endif
 
 #define ARCH_PAGE_TABLE_SYNC_MASK	(SHARED_KERNEL_PMD ? 0 : PGTBL_PMD_MODIFIED)
 
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 9646c300f128..517920928989 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -222,10 +222,6 @@
 
 #endif
 
-#ifndef CONFIG_PARAVIRT_XXL
-# define get_kernel_rpl()		0
-#endif
-
 #define IDT_ENTRIES			256
 #define NUM_EXCEPTION_VECTORS		32
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 965474d78cef..ca89cea31e81 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1412,15 +1412,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	 * ESPFIX issue, we can change this.
 	 */
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_PARAVIRT_XXL
-	do {
-		extern void native_iret(void);
-		if (pv_ops.cpu.iret == native_iret)
-			set_cpu_bug(c, X86_BUG_ESPFIX);
-	} while (0);
-# else
 	set_cpu_bug(c, X86_BUG_ESPFIX);
-# endif
 #endif
 }
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index fdadc37d72af..2ca10b770cff 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -793,7 +793,6 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 	/* fixup registers */
 	regs->cs = __KERNEL_CS;
 #ifdef CONFIG_X86_32
-	regs->cs |= get_kernel_rpl();
 	regs->gs = 0;
 #endif
 	/* We use pt_regs->sp for return address holder. */
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 40f380461e6d..b8dd113a1284 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -181,7 +181,6 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
 		/* Save skipped registers */
 		regs->cs = __KERNEL_CS;
 #ifdef CONFIG_X86_32
-		regs->cs |= get_kernel_rpl();
 		regs->gs = 0;
 #endif
 		regs->ip = (unsigned long)op->kp.addr + INT3_INSN_SIZE;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index de2138ba38e5..e56a144c13b3 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -263,13 +263,8 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 struct pv_info pv_info = {
 	.name = "bare hardware",
 #ifdef CONFIG_PARAVIRT_XXL
-	.kernel_rpl = 0,
-	.shared_kernel_pmd = 1,	/* Only used when CONFIG_X86_PAE is set */
-
-#ifdef CONFIG_X86_64
 	.extra_user_64bit_cs = __USER_CS,
 #endif
-#endif
 };
 
 /* 64-bit pagetable entries */
@@ -305,9 +300,7 @@ struct paravirt_patch_template pv_ops = {
 	.cpu.load_idt		= native_load_idt,
 	.cpu.store_tr		= native_store_tr,
 	.cpu.load_tls		= native_load_tls,
-#ifdef CONFIG_X86_64
 	.cpu.load_gs_index	= native_load_gs_index,
-#endif
 	.cpu.write_ldt_entry	= native_write_ldt_entry,
 	.cpu.write_gdt_entry	= native_write_gdt_entry,
 	.cpu.write_idt_entry	= native_write_idt_entry,
@@ -317,9 +310,7 @@ struct paravirt_patch_template pv_ops = {
 
 	.cpu.load_sp0		= native_load_sp0,
 
-#ifdef CONFIG_X86_64
 	.cpu.usergs_sysret64	= native_usergs_sysret64,
-#endif
 	.cpu.iret		= native_iret,
 	.cpu.swapgs		= native_swapgs,
 
@@ -375,18 +366,11 @@ struct paravirt_patch_template pv_ops = {
 	.mmu.ptep_modify_prot_start	= __ptep_modify_prot_start,
 	.mmu.ptep_modify_prot_commit	= __ptep_modify_prot_commit,
 
-#if CONFIG_PGTABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-	.mmu.set_pte_atomic	= native_set_pte_atomic,
-	.mmu.pte_clear		= native_pte_clear,
-	.mmu.pmd_clear		= native_pmd_clear,
-#endif
 	.mmu.set_pud		= native_set_pud,
 
 	.mmu.pmd_val		= PTE_IDENT,
 	.mmu.make_pmd		= PTE_IDENT,
 
-#if CONFIG_PGTABLE_LEVELS >= 4
 	.mmu.pud_val		= PTE_IDENT,
 	.mmu.make_pud		= PTE_IDENT,
 
@@ -398,8 +382,6 @@ struct paravirt_patch_template pv_ops = {
 
 	.mmu.set_pgd		= native_set_pgd,
 #endif /* CONFIG_PGTABLE_LEVELS >= 5 */
-#endif /* CONFIG_PGTABLE_LEVELS >= 4 */
-#endif /* CONFIG_PGTABLE_LEVELS >= 3 */
 
 	.mmu.pte_val		= PTE_IDENT,
 	.mmu.pgd_val		= PTE_IDENT,
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index 3eff63c090d2..ace6e334cb39 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -26,14 +26,10 @@ struct patch_xxl {
 	const unsigned char	mmu_read_cr3[3];
 	const unsigned char	mmu_write_cr3[3];
 	const unsigned char	irq_restore_fl[2];
-# ifdef CONFIG_X86_64
 	const unsigned char	cpu_wbinvd[2];
 	const unsigned char	cpu_usergs_sysret64[6];
 	const unsigned char	cpu_swapgs[3];
 	const unsigned char	mov64[3];
-# else
-	const unsigned char	cpu_iret[1];
-# endif
 };
 
 static const struct patch_xxl patch_data_xxl = {
@@ -42,7 +38,6 @@ static const struct patch_xxl patch_data_xxl = {
 	.irq_save_fl		= { 0x9c, 0x58 },	// pushf; pop %[re]ax
 	.mmu_read_cr2		= { 0x0f, 0x20, 0xd0 },	// mov %cr2, %[re]ax
 	.mmu_read_cr3		= { 0x0f, 0x20, 0xd8 },	// mov %cr3, %[re]ax
-# ifdef CONFIG_X86_64
 	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
 	.irq_restore_fl		= { 0x57, 0x9d },	// push %rdi; popfq
 	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
@@ -50,19 +45,11 @@ static const struct patch_xxl patch_data_xxl = {
 				    0x48, 0x0f, 0x07 },	// swapgs; sysretq
 	.cpu_swapgs		= { 0x0f, 0x01, 0xf8 },	// swapgs
 	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
-# else
-	.mmu_write_cr3		= { 0x0f, 0x22, 0xd8 },	// mov %eax, %cr3
-	.irq_restore_fl		= { 0x50, 0x9d },	// push %eax; popf
-	.cpu_iret		= { 0xcf },		// iret
-# endif
 };
 
 unsigned int paravirt_patch_ident_64(void *insn_buff, unsigned int len)
 {
-#ifdef CONFIG_X86_64
 	return PATCH(xxl, mov64, insn_buff, len);
-#endif
-	return 0;
 }
 # endif /* CONFIG_PARAVIRT_XXL */
 
@@ -98,13 +85,9 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 	PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
 	PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
 
-# ifdef CONFIG_X86_64
 	PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len);
 	PATCH_CASE(cpu, swapgs, xxl, insn_buff, len);
 	PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
-# else
-	PATCH_CASE(cpu, iret, xxl, insn_buff, len);
-# endif
 #endif
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 9fec952f84f3..b84d3d47082b 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1017,8 +1017,6 @@ void __init xen_setup_vcpu_info_placement(void)
 }
 
 static const struct pv_info xen_info __initconst = {
-	.shared_kernel_pmd = 0,
-
 	.extra_user_64bit_cs = FLAT_USER_CS64,
 	.name = "Xen",
 };
@@ -1317,10 +1315,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 				   xen_start_info->nr_pages);
 	xen_reserve_special_pages();
 
-	/* keep using Xen gdt for now; no urgent need to change it */
-
-	pv_info.kernel_rpl = 0;
-
 	/* set the limit of our address space */
 	xen_reserve_top();
 
-- 
2.26.2

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

[PATCH v3 5/7] x86/paravirt: cleanup paravirt macros

[Juergen Gross]

Some paravirt macros are no longer used, delete them.

Signed-off-by: Juergen Gross <jgross@suse.com>
---
 arch/x86/include/asm/paravirt.h | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index dedc89a07826..99da08852df0 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -614,16 +614,9 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 #endif /* SMP && PARAVIRT_SPINLOCKS */
 
 #ifdef CONFIG_X86_32
-#define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
-#define PV_RESTORE_REGS "popl %edx; popl %ecx;"
-
 /* save and restore all caller-save registers, except return value */
 #define PV_SAVE_ALL_CALLER_REGS		"pushl %ecx;"
 #define PV_RESTORE_ALL_CALLER_REGS	"popl  %ecx;"
-
-#define PV_FLAGS_ARG "0"
-#define PV_EXTRA_CLOBBERS
-#define PV_VEXTRA_CLOBBERS
 #else
 /* save and restore all caller-save registers, except return value */
 #define PV_SAVE_ALL_CALLER_REGS						\
@@ -644,14 +637,6 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 	"pop %rsi;"							\
 	"pop %rdx;"							\
 	"pop %rcx;"
-
-/* We save some registers, but all of them, that's too much. We clobber all
- * caller saved registers but the argument parameter */
-#define PV_SAVE_REGS "pushq %%rdi;"
-#define PV_RESTORE_REGS "popq %%rdi;"
-#define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx", "rsi"
-#define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx", "rsi"
-#define PV_FLAGS_ARG "D"
 #endif
 
 /*
-- 
2.26.2

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH v3 4/7] x86/paravirt: remove 32-bit support from PARAVIRT_XXL

[peterz]

On Fri, Aug 07, 2020 at 10:38:23AM +0200, Juergen Gross wrote:

> -# else
> -	const unsigned char	cpu_iret[1];
> -# endif
>  };
>  
>  static const struct patch_xxl patch_data_xxl = {
> @@ -42,7 +38,6 @@ static const struct patch_xxl patch_data_xxl = {
>  	.irq_save_fl		= { 0x9c, 0x58 },	// pushf; pop %[re]ax
>  	.mmu_read_cr2		= { 0x0f, 0x20, 0xd0 },	// mov %cr2, %[re]ax
>  	.mmu_read_cr3		= { 0x0f, 0x20, 0xd8 },	// mov %cr3, %[re]ax
> -# ifdef CONFIG_X86_64
>  	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
>  	.irq_restore_fl		= { 0x57, 0x9d },	// push %rdi; popfq
>  	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
> @@ -50,19 +45,11 @@ static const struct patch_xxl patch_data_xxl = {
>  				    0x48, 0x0f, 0x07 },	// swapgs; sysretq
>  	.cpu_swapgs		= { 0x0f, 0x01, 0xf8 },	// swapgs
>  	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
> -# else
> -	.mmu_write_cr3		= { 0x0f, 0x22, 0xd8 },	// mov %eax, %cr3
> -	.irq_restore_fl		= { 0x50, 0x9d },	// push %eax; popf
> -	.cpu_iret		= { 0xcf },		// iret
> -# endif

I was looking at x86_64 paravirt the other day and found we actually
have pv_ops.cpu.iret users there..

So we want to change the above to also patch iret on x86_64 or do we
need to fix x86_64 to not have pv-iret?
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH v3 4/7] x86/paravirt: remove 32-bit support from PARAVIRT_XXL

[Jürgen Groß]

On 07.08.20 11:39, peterz@infradead.org wrote:
> On Fri, Aug 07, 2020 at 10:38:23AM +0200, Juergen Gross wrote:
> 
>> -# else
>> -	const unsigned char	cpu_iret[1];
>> -# endif
>>   };
>>   
>>   static const struct patch_xxl patch_data_xxl = {
>> @@ -42,7 +38,6 @@ static const struct patch_xxl patch_data_xxl = {
>>   	.irq_save_fl		= { 0x9c, 0x58 },	// pushf; pop %[re]ax
>>   	.mmu_read_cr2		= { 0x0f, 0x20, 0xd0 },	// mov %cr2, %[re]ax
>>   	.mmu_read_cr3		= { 0x0f, 0x20, 0xd8 },	// mov %cr3, %[re]ax
>> -# ifdef CONFIG_X86_64
>>   	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
>>   	.irq_restore_fl		= { 0x57, 0x9d },	// push %rdi; popfq
>>   	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
>> @@ -50,19 +45,11 @@ static const struct patch_xxl patch_data_xxl = {
>>   				    0x48, 0x0f, 0x07 },	// swapgs; sysretq
>>   	.cpu_swapgs		= { 0x0f, 0x01, 0xf8 },	// swapgs
>>   	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
>> -# else
>> -	.mmu_write_cr3		= { 0x0f, 0x22, 0xd8 },	// mov %eax, %cr3
>> -	.irq_restore_fl		= { 0x50, 0x9d },	// push %eax; popf
>> -	.cpu_iret		= { 0xcf },		// iret
>> -# endif
> 
> I was looking at x86_64 paravirt the other day and found we actually
> have pv_ops.cpu.iret users there..

On x86_64 we have (without PARAVIRT_XXL):

#define INTERRUPT_RETURN        jmp native_iret

and with PARAVIRT_XXL this is basically a jmp *pv_ops.cpu.iret which
will then be patched to either jmp native_iret or jmp xen_iret.

On x86_32 INTERRUPT_RETURN was just "iret" for the non-paravirt case.
This is the reason for above dropping of the static patch data.

> So we want to change the above to also patch iret on x86_64 or do we
> need to fix x86_64 to not have pv-iret?

We want it to stay how it is. This will let both variants (PARVIRT y/n)
continue to work.


Juergen
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH v3 4/7] x86/paravirt: remove 32-bit support from PARAVIRT_XXL

[peterz]

On Fri, Aug 07, 2020 at 12:02:59PM +0200, Jürgen Groß wrote:
> On 07.08.20 11:39, peterz@infradead.org wrote:
> > On Fri, Aug 07, 2020 at 10:38:23AM +0200, Juergen Gross wrote:
> > 
> > > -# else
> > > -	const unsigned char	cpu_iret[1];
> > > -# endif
> > >   };
> > >   static const struct patch_xxl patch_data_xxl = {
> > > @@ -42,7 +38,6 @@ static const struct patch_xxl patch_data_xxl = {
> > >   	.irq_save_fl		= { 0x9c, 0x58 },	// pushf; pop %[re]ax
> > >   	.mmu_read_cr2		= { 0x0f, 0x20, 0xd0 },	// mov %cr2, %[re]ax
> > >   	.mmu_read_cr3		= { 0x0f, 0x20, 0xd8 },	// mov %cr3, %[re]ax
> > > -# ifdef CONFIG_X86_64
> > >   	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
> > >   	.irq_restore_fl		= { 0x57, 0x9d },	// push %rdi; popfq
> > >   	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
> > > @@ -50,19 +45,11 @@ static const struct patch_xxl patch_data_xxl = {
> > >   				    0x48, 0x0f, 0x07 },	// swapgs; sysretq
> > >   	.cpu_swapgs		= { 0x0f, 0x01, 0xf8 },	// swapgs
> > >   	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
> > > -# else
> > > -	.mmu_write_cr3		= { 0x0f, 0x22, 0xd8 },	// mov %eax, %cr3
> > > -	.irq_restore_fl		= { 0x50, 0x9d },	// push %eax; popf
> > > -	.cpu_iret		= { 0xcf },		// iret
> > > -# endif
> > 
> > I was looking at x86_64 paravirt the other day and found we actually
> > have pv_ops.cpu.iret users there..
> 
> On x86_64 we have (without PARAVIRT_XXL):
> 
> #define INTERRUPT_RETURN        jmp native_iret
> 
> and with PARAVIRT_XXL this is basically a jmp *pv_ops.cpu.iret which
> will then be patched to either jmp native_iret or jmp xen_iret.

Ah, okay. Clearly I didn't look hard enough. Thanks!
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH v3 4/7] x86/paravirt: remove 32-bit support from PARAVIRT_XXL

[Boris Ostrovsky]

On 8/7/20 4:38 AM, Juergen Gross wrote:
> @@ -377,10 +373,7 @@ static inline pte_t __pte(pteval_t val)
>  {
>  	pteval_t ret;
>  
> -	if (sizeof(pteval_t) > sizeof(long))
> -		ret = PVOP_CALLEE2(pteval_t, mmu.make_pte, val, (u64)val >> 32);
> -	else
> -		ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
> +	ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
>  
>  	return (pte_t) { .pte = ret };


Can this now simply return (pte_t) ret?


-boris



_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH v3 4/7] x86/paravirt: remove 32-bit support from PARAVIRT_XXL

[Jürgen Groß]

On 09.08.20 04:34, Boris Ostrovsky wrote:
> On 8/7/20 4:38 AM, Juergen Gross wrote:
>> @@ -377,10 +373,7 @@ static inline pte_t __pte(pteval_t val)
>>   {
>>   	pteval_t ret;
>>   
>> -	if (sizeof(pteval_t) > sizeof(long))
>> -		ret = PVOP_CALLEE2(pteval_t, mmu.make_pte, val, (u64)val >> 32);
>> -	else
>> -		ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
>> +	ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
>>   
>>   	return (pte_t) { .pte = ret };
> 
> 
> Can this now simply return (pte_t) ret?

I don't think so, but I can turn it into

   return native_make_pte(PVOP_CALLEE1(...));


Juergen
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH v3 4/7] x86/paravirt: remove 32-bit support from PARAVIRT_XXL

[Boris Ostrovsky]

On 8/10/20 12:39 AM, Jürgen Groß wrote:
> On 09.08.20 04:34, Boris Ostrovsky wrote:
>> On 8/7/20 4:38 AM, Juergen Gross wrote:
>>> @@ -377,10 +373,7 @@ static inline pte_t __pte(pteval_t val)
>>>   {
>>>       pteval_t ret;
>>>   -    if (sizeof(pteval_t) > sizeof(long))
>>> -        ret = PVOP_CALLEE2(pteval_t, mmu.make_pte, val, (u64)val >>
>>> 32);
>>> -    else
>>> -        ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
>>> +    ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
>>>         return (pte_t) { .pte = ret };
>>
>>
>> Can this now simply return (pte_t) ret?
>
> I don't think so, but I can turn it into
>
>   return native_make_pte(PVOP_CALLEE1(...)); 


I thought that since now this is only built for 64-bit we don't have to
worry about different pte_t definitions and can do what we do for
example, for __pgd()?


-boris


_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH v3 4/7] x86/paravirt: remove 32-bit support from PARAVIRT_XXL

[Jürgen Groß]

On 10.08.20 18:53, Boris Ostrovsky wrote:
> On 8/10/20 12:39 AM, Jürgen Groß wrote:
>> On 09.08.20 04:34, Boris Ostrovsky wrote:
>>> On 8/7/20 4:38 AM, Juergen Gross wrote:
>>>> @@ -377,10 +373,7 @@ static inline pte_t __pte(pteval_t val)
>>>>    {
>>>>        pteval_t ret;
>>>>    -    if (sizeof(pteval_t) > sizeof(long))
>>>> -        ret = PVOP_CALLEE2(pteval_t, mmu.make_pte, val, (u64)val >>
>>>> 32);
>>>> -    else
>>>> -        ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
>>>> +    ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
>>>>          return (pte_t) { .pte = ret };
>>>
>>>
>>> Can this now simply return (pte_t) ret?
>>
>> I don't think so, but I can turn it into
>>
>>    return native_make_pte(PVOP_CALLEE1(...));
> 
> 
> I thought that since now this is only built for 64-bit we don't have to
> worry about different pte_t definitions and can do what we do for
> example, for __pgd()?

Yes, I did that:

  return (pte_t) { ret };


Juergen

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization