From ab897d2013128f470240a541b31cf5e636984e71 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 22 Jan 2009 14:24:16 -0800 Subject: x86/pvops: remove pte_flags pvop pte_flags() was introduced as a new pvop in order to extract just the flags portion of a pte, which is a potentially cheaper operation than extracting the page number as well. It turns out this operation is not needed, because simply using a mask to extract the flags from a pte is sufficient for all current users. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- arch/x86/kernel/paravirt.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel/paravirt.c') diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index e4c8fb608873..202514be5923 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -435,7 +435,6 @@ struct pv_mmu_ops pv_mmu_ops = { #endif /* PAGETABLE_LEVELS >= 3 */ .pte_val = native_pte_val, - .pte_flags = native_pte_flags, .pgd_val = native_pgd_val, .make_pte = native_make_pte, -- cgit v1.2.1 From 41edafdb78feac1d1f8823846209975fde990633 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 28 Jan 2009 14:35:02 -0800 Subject: x86/pvops: add a paravirt_ident functions to allow special patching Impact: Optimization Several paravirt ops implementations simply return their arguments, the most obvious being the make_pte/pte_val class of operations on native. On 32-bit, the identity function is literally a no-op, as the calling convention uses the same registers for the first argument and return. On 64-bit, it can be implemented with a single "mov". This patch adds special identity functions for 32 and 64 bit argument, and machinery to recognize them and replace them with either nops or a mov as appropriate. At the moment, the only users for the identity functions are the pagetable entry conversion functions. The result is a measureable improvement on pagetable-heavy benchmarks (2-3%, reducing the pvops overhead from 5 to 2%). Signed-off-by: Jeremy Fitzhardinge Signed-off-by: H. Peter Anvin --- arch/x86/kernel/paravirt.c | 75 ++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 66 insertions(+), 9 deletions(-) (limited to 'arch/x86/kernel/paravirt.c') diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 202514be5923..dd25e2b1593b 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -44,6 +44,17 @@ void _paravirt_nop(void) { } +/* identity function, which can be inlined */ +u32 _paravirt_ident_32(u32 x) +{ + return x; +} + +u64 _paravirt_ident_64(u64 x) +{ + return x; +} + static void __init default_banner(void) { printk(KERN_INFO "Booting paravirtualized kernel on %s\n", @@ -138,9 +149,16 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, if (opfunc == NULL) /* If there's no function, patch it with a ud2a (BUG) */ ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a)); - else if (opfunc == paravirt_nop) + else if (opfunc == _paravirt_nop) /* If the operation is a nop, then nop the callsite */ ret = paravirt_patch_nop(); + + /* identity functions just return their single argument */ + else if (opfunc == _paravirt_ident_32) + ret = paravirt_patch_ident_32(insnbuf, len); + else if (opfunc == _paravirt_ident_64) + ret = paravirt_patch_ident_64(insnbuf, len); + else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || @@ -373,6 +391,45 @@ struct pv_apic_ops pv_apic_ops = { #endif }; +typedef pte_t make_pte_t(pteval_t); +typedef pmd_t make_pmd_t(pmdval_t); +typedef pud_t make_pud_t(pudval_t); +typedef pgd_t make_pgd_t(pgdval_t); + +typedef pteval_t pte_val_t(pte_t); +typedef pmdval_t pmd_val_t(pmd_t); +typedef pudval_t pud_val_t(pud_t); +typedef pgdval_t pgd_val_t(pgd_t); + + +#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE) +/* 32-bit pagetable entries */ +#define paravirt_native_make_pte (make_pte_t *)_paravirt_ident_32 +#define paravirt_native_pte_val (pte_val_t *)_paravirt_ident_32 + +#define paravirt_native_make_pmd (make_pmd_t *)_paravirt_ident_32 +#define paravirt_native_pmd_val (pmd_val_t *)_paravirt_ident_32 + +#define paravirt_native_make_pud (make_pud_t *)_paravirt_ident_32 +#define paravirt_native_pud_val (pud_val_t *)_paravirt_ident_32 + +#define paravirt_native_make_pgd (make_pgd_t *)_paravirt_ident_32 +#define paravirt_native_pgd_val (pgd_val_t *)_paravirt_ident_32 +#else +/* 64-bit pagetable entries */ +#define paravirt_native_make_pte (make_pte_t *)_paravirt_ident_64 +#define paravirt_native_pte_val (pte_val_t *)_paravirt_ident_64 + +#define paravirt_native_make_pmd (make_pmd_t *)_paravirt_ident_64 +#define paravirt_native_pmd_val (pmd_val_t *)_paravirt_ident_64 + +#define paravirt_native_make_pud (make_pud_t *)_paravirt_ident_64 +#define paravirt_native_pud_val (pud_val_t *)_paravirt_ident_64 + +#define paravirt_native_make_pgd (make_pgd_t *)_paravirt_ident_64 +#define paravirt_native_pgd_val (pgd_val_t *)_paravirt_ident_64 +#endif + struct pv_mmu_ops pv_mmu_ops = { #ifndef CONFIG_X86_64 .pagetable_setup_start = native_pagetable_setup_start, @@ -424,21 +481,21 @@ struct pv_mmu_ops pv_mmu_ops = { .pmd_clear = native_pmd_clear, #endif .set_pud = native_set_pud, - .pmd_val = native_pmd_val, - .make_pmd = native_make_pmd, + .pmd_val = paravirt_native_pmd_val, + .make_pmd = paravirt_native_make_pmd, #if PAGETABLE_LEVELS == 4 - .pud_val = native_pud_val, - .make_pud = native_make_pud, + .pud_val = paravirt_native_pud_val, + .make_pud = paravirt_native_make_pud, .set_pgd = native_set_pgd, #endif #endif /* PAGETABLE_LEVELS >= 3 */ - .pte_val = native_pte_val, - .pgd_val = native_pgd_val, + .pte_val = paravirt_native_pte_val, + .pgd_val = paravirt_native_pgd_val, - .make_pte = native_make_pte, - .make_pgd = native_make_pgd, + .make_pte = paravirt_native_make_pte, + .make_pgd = paravirt_native_make_pgd, .dup_mmap = paravirt_nop, .exit_mmap = paravirt_nop, -- cgit v1.2.1 From ecb93d1ccd0aac63f03be2db3cac3fa974716f4c Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 28 Jan 2009 14:35:05 -0800 Subject: x86/paravirt: add register-saving thunks to reduce caller register pressure Impact: Optimization One of the problems with inserting a pile of C calls where previously there were none is that the register pressure is greatly increased. The C calling convention says that the caller must expect a certain set of registers may be trashed by the callee, and that the callee can use those registers without restriction. This includes the function argument registers, and several others. This patch seeks to alleviate this pressure by introducing wrapper thunks that will do the register saving/restoring, so that the callsite doesn't need to worry about it, but the callee function can be conventional compiler-generated code. In many cases (particularly performance-sensitive cases) the callee will be in assembler anyway, and need not use the compiler's calling convention. Standard calling convention is: arguments return scratch x86-32 eax edx ecx eax ? x86-64 rdi rsi rdx rcx rax r8 r9 r10 r11 The thunk preserves all argument and scratch registers. The return register is not preserved, and is available as a scratch register for unwrapped callee code (and of course the return value). Wrapped function pointers are themselves wrapped in a struct paravirt_callee_save structure, in order to get some warning from the compiler when functions with mismatched calling conventions are used. The most common paravirt ops, both statically and dynamically, are interrupt enable/disable/save/restore, so handle them first. This is particularly easy since their calls are handled specially anyway. XXX Deal with VMI. What's their calling convention? Signed-off-by: H. Peter Anvin --- arch/x86/kernel/paravirt.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel/paravirt.c') diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index dd25e2b1593b..8adb6b5aa421 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -310,10 +310,10 @@ struct pv_time_ops pv_time_ops = { struct pv_irq_ops pv_irq_ops = { .init_IRQ = native_init_IRQ, - .save_fl = native_save_fl, - .restore_fl = native_restore_fl, - .irq_disable = native_irq_disable, - .irq_enable = native_irq_enable, + .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), + .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl), + .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), + .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), .safe_halt = native_safe_halt, .halt = native_halt, #ifdef CONFIG_X86_64 -- cgit v1.2.1 From da5de7c22eb705be709a57e486e7475a6969b994 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 28 Jan 2009 14:35:07 -0800 Subject: x86/paravirt: use callee-saved convention for pte_val/make_pte/etc Impact: Optimization In the native case, pte_val, make_pte, etc are all just identity functions, so there's no need to clobber a lot of registers over them. (This changes the 32-bit callee-save calling convention to return both EAX and EDX so functions can return 64-bit values.) Signed-off-by: Jeremy Fitzhardinge Signed-off-by: H. Peter Anvin --- arch/x86/kernel/paravirt.c | 53 +++++++++++----------------------------------- 1 file changed, 12 insertions(+), 41 deletions(-) (limited to 'arch/x86/kernel/paravirt.c') diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 8adb6b5aa421..cea11c8e3049 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -391,43 +391,12 @@ struct pv_apic_ops pv_apic_ops = { #endif }; -typedef pte_t make_pte_t(pteval_t); -typedef pmd_t make_pmd_t(pmdval_t); -typedef pud_t make_pud_t(pudval_t); -typedef pgd_t make_pgd_t(pgdval_t); - -typedef pteval_t pte_val_t(pte_t); -typedef pmdval_t pmd_val_t(pmd_t); -typedef pudval_t pud_val_t(pud_t); -typedef pgdval_t pgd_val_t(pgd_t); - - #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE) /* 32-bit pagetable entries */ -#define paravirt_native_make_pte (make_pte_t *)_paravirt_ident_32 -#define paravirt_native_pte_val (pte_val_t *)_paravirt_ident_32 - -#define paravirt_native_make_pmd (make_pmd_t *)_paravirt_ident_32 -#define paravirt_native_pmd_val (pmd_val_t *)_paravirt_ident_32 - -#define paravirt_native_make_pud (make_pud_t *)_paravirt_ident_32 -#define paravirt_native_pud_val (pud_val_t *)_paravirt_ident_32 - -#define paravirt_native_make_pgd (make_pgd_t *)_paravirt_ident_32 -#define paravirt_native_pgd_val (pgd_val_t *)_paravirt_ident_32 +#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32) #else /* 64-bit pagetable entries */ -#define paravirt_native_make_pte (make_pte_t *)_paravirt_ident_64 -#define paravirt_native_pte_val (pte_val_t *)_paravirt_ident_64 - -#define paravirt_native_make_pmd (make_pmd_t *)_paravirt_ident_64 -#define paravirt_native_pmd_val (pmd_val_t *)_paravirt_ident_64 - -#define paravirt_native_make_pud (make_pud_t *)_paravirt_ident_64 -#define paravirt_native_pud_val (pud_val_t *)_paravirt_ident_64 - -#define paravirt_native_make_pgd (make_pgd_t *)_paravirt_ident_64 -#define paravirt_native_pgd_val (pgd_val_t *)_paravirt_ident_64 +#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64) #endif struct pv_mmu_ops pv_mmu_ops = { @@ -481,21 +450,23 @@ struct pv_mmu_ops pv_mmu_ops = { .pmd_clear = native_pmd_clear, #endif .set_pud = native_set_pud, - .pmd_val = paravirt_native_pmd_val, - .make_pmd = paravirt_native_make_pmd, + + .pmd_val = PTE_IDENT, + .make_pmd = PTE_IDENT, #if PAGETABLE_LEVELS == 4 - .pud_val = paravirt_native_pud_val, - .make_pud = paravirt_native_make_pud, + .pud_val = PTE_IDENT, + .make_pud = PTE_IDENT, + .set_pgd = native_set_pgd, #endif #endif /* PAGETABLE_LEVELS >= 3 */ - .pte_val = paravirt_native_pte_val, - .pgd_val = paravirt_native_pgd_val, + .pte_val = PTE_IDENT, + .pgd_val = PTE_IDENT, - .make_pte = paravirt_native_make_pte, - .make_pgd = paravirt_native_make_pgd, + .make_pte = PTE_IDENT, + .make_pgd = PTE_IDENT, .dup_mmap = paravirt_nop, .exit_mmap = paravirt_nop, -- cgit v1.2.1 From 8e6dafd6c741cd4679b4de3c5d9698851e4fa59c Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 23 Feb 2009 00:34:39 +0100 Subject: x86: refactor x86_quirks support Impact: cleanup Make x86_quirks support more transparent. The highlevel methods are now named: extern void x86_quirk_pre_intr_init(void); extern void x86_quirk_intr_init(void); extern void x86_quirk_trap_init(void); extern void x86_quirk_pre_time_init(void); extern void x86_quirk_time_init(void); This makes it clear that if some platform extension has to do something here that it is considered ... weird, and is discouraged. Also remove arch_hooks.h and move it into setup.h (and other header files where appropriate). Signed-off-by: Ingo Molnar --- arch/x86/kernel/paravirt.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel/paravirt.c') diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 6dc4dca255e4..63dd358d8ee1 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.1