On Fri, Jun 19, 2015 at 01:23:46PM +0100, Alex Bennée wrote: > This is a pre-cursor to sharing the code with the guest debug support. > This replaces the big macro that fishes data out of a fixed location > with a more general helper macro to restore a set of debug registers. It > uses macro substitution so it can be re-used for debug control and value > registers. It does however rely on the debug registers being 64 bit > aligned (as they happen to be in the hyp ABI). > > Signed-off-by: Alex Bennée <alex.bennee@xxxxxxxxxx> > > --- > v3: > - return to the patch series > - add save and restore targets > - change register use and document > v4: > - keep original setup/restore names > - don't use split u32/u64 structure yet > v6: > - fix ws and clobber info in hyp.S > --- > arch/arm64/kvm/hyp.S | 517 ++++++++++++++------------------------------------- > 1 file changed, 138 insertions(+), 379 deletions(-) > > diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S > index 74e63d8..ee7f649 100644 > --- a/arch/arm64/kvm/hyp.S > +++ b/arch/arm64/kvm/hyp.S > @@ -228,199 +228,52 @@ > stp x24, x25, [x3, #160] > .endm > > -.macro save_debug > - // x2: base address for cpu context > - // x3: tmp register > - > - mrs x26, id_aa64dfr0_el1 > - ubfx x24, x26, #12, #4 // Extract BRPs > - ubfx x25, x26, #20, #4 // Extract WRPs > - mov w26, #15 > - sub w24, w26, w24 // How many BPs to skip > - sub w25, w26, w25 // How many WPs to skip > - > - add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1) > - > - adr x26, 1f > - add x26, x26, x24, lsl #2 > - br x26 > -1: > - mrs x20, dbgbcr15_el1 > - mrs x19, dbgbcr14_el1 > - mrs x18, dbgbcr13_el1 > - mrs x17, dbgbcr12_el1 > - mrs x16, dbgbcr11_el1 > - mrs x15, dbgbcr10_el1 > - mrs x14, dbgbcr9_el1 > - mrs x13, dbgbcr8_el1 > - mrs x12, dbgbcr7_el1 > - mrs x11, dbgbcr6_el1 > - mrs x10, dbgbcr5_el1 > - mrs x9, dbgbcr4_el1 > - mrs x8, dbgbcr3_el1 > - mrs x7, dbgbcr2_el1 > - mrs x6, dbgbcr1_el1 > - mrs x5, dbgbcr0_el1 > - > - adr x26, 1f > - add x26, x26, x24, lsl #2 > - br x26 > - > -1: > - str x20, [x3, #(15 * 8)] > - str x19, [x3, #(14 * 8)] > - str x18, [x3, #(13 * 8)] > - str x17, [x3, #(12 * 8)] > - str x16, [x3, #(11 * 8)] > - str x15, [x3, #(10 * 8)] > - str x14, [x3, #(9 * 8)] > - str x13, [x3, #(8 * 8)] > - str x12, [x3, #(7 * 8)] > - str x11, [x3, #(6 * 8)] > - str x10, [x3, #(5 * 8)] > - str x9, [x3, #(4 * 8)] > - str x8, [x3, #(3 * 8)] > - str x7, [x3, #(2 * 8)] > - str x6, [x3, #(1 * 8)] > - str x5, [x3, #(0 * 8)] > - > - add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1) > - > - adr x26, 1f > - add x26, x26, x24, lsl #2 > - br x26 > -1: > - mrs x20, dbgbvr15_el1 > - mrs x19, dbgbvr14_el1 > - mrs x18, dbgbvr13_el1 > - mrs x17, dbgbvr12_el1 > - mrs x16, dbgbvr11_el1 > - mrs x15, dbgbvr10_el1 > - mrs x14, dbgbvr9_el1 > - mrs x13, dbgbvr8_el1 > - mrs x12, dbgbvr7_el1 > - mrs x11, dbgbvr6_el1 > - mrs x10, dbgbvr5_el1 > - mrs x9, dbgbvr4_el1 > - mrs x8, dbgbvr3_el1 > - mrs x7, dbgbvr2_el1 > - mrs x6, dbgbvr1_el1 > - mrs x5, dbgbvr0_el1 > - > - adr x26, 1f > - add x26, x26, x24, lsl #2 > - br x26 > - > -1: > - str x20, [x3, #(15 * 8)] > - str x19, [x3, #(14 * 8)] > - str x18, [x3, #(13 * 8)] > - str x17, [x3, #(12 * 8)] > - str x16, [x3, #(11 * 8)] > - str x15, [x3, #(10 * 8)] > - str x14, [x3, #(9 * 8)] > - str x13, [x3, #(8 * 8)] > - str x12, [x3, #(7 * 8)] > - str x11, [x3, #(6 * 8)] > - str x10, [x3, #(5 * 8)] > - str x9, [x3, #(4 * 8)] > - str x8, [x3, #(3 * 8)] > - str x7, [x3, #(2 * 8)] > - str x6, [x3, #(1 * 8)] > - str x5, [x3, #(0 * 8)] > - > - add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1) > - > - adr x26, 1f > - add x26, x26, x25, lsl #2 > - br x26 > +.macro save_debug type > + // x4: pointer to register set > + // x5: number of registers to skip > + // x6..x22 trashed > + > + adr x22, 1f > + add x22, x22, x5, lsl #2 > + br x22 > 1: > - mrs x20, dbgwcr15_el1 > - mrs x19, dbgwcr14_el1 > - mrs x18, dbgwcr13_el1 > - mrs x17, dbgwcr12_el1 > - mrs x16, dbgwcr11_el1 > - mrs x15, dbgwcr10_el1 > - mrs x14, dbgwcr9_el1 > - mrs x13, dbgwcr8_el1 > - mrs x12, dbgwcr7_el1 > - mrs x11, dbgwcr6_el1 > - mrs x10, dbgwcr5_el1 > - mrs x9, dbgwcr4_el1 > - mrs x8, dbgwcr3_el1 > - mrs x7, dbgwcr2_el1 > - mrs x6, dbgwcr1_el1 > - mrs x5, dbgwcr0_el1 > - > - adr x26, 1f > - add x26, x26, x25, lsl #2 > - br x26 > - > -1: > - str x20, [x3, #(15 * 8)] > - str x19, [x3, #(14 * 8)] > - str x18, [x3, #(13 * 8)] > - str x17, [x3, #(12 * 8)] > - str x16, [x3, #(11 * 8)] > - str x15, [x3, #(10 * 8)] > - str x14, [x3, #(9 * 8)] > - str x13, [x3, #(8 * 8)] > - str x12, [x3, #(7 * 8)] > - str x11, [x3, #(6 * 8)] > - str x10, [x3, #(5 * 8)] > - str x9, [x3, #(4 * 8)] > - str x8, [x3, #(3 * 8)] > - str x7, [x3, #(2 * 8)] > - str x6, [x3, #(1 * 8)] > - str x5, [x3, #(0 * 8)] > - > - add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1) > - > - adr x26, 1f > - add x26, x26, x25, lsl #2 > - br x26 > + mrs x21, \type\()15_el1 > + mrs x20, \type\()14_el1 > + mrs x19, \type\()13_el1 > + mrs x18, \type\()12_el1 > + mrs x17, \type\()11_el1 > + mrs x16, \type\()10_el1 > + mrs x15, \type\()9_el1 > + mrs x14, \type\()8_el1 > + mrs x13, \type\()7_el1 > + mrs x12, \type\()6_el1 > + mrs x11, \type\()5_el1 > + mrs x10, \type\()4_el1 > + mrs x9, \type\()3_el1 > + mrs x8, \type\()2_el1 > + mrs x7, \type\()1_el1 > + mrs x6, \type\()0_el1 > + > + adr x22, 1f > + add x22, x22, x5, lsl #2 > + br x22 > 1: > - mrs x20, dbgwvr15_el1 > - mrs x19, dbgwvr14_el1 > - mrs x18, dbgwvr13_el1 > - mrs x17, dbgwvr12_el1 > - mrs x16, dbgwvr11_el1 > - mrs x15, dbgwvr10_el1 > - mrs x14, dbgwvr9_el1 > - mrs x13, dbgwvr8_el1 > - mrs x12, dbgwvr7_el1 > - mrs x11, dbgwvr6_el1 > - mrs x10, dbgwvr5_el1 > - mrs x9, dbgwvr4_el1 > - mrs x8, dbgwvr3_el1 > - mrs x7, dbgwvr2_el1 > - mrs x6, dbgwvr1_el1 > - mrs x5, dbgwvr0_el1 > - > - adr x26, 1f > - add x26, x26, x25, lsl #2 > - br x26 > - > -1: > - str x20, [x3, #(15 * 8)] > - str x19, [x3, #(14 * 8)] > - str x18, [x3, #(13 * 8)] > - str x17, [x3, #(12 * 8)] > - str x16, [x3, #(11 * 8)] > - str x15, [x3, #(10 * 8)] > - str x14, [x3, #(9 * 8)] > - str x13, [x3, #(8 * 8)] > - str x12, [x3, #(7 * 8)] > - str x11, [x3, #(6 * 8)] > - str x10, [x3, #(5 * 8)] > - str x9, [x3, #(4 * 8)] > - str x8, [x3, #(3 * 8)] > - str x7, [x3, #(2 * 8)] > - str x6, [x3, #(1 * 8)] > - str x5, [x3, #(0 * 8)] > - > - mrs x21, mdccint_el1 > - str x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] > + str x21, [x4, #(15 * 8)] > + str x20, [x4, #(14 * 8)] > + str x19, [x4, #(13 * 8)] > + str x18, [x4, #(12 * 8)] > + str x17, [x4, #(11 * 8)] > + str x16, [x4, #(10 * 8)] > + str x15, [x4, #(9 * 8)] > + str x14, [x4, #(8 * 8)] > + str x13, [x4, #(7 * 8)] > + str x12, [x4, #(6 * 8)] > + str x11, [x4, #(5 * 8)] > + str x10, [x4, #(4 * 8)] > + str x9, [x4, #(3 * 8)] > + str x8, [x4, #(2 * 8)] > + str x7, [x4, #(1 * 8)] > + str x6, [x4, #(0 * 8)] > .endm > > .macro restore_sysregs > @@ -465,195 +318,52 @@ > msr mdscr_el1, x25 > .endm > > -.macro restore_debug > - // x2: base address for cpu context > - // x3: tmp register > - > - mrs x26, id_aa64dfr0_el1 > - ubfx x24, x26, #12, #4 // Extract BRPs > - ubfx x25, x26, #20, #4 // Extract WRPs > - mov w26, #15 > - sub w24, w26, w24 // How many BPs to skip > - sub w25, w26, w25 // How many WPs to skip > - > - add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1) > +.macro restore_debug type > + // x4: pointer to register set > + // x5: number of registers to skip there's a white space issue here, should be tabs instead of spaces. We can probably fix while applying, if there's no need to respin. > + // x6..x22 trashed > > - adr x26, 1f > - add x26, x26, x24, lsl #2 > - br x26 > + adr x22, 1f > + add x22, x22, x5, lsl #2 > + br x22 > 1: > - ldr x20, [x3, #(15 * 8)] > - ldr x19, [x3, #(14 * 8)] > - ldr x18, [x3, #(13 * 8)] > - ldr x17, [x3, #(12 * 8)] > - ldr x16, [x3, #(11 * 8)] > - ldr x15, [x3, #(10 * 8)] > - ldr x14, [x3, #(9 * 8)] > - ldr x13, [x3, #(8 * 8)] > - ldr x12, [x3, #(7 * 8)] > - ldr x11, [x3, #(6 * 8)] > - ldr x10, [x3, #(5 * 8)] > - ldr x9, [x3, #(4 * 8)] > - ldr x8, [x3, #(3 * 8)] > - ldr x7, [x3, #(2 * 8)] > - ldr x6, [x3, #(1 * 8)] > - ldr x5, [x3, #(0 * 8)] > - > - adr x26, 1f > - add x26, x26, x24, lsl #2 > - br x26 > + ldr x21, [x4, #(15 * 8)] > + ldr x20, [x4, #(14 * 8)] > + ldr x19, [x4, #(13 * 8)] > + ldr x18, [x4, #(12 * 8)] > + ldr x17, [x4, #(11 * 8)] > + ldr x16, [x4, #(10 * 8)] > + ldr x15, [x4, #(9 * 8)] > + ldr x14, [x4, #(8 * 8)] > + ldr x13, [x4, #(7 * 8)] > + ldr x12, [x4, #(6 * 8)] > + ldr x11, [x4, #(5 * 8)] > + ldr x10, [x4, #(4 * 8)] > + ldr x9, [x4, #(3 * 8)] > + ldr x8, [x4, #(2 * 8)] > + ldr x7, [x4, #(1 * 8)] > + ldr x6, [x4, #(0 * 8)] > + > + adr x22, 1f > + add x22, x22, x5, lsl #2 > + br x22 > 1: > - msr dbgbcr15_el1, x20 > - msr dbgbcr14_el1, x19 > - msr dbgbcr13_el1, x18 > - msr dbgbcr12_el1, x17 > - msr dbgbcr11_el1, x16 > - msr dbgbcr10_el1, x15 > - msr dbgbcr9_el1, x14 > - msr dbgbcr8_el1, x13 > - msr dbgbcr7_el1, x12 > - msr dbgbcr6_el1, x11 > - msr dbgbcr5_el1, x10 > - msr dbgbcr4_el1, x9 > - msr dbgbcr3_el1, x8 > - msr dbgbcr2_el1, x7 > - msr dbgbcr1_el1, x6 > - msr dbgbcr0_el1, x5 > - > - add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1) > - > - adr x26, 1f > - add x26, x26, x24, lsl #2 > - br x26 > -1: > - ldr x20, [x3, #(15 * 8)] > - ldr x19, [x3, #(14 * 8)] > - ldr x18, [x3, #(13 * 8)] > - ldr x17, [x3, #(12 * 8)] > - ldr x16, [x3, #(11 * 8)] > - ldr x15, [x3, #(10 * 8)] > - ldr x14, [x3, #(9 * 8)] > - ldr x13, [x3, #(8 * 8)] > - ldr x12, [x3, #(7 * 8)] > - ldr x11, [x3, #(6 * 8)] > - ldr x10, [x3, #(5 * 8)] > - ldr x9, [x3, #(4 * 8)] > - ldr x8, [x3, #(3 * 8)] > - ldr x7, [x3, #(2 * 8)] > - ldr x6, [x3, #(1 * 8)] > - ldr x5, [x3, #(0 * 8)] > - > - adr x26, 1f > - add x26, x26, x24, lsl #2 > - br x26 > -1: > - msr dbgbvr15_el1, x20 > - msr dbgbvr14_el1, x19 > - msr dbgbvr13_el1, x18 > - msr dbgbvr12_el1, x17 > - msr dbgbvr11_el1, x16 > - msr dbgbvr10_el1, x15 > - msr dbgbvr9_el1, x14 > - msr dbgbvr8_el1, x13 > - msr dbgbvr7_el1, x12 > - msr dbgbvr6_el1, x11 > - msr dbgbvr5_el1, x10 > - msr dbgbvr4_el1, x9 > - msr dbgbvr3_el1, x8 > - msr dbgbvr2_el1, x7 > - msr dbgbvr1_el1, x6 > - msr dbgbvr0_el1, x5 > - > - add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1) > - > - adr x26, 1f > - add x26, x26, x25, lsl #2 > - br x26 > -1: > - ldr x20, [x3, #(15 * 8)] > - ldr x19, [x3, #(14 * 8)] > - ldr x18, [x3, #(13 * 8)] > - ldr x17, [x3, #(12 * 8)] > - ldr x16, [x3, #(11 * 8)] > - ldr x15, [x3, #(10 * 8)] > - ldr x14, [x3, #(9 * 8)] > - ldr x13, [x3, #(8 * 8)] > - ldr x12, [x3, #(7 * 8)] > - ldr x11, [x3, #(6 * 8)] > - ldr x10, [x3, #(5 * 8)] > - ldr x9, [x3, #(4 * 8)] > - ldr x8, [x3, #(3 * 8)] > - ldr x7, [x3, #(2 * 8)] > - ldr x6, [x3, #(1 * 8)] > - ldr x5, [x3, #(0 * 8)] > - > - adr x26, 1f > - add x26, x26, x25, lsl #2 > - br x26 > -1: > - msr dbgwcr15_el1, x20 > - msr dbgwcr14_el1, x19 > - msr dbgwcr13_el1, x18 > - msr dbgwcr12_el1, x17 > - msr dbgwcr11_el1, x16 > - msr dbgwcr10_el1, x15 > - msr dbgwcr9_el1, x14 > - msr dbgwcr8_el1, x13 > - msr dbgwcr7_el1, x12 > - msr dbgwcr6_el1, x11 > - msr dbgwcr5_el1, x10 > - msr dbgwcr4_el1, x9 > - msr dbgwcr3_el1, x8 > - msr dbgwcr2_el1, x7 > - msr dbgwcr1_el1, x6 > - msr dbgwcr0_el1, x5 > - > - add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1) > - > - adr x26, 1f > - add x26, x26, x25, lsl #2 > - br x26 > -1: > - ldr x20, [x3, #(15 * 8)] > - ldr x19, [x3, #(14 * 8)] > - ldr x18, [x3, #(13 * 8)] > - ldr x17, [x3, #(12 * 8)] > - ldr x16, [x3, #(11 * 8)] > - ldr x15, [x3, #(10 * 8)] > - ldr x14, [x3, #(9 * 8)] > - ldr x13, [x3, #(8 * 8)] > - ldr x12, [x3, #(7 * 8)] > - ldr x11, [x3, #(6 * 8)] > - ldr x10, [x3, #(5 * 8)] > - ldr x9, [x3, #(4 * 8)] > - ldr x8, [x3, #(3 * 8)] > - ldr x7, [x3, #(2 * 8)] > - ldr x6, [x3, #(1 * 8)] > - ldr x5, [x3, #(0 * 8)] > - > - adr x26, 1f > - add x26, x26, x25, lsl #2 > - br x26 > -1: > - msr dbgwvr15_el1, x20 > - msr dbgwvr14_el1, x19 > - msr dbgwvr13_el1, x18 > - msr dbgwvr12_el1, x17 > - msr dbgwvr11_el1, x16 > - msr dbgwvr10_el1, x15 > - msr dbgwvr9_el1, x14 > - msr dbgwvr8_el1, x13 > - msr dbgwvr7_el1, x12 > - msr dbgwvr6_el1, x11 > - msr dbgwvr5_el1, x10 > - msr dbgwvr4_el1, x9 > - msr dbgwvr3_el1, x8 > - msr dbgwvr2_el1, x7 > - msr dbgwvr1_el1, x6 > - msr dbgwvr0_el1, x5 > - > - ldr x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] > - msr mdccint_el1, x21 > + msr \type\()15_el1, x21 > + msr \type\()14_el1, x20 > + msr \type\()13_el1, x19 > + msr \type\()12_el1, x18 > + msr \type\()11_el1, x17 > + msr \type\()10_el1, x16 > + msr \type\()9_el1, x15 > + msr \type\()8_el1, x14 > + msr \type\()7_el1, x13 > + msr \type\()6_el1, x12 > + msr \type\()5_el1, x11 > + msr \type\()4_el1, x10 > + msr \type\()3_el1, x9 > + msr \type\()2_el1, x8 > + msr \type\()1_el1, x7 > + msr \type\()0_el1, x6 > .endm > > .macro skip_32bit_state tmp, target > @@ -887,12 +597,61 @@ __restore_sysregs: > restore_sysregs > ret > > +/* Save debug state */ > __save_debug: > - save_debug > + // x2: ptr to CPU context > + // x4/x5/x6-22/x24-26: trashed > + > + mrs x26, id_aa64dfr0_el1 > + ubfx x24, x26, #12, #4 // Extract BRPs > + ubfx x25, x26, #20, #4 // Extract WRPs > + mov w26, #15 > + sub w24, w26, w24 // How many BPs to skip > + sub w25, w26, w25 // How many WPs to skip > + > + mov x5, x24 > + add x4, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1) > + save_debug dbgbcr > + add x4, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1) > + save_debug dbgbvr > + > + mov x5, x25 > + add x4, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1) > + save_debug dbgwcr > + add x4, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1) > + save_debug dbgwvr > + > + mrs x21, mdccint_el1 > + str x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] > ret > > +/* Restore debug state */ > __restore_debug: > - restore_debug > + // x2: ptr to CPU context > + // x4/x5/x6-22/x24-26: trashed > + > + mrs x26, id_aa64dfr0_el1 > + ubfx x24, x26, #12, #4 // Extract BRPs > + ubfx x25, x26, #20, #4 // Extract WRPs > + mov w26, #15 > + sub w24, w26, w24 // How many BPs to skip > + sub w25, w26, w25 // How many WPs to skip > + > + mov x5, x24 > + add x4, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1) > + restore_debug dbgbcr > + add x4, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1) > + restore_debug dbgbvr > + > + mov x5, x25 > + add x4, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1) > + restore_debug dbgwcr > + add x4, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1) > + restore_debug dbgwvr > + > + ldr x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] > + msr mdccint_el1, x21 > + > ret > > __save_fpsimd: > -- > 2.4.3 > Besides the whitespace nit: Reviewed-by: Christoffer Dall <christoffer.dall@xxxxxxxxxx> -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
