diff options
Diffstat (limited to 'hw/intc/xive.c')
| -rw-r--r-- | hw/intc/xive.c | 205 |
1 files changed, 132 insertions, 73 deletions
diff --git a/hw/intc/xive.c b/hw/intc/xive.c index 139cfdf9bf..c77df2c1f8 100644 --- a/hw/intc/xive.c +++ b/hw/intc/xive.c @@ -3,8 +3,7 @@ * * Copyright (c) 2017-2018, IBM Corporation. * - * This code is licensed under the GPL version 2 or later. See the - * COPYING file in the top-level directory. + * SPDX-License-Identifier: GPL-2.0-or-later */ #include "qemu/osdep.h" @@ -27,28 +26,6 @@ * XIVE Thread Interrupt Management context */ -/* - * Convert an Interrupt Pending Buffer (IPB) register to a Pending - * Interrupt Priority Register (PIPR), which contains the priority of - * the most favored pending notification. - */ -static uint8_t ipb_to_pipr(uint8_t ibp) -{ - return ibp ? clz32((uint32_t)ibp << 24) : 0xff; -} - -static uint8_t exception_mask(uint8_t ring) -{ - switch (ring) { - case TM_QW1_OS: - return TM_QW1_NSR_EO; - case TM_QW3_HV_PHYS: - return TM_QW3_NSR_HE; - default: - g_assert_not_reached(); - } -} - static qemu_irq xive_tctx_output(XiveTCTX *tctx, uint8_t ring) { switch (ring) { @@ -68,11 +45,10 @@ static uint64_t xive_tctx_accept(XiveTCTX *tctx, uint8_t ring) { uint8_t *regs = &tctx->regs[ring]; uint8_t nsr = regs[TM_NSR]; - uint8_t mask = exception_mask(ring); qemu_irq_lower(xive_tctx_output(tctx, ring)); - if (regs[TM_NSR] & mask) { + if (regs[TM_NSR] != 0) { uint8_t cppr = regs[TM_PIPR]; uint8_t alt_ring; uint8_t *alt_regs; @@ -87,11 +63,18 @@ static uint64_t xive_tctx_accept(XiveTCTX *tctx, uint8_t ring) regs[TM_CPPR] = cppr; - /* Reset the pending buffer bit */ - alt_regs[TM_IPB] &= ~xive_priority_to_ipb(cppr); + /* + * If the interrupt was for a specific VP, reset the pending + * buffer bit, otherwise clear the logical server indicator + */ + if (regs[TM_NSR] & TM_NSR_GRP_LVL) { + regs[TM_NSR] &= ~TM_NSR_GRP_LVL; + } else { + alt_regs[TM_IPB] &= ~xive_priority_to_ipb(cppr); + } - /* Drop Exception bit */ - regs[TM_NSR] &= ~mask; + /* Drop the exception bit and any group/crowd */ + regs[TM_NSR] = 0; trace_xive_tctx_accept(tctx->cs->cpu_index, alt_ring, alt_regs[TM_IPB], regs[TM_PIPR], @@ -101,7 +84,7 @@ static uint64_t xive_tctx_accept(XiveTCTX *tctx, uint8_t ring) return ((uint64_t)nsr << 8) | regs[TM_CPPR]; } -static void xive_tctx_notify(XiveTCTX *tctx, uint8_t ring) +void xive_tctx_notify(XiveTCTX *tctx, uint8_t ring, uint8_t group_level) { /* HV_POOL ring uses HV_PHYS NSR, CPPR and PIPR registers */ uint8_t alt_ring = (ring == TM_QW2_HV_POOL) ? TM_QW3_HV_PHYS : ring; @@ -111,13 +94,13 @@ static void xive_tctx_notify(XiveTCTX *tctx, uint8_t ring) if (alt_regs[TM_PIPR] < alt_regs[TM_CPPR]) { switch (ring) { case TM_QW1_OS: - regs[TM_NSR] |= TM_QW1_NSR_EO; + regs[TM_NSR] = TM_QW1_NSR_EO | (group_level & 0x3F); break; case TM_QW2_HV_POOL: - alt_regs[TM_NSR] = (TM_QW3_NSR_HE_POOL << 6); + alt_regs[TM_NSR] = (TM_QW3_NSR_HE_POOL << 6) | (group_level & 0x3F); break; case TM_QW3_HV_PHYS: - regs[TM_NSR] |= (TM_QW3_NSR_HE_PHYS << 6); + regs[TM_NSR] = (TM_QW3_NSR_HE_PHYS << 6) | (group_level & 0x3F); break; default: g_assert_not_reached(); @@ -159,7 +142,7 @@ static void xive_tctx_set_cppr(XiveTCTX *tctx, uint8_t ring, uint8_t cppr) * Recompute the PIPR based on local pending interrupts. The PHYS * ring must take the minimum of both the PHYS and POOL PIPR values. */ - pipr_min = ipb_to_pipr(regs[TM_IPB]); + pipr_min = xive_ipb_to_pipr(regs[TM_IPB]); ring_min = ring; /* PHYS updates also depend on POOL values */ @@ -169,7 +152,7 @@ static void xive_tctx_set_cppr(XiveTCTX *tctx, uint8_t ring, uint8_t cppr) /* POOL values only matter if POOL ctx is valid */ if (pool_regs[TM_WORD2] & 0x80) { - uint8_t pool_pipr = ipb_to_pipr(pool_regs[TM_IPB]); + uint8_t pool_pipr = xive_ipb_to_pipr(pool_regs[TM_IPB]); /* * Determine highest priority interrupt and @@ -185,17 +168,27 @@ static void xive_tctx_set_cppr(XiveTCTX *tctx, uint8_t ring, uint8_t cppr) regs[TM_PIPR] = pipr_min; /* CPPR has changed, check if we need to raise a pending exception */ - xive_tctx_notify(tctx, ring_min); + xive_tctx_notify(tctx, ring_min, 0); } -void xive_tctx_ipb_update(XiveTCTX *tctx, uint8_t ring, uint8_t ipb) -{ +void xive_tctx_pipr_update(XiveTCTX *tctx, uint8_t ring, uint8_t priority, + uint8_t group_level) + { + /* HV_POOL ring uses HV_PHYS NSR, CPPR and PIPR registers */ + uint8_t alt_ring = (ring == TM_QW2_HV_POOL) ? TM_QW3_HV_PHYS : ring; + uint8_t *alt_regs = &tctx->regs[alt_ring]; uint8_t *regs = &tctx->regs[ring]; - regs[TM_IPB] |= ipb; - regs[TM_PIPR] = ipb_to_pipr(regs[TM_IPB]); - xive_tctx_notify(tctx, ring); -} + if (group_level == 0) { + /* VP-specific */ + regs[TM_IPB] |= xive_priority_to_ipb(priority); + alt_regs[TM_PIPR] = xive_ipb_to_pipr(regs[TM_IPB]); + } else { + /* VP-group */ + alt_regs[TM_PIPR] = xive_priority_to_pipr(priority); + } + xive_tctx_notify(tctx, ring, group_level); + } /* * XIVE Thread Interrupt Management Area (TIMA) @@ -411,13 +404,13 @@ static void xive_tm_set_os_lgs(XivePresenter *xptr, XiveTCTX *tctx, } /* - * Adjust the IPB to allow a CPU to process event queues of other + * Adjust the PIPR to allow a CPU to process event queues of other * priorities during one physical interrupt cycle. */ static void xive_tm_set_os_pending(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, uint64_t value, unsigned size) { - xive_tctx_ipb_update(tctx, TM_QW1_OS, xive_priority_to_ipb(value & 0xff)); + xive_tctx_pipr_update(tctx, TM_QW1_OS, value & 0xff, 0); } static void xive_os_cam_decode(uint32_t cam, uint8_t *nvt_blk, @@ -495,16 +488,20 @@ static void xive_tctx_need_resend(XiveRouter *xrtr, XiveTCTX *tctx, /* Reset the NVT value */ nvt.w4 = xive_set_field32(NVT_W4_IPB, nvt.w4, 0); xive_router_write_nvt(xrtr, nvt_blk, nvt_idx, &nvt, 4); + + uint8_t *regs = &tctx->regs[TM_QW1_OS]; + regs[TM_IPB] |= ipb; } + /* - * Always call xive_tctx_ipb_update(). Even if there were no + * Always call xive_tctx_pipr_update(). Even if there were no * escalation triggered, there could be a pending interrupt which * was saved when the context was pulled and that we need to take * into account by recalculating the PIPR (which is not * saved/restored). * It will also raise the External interrupt signal if needed. */ - xive_tctx_ipb_update(tctx, TM_QW1_OS, ipb); + xive_tctx_pipr_update(tctx, TM_QW1_OS, 0xFF, 0); /* fxb */ } /* @@ -592,7 +589,7 @@ static const XiveTmOp xive2_tm_operations[] = { * MMIOs below 2K : raw values and special operations without side * effects */ - { XIVE_TM_OS_PAGE, TM_QW1_OS + TM_CPPR, 1, xive_tm_set_os_cppr, + { XIVE_TM_OS_PAGE, TM_QW1_OS + TM_CPPR, 1, xive2_tm_set_os_cppr, NULL }, { XIVE_TM_HV_PAGE, TM_QW1_OS + TM_WORD2, 4, xive2_tm_push_os_ctx, NULL }, @@ -600,7 +597,7 @@ static const XiveTmOp xive2_tm_operations[] = { NULL }, { XIVE_TM_OS_PAGE, TM_QW1_OS + TM_LGS, 1, xive_tm_set_os_lgs, NULL }, - { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_CPPR, 1, xive_tm_set_hv_cppr, + { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_CPPR, 1, xive2_tm_set_hv_cppr, NULL }, { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, xive_tm_vt_push, NULL }, @@ -841,9 +838,9 @@ void xive_tctx_reset(XiveTCTX *tctx) * CPPR is first set. */ tctx->regs[TM_QW1_OS + TM_PIPR] = - ipb_to_pipr(tctx->regs[TM_QW1_OS + TM_IPB]); + xive_ipb_to_pipr(tctx->regs[TM_QW1_OS + TM_IPB]); tctx->regs[TM_QW3_HV_PHYS + TM_PIPR] = - ipb_to_pipr(tctx->regs[TM_QW3_HV_PHYS + TM_IPB]); + xive_ipb_to_pipr(tctx->regs[TM_QW3_HV_PHYS + TM_IPB]); } static void xive_tctx_realize(DeviceState *dev, Error **errp) @@ -1658,6 +1655,54 @@ static uint32_t xive_tctx_hw_cam_line(XivePresenter *xptr, XiveTCTX *tctx) return xive_nvt_cam_line(blk, 1 << 7 | (pir & 0x7f)); } +uint32_t xive_get_vpgroup_size(uint32_t nvp_index) +{ + /* + * Group size is a power of 2. The position of the first 0 + * (starting with the least significant bits) in the NVP index + * gives the size of the group. + */ + return 1 << (ctz32(~nvp_index) + 1); +} + +static uint8_t xive_get_group_level(bool crowd, bool ignore, + uint32_t nvp_blk, uint32_t nvp_index) +{ + uint8_t level; + + if (!ignore) { + g_assert(!crowd); + return 0; + } + + level = (ctz32(~nvp_index) + 1) & 0b1111; + if (crowd) { + uint32_t blk; + + /* crowd level is bit position of first 0 from the right in nvp_blk */ + blk = ctz32(~nvp_blk) + 1; + + /* + * Supported crowd sizes are 2^1, 2^2, and 2^4. 2^3 is not supported. + * HW will encode level 4 as the value 3. See xive2_pgofnext(). + */ + switch (level) { + case 1: + case 2: + break; + case 4: + blk = 3; + break; + default: + g_assert_not_reached(); + } + + /* Crowd level bits reside in upper 2 bits of the 6 bit group level */ + level |= blk << 4; + } + return level; +} + /* * The thread context register words are in big-endian format. */ @@ -1724,31 +1769,41 @@ int xive_presenter_tctx_match(XivePresenter *xptr, XiveTCTX *tctx, /* * This is our simple Xive Presenter Engine model. It is merged in the * Router as it does not require an extra object. - * - * It receives notification requests sent by the IVRE to find one - * matching NVT (or more) dispatched on the processor threads. In case - * of a single NVT notification, the process is abbreviated and the - * thread is signaled if a match is found. In case of a logical server - * notification (bits ignored at the end of the NVT identifier), the - * IVPE and IVRE select a winning thread using different filters. This - * involves 2 or 3 exchanges on the PowerBus that the model does not - * support. - * - * The parameters represent what is sent on the PowerBus */ bool xive_presenter_notify(XiveFabric *xfb, uint8_t format, uint8_t nvt_blk, uint32_t nvt_idx, - bool cam_ignore, uint8_t priority, - uint32_t logic_serv) + bool crowd, bool cam_ignore, uint8_t priority, + uint32_t logic_serv, bool *precluded) { XiveFabricClass *xfc = XIVE_FABRIC_GET_CLASS(xfb); - XiveTCTXMatch match = { .tctx = NULL, .ring = 0 }; + XiveTCTXMatch match = { .tctx = NULL, .ring = 0, .precluded = false }; + uint8_t group_level; int count; /* - * Ask the machine to scan the interrupt controllers for a match + * Ask the machine to scan the interrupt controllers for a match. + * + * For VP-specific notification, we expect at most one match and + * one call to the presenters is all we need (abbreviated notify + * sequence documented by the architecture). + * + * For VP-group notification, match_nvt() is the equivalent of the + * "histogram" and "poll" commands sent to the power bus to the + * presenters. 'count' could be more than one, but we always + * select the first match for now. 'precluded' tells if (at least) + * one thread matches but can't take the interrupt now because + * it's running at a more favored priority. We return the + * information to the router so that it can take appropriate + * actions (backlog, escalation, broadcast, etc...) + * + * If we were to implement a better way of dispatching the + * interrupt in case of multiple matches (instead of the first + * match), we would need a heuristic to elect a thread (for + * example, the hardware keeps track of an 'age' in the TIMA) and + * a new command to the presenters (the equivalent of the "assign" + * power bus command in the documented full notify sequence. */ - count = xfc->match_nvt(xfb, format, nvt_blk, nvt_idx, cam_ignore, + count = xfc->match_nvt(xfb, format, nvt_blk, nvt_idx, crowd, cam_ignore, priority, logic_serv, &match); if (count < 0) { return false; @@ -1756,9 +1811,11 @@ bool xive_presenter_notify(XiveFabric *xfb, uint8_t format, /* handle CPU exception delivery */ if (count) { - trace_xive_presenter_notify(nvt_blk, nvt_idx, match.ring); - xive_tctx_ipb_update(match.tctx, match.ring, - xive_priority_to_ipb(priority)); + group_level = xive_get_group_level(crowd, cam_ignore, nvt_blk, nvt_idx); + trace_xive_presenter_notify(nvt_blk, nvt_idx, match.ring, group_level); + xive_tctx_pipr_update(match.tctx, match.ring, priority, group_level); + } else { + *precluded = match.precluded; } return !!count; @@ -1798,7 +1855,7 @@ void xive_router_end_notify(XiveRouter *xrtr, XiveEAS *eas) uint8_t nvt_blk; uint32_t nvt_idx; XiveNVT nvt; - bool found; + bool found, precluded; uint8_t end_blk = xive_get_field64(EAS_END_BLOCK, eas->w); uint32_t end_idx = xive_get_field64(EAS_END_INDEX, eas->w); @@ -1879,10 +1936,12 @@ void xive_router_end_notify(XiveRouter *xrtr, XiveEAS *eas) } found = xive_presenter_notify(xrtr->xfb, format, nvt_blk, nvt_idx, + false /* crowd */, xive_get_field32(END_W7_F0_IGNORE, end.w7), priority, - xive_get_field32(END_W7_F1_LOG_SERVER_ID, end.w7)); - + xive_get_field32(END_W7_F1_LOG_SERVER_ID, end.w7), + &precluded); + /* we don't support VP-group notification on P9, so precluded is not used */ /* TODO: Auto EOI. */ if (found) { |